rebuild

1 files changed, 1 insertions, 1 deletions

diff --git a/site/datasets/final/coco.json b/site/datasets/final/coco.json
index 5e31a629..dbe4911f 100644
--- a/site/datasets/final/coco.json
+++ b/site/datasets/final/coco.json
@@ -1 +1 @@
-{"id": "5e0f8c355a37a5a89351c02f174e7a5ddcb98683", "dataset": {"key": "coco", "name_short": "COCO", "name_display": "COCO Dataset", "name_full": "Microsoft COCO: Common Objects in Context", "purpose": "object and scene recognition", "comment": "First published in 2014, revised in 2015: dataset split in two", "created_by": "", "funded_by": "", "funded_by_short": "", "used_by": "", "license": "", "url": "http://cocodataset.org/", "verify_do": "Y", "verify_done": "", "cooperative": "N", "dl_im": "Y", "dl_meta": "", "dl_paper": "", "dl_web": "", "mp_pub": "N", "ft_share": "Y", "nyt_share": "Y", "indoor": "", "outdoor": "", "campus": "", "cyberspace": "Y", "parent": "", "sources": "www, google, bing, flickr", "source_cat": "", "usernames": "", "names": "", "flickr_meta": "", "year_start": "", "year_end": "", "year_published": "2014", "ongoing": "", "images": "328,000 ", "videos": "", "tracklets": "", "identities": "", "img_per_person": "", "num_cameras": "", "faces_or_persons": "", "female": "", "male": "", "landmarks": "", "width": "", "height": "", "color": "Y", "gray": "", "tags": "ped_detect, obj", "size_gb": "", "agreement": "", "agreement_signed": "", "flickr": "", "facebook": "", "youtube": "", "vimeo": "", "google": "", "bing": "", "adam": "", "berit": "", "charlie": "Y", "notes": "", "derivative_of": "", "": ""}, "paper": {"paper_id": "5e0f8c355a37a5a89351c02f174e7a5ddcb98683", "key": "coco", "title": "Microsoft COCO: Common Objects in Context", "year": "2014", "pdf": ["https://arxiv.org/pdf/1405.0312.pdf"], "address": "", "name": "COCO", "doi": []}, "addresses": [], "additional_papers": [], "citations": [{"id": "8b9377ead9b05d0e5d86f7092ce5084841c146a4", "title": "Asking for Help with the Right Question by Predicting Human Visual Performance", "addresses": [{"name": "University of California, Santa Barbara", "source_name": "University of California, Santa Barbara", "street_adddress": "UCSB, Santa Barbara County, California, 93106, USA", "lat": "34.41459370", "lng": "-119.84581950", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/ebbc/4569b767323c5bf6917c0efdce5d172e721d.pdf"], "doi": []}, {"id": "133f1f2679892d408420d8092283539010723359", "title": "What Makes for Effective Detection Proposals?", "addresses": [{"name": "Max Planck Institute for Informatics", "source_name": "Max Planck Institute for Informatics", "street_adddress": "MPII, E1 4, Campus, Universit\u00e4t, Sankt Johann, Bezirk Mitte, Saarbr\u00fccken, Regionalverband Saarbr\u00fccken, Saarland, 66123, Deutschland", "lat": "49.25795660", "lng": "7.04577417", "type": "edu", "country": "Germany"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1502.05082.pdf"], "doi": []}, {"id": "e0ef2d1e9bcde8da814bf510a31ce3dc90919ed8", "title": "SHPD: Surveillance Human Pose Dataset and Performance Evaluation for Coarse-Grained Pose Estimation", "addresses": [{"name": "Shanghai Jiao Tong University", "source_name": "Shanghai Jiao Tong University", "street_adddress": "\u4e0a\u6d77\u4ea4\u901a\u5927\u5b66\uff08\u5f90\u6c47\u6821\u533a\uff09, \u6dee\u6d77\u897f\u8def, \u756a\u79ba\u5c0f\u533a, \u5e73\u9634\u6865, \u5f90\u6c47\u533a, \u4e0a\u6d77\u5e02, 200052, \u4e2d\u56fd", "lat": "31.20081505", "lng": "121.42840681", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8451116", "http://doi.org/10.1109/ICIP.2018.8451116"]}, {"id": "55761bdf5cbbff5fbede8ee9d0573d1561a9254b", "title": "The Impact of Visual Saliency Prediction in Image Classification", "addresses": [{"name": "Dublin City University", "source_name": "DUBLIN CITY UNIVERSITY", "street_adddress": "Dublin City University Glasnevin Campus, Lower Car Park, Wad, Whitehall A ED, Dublin 9, Dublin, County Dublin, Leinster, D09 FW22, Ireland", "lat": "53.38522185", "lng": "-6.25740874", "type": "edu", "country": "Ireland"}, {"name": "Universitat Politecnica de Catalunya", "source_name": "Universitat Politcnica de Catalunya, EU, Spain", "street_adddress": "Campus Nord, Carrer de Jordi Girona, 1, 3, 08034 Barcelona, Spain", "lat": "41.38800400", "lng": "2.11328040", "type": "edu", "country": "Spain"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/5576/1bdf5cbbff5fbede8ee9d0573d1561a9254b.pdf"], "doi": []}, {"id": "a31a01827d809673a641877f21759633936d7da5", "title": "Reducing Network Agnostophobia", "addresses": [{"name": "University of Colorado, Colorado Springs", "source_name": "University of Colorado Colorado Springs", "street_adddress": "Main Hall, The Spine, Colorado Springs, El Paso County, Colorado, 80907, USA", "lat": "38.89207560", "lng": "-104.79716389", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.04110.pdf"], "doi": []}, {"id": "12a91c9d4a55fc93f15f4acef078c8908af3c9b9", "title": "Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.01642.pdf"], "doi": []}, {"id": "c32b66a9badc57e416cf15287c9c8861b264805b", "title": "Towards Closing the Gap in Weakly Supervised Semantic Segmentation with DCNNs: Combining Local and Global Models.", "addresses": [{"name": "ETH Z\u00fcrich", "source_name": "ETH Z\u00fcrich", "street_adddress": "ETH Z\u00fcrich, 101, R\u00e4mistrasse, Hochschulen, Altstadt, Z\u00fcrich, Bezirk Z\u00fcrich, Z\u00fcrich, 8092, Schweiz/Suisse/Svizzera/Svizra", "lat": "47.37645340", "lng": "8.54770931", "type": "edu", "country": "Switzerland"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.01625.pdf"], "doi": []}, {"id": "02a4462e6c63007dda36ca5305f6b57d03f1316f", "title": "The Real-Time Detection of Traffic Participants Using YOLO Algorithm", "addresses": [{"name": "RT-RK, Institute for Computer Based Systems, Novi Sad, Serbia", "source_name": "RT-RK, Institute for Computer Based Systems, Novi Sad, Serbia", "street_adddress": "Narodnog fronta 23A, Novi Sad 21000, Serbia", "lat": "45.23963230", "lng": "19.83640040", "type": "edu", "country": "Serbia"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8611986"]}, {"id": "0754d3d8fbae668880a3eb91b2bce89543ea467e", "title": "Natural Language Driven Image Edits using a Semantic Image Manipulation Language (SIMPL)", "addresses": [{"name": "Virginia Tech", "source_name": "Virginia Tech", "street_adddress": "Blacksburg, VA 24061, USA", "lat": "37.22838430", "lng": "-80.42341670", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/0754/d3d8fbae668880a3eb91b2bce89543ea467e.pdf"], "doi": []}, {"id": "47067114c681e93322a9152fe7ceb7a9178bb32b", "title": "Monitoring Scene Understanders with Conceptual Primitive Decomposition and Commonsense Knowledge", "addresses": [{"name": "MIT", "source_name": "Massachusetts Institute", "street_adddress": "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/4706/7114c681e93322a9152fe7ceb7a9178bb32b.pdf"], "doi": []}, {"id": "fbaceba60619d9f76f7acf6e639669cd6150049e", "title": "Automatic Semantic Content Removal by Learning to Neglect.", "addresses": [{"name": "University of California, Santa Cruz", "source_name": "University of California, Santa Cruz, Santa Cruz", "street_adddress": "1156 High St, Santa Cruz, CA 95064, USA", "lat": "36.99158470", "lng": "-122.05827710", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.07696.pdf"], "doi": []}, {"id": "b5cd9e5d81d14868f1a86ca4f3fab079f63a366d", "title": "Tag-based video retrieval by embedding semantic content in a continuous word space", "addresses": [{"name": "University of Southern California", "source_name": "University of Southern California", "street_adddress": "University of Southern California, Watt Way, Saint James Park, LA, Los Angeles County, California, 90089, USA", "lat": "34.02241490", "lng": "-118.28634407", "type": "edu", "country": "United States"}, {"name": "University of Amsterdam", "source_name": "University of Amsterdam", "street_adddress": "Institute for Logic, Language and Computation (ILLC), 107, Science Park, Oost-Watergraafsmeer, Amsterdam, Oost, Amsterdam, Noord-Holland, Nederland, 1098XG, Nederland", "lat": "52.35536550", "lng": "4.95016440", "type": "edu", "country": "Netherlands"}], "year": "2016", "pdf": ["https://ivi.fnwi.uva.nl/isis/publications/2016/AgharwalWCACV2016/AgharwalWCACV2016.pdf", "https://pure.uva.nl/ws/files/2779402/175913_AgharwalWCACV2016.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7477706", "http://doi.ieeecomputersociety.org/10.1109/WACV.2016.7477706", "http://doi.org/10.1109/WACV.2016.7477706"]}, {"id": "6e3e5f5fac0bfe1d54d6d414a1a8c2d8de586eee", "title": "Design Pseudo Ground Truth with Motion Cue for Unsupervised Video Object Segmentation.", "addresses": [{"name": "University of Southern California", "source_name": "University of Southern California", "street_adddress": "University of Southern California, Watt Way, Saint James Park, LA, Los Angeles County, California, 90089, USA", "lat": "34.02241490", "lng": "-118.28634407", "type": "edu", "country": "United States"}, {"name": "National Taiwan University", "source_name": "National Taiwan University", "street_adddress": "\u81fa\u5927;\u53f0\u5927, 1, \u7f85\u65af\u798f\u8def\u56db\u6bb5, \u5b78\u5e9c\u91cc, \u5927\u5b89\u5340, \u81fa\u5317\u5e02, 10617, \u81fa\u7063", "lat": "25.01682835", "lng": "121.53846924", "type": "edu", "country": "Taiwan"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.05206.pdf"], "doi": []}, {"id": "c486eeced06b1db66b7deb58496d71074b88fb86", "title": "ScratchDet: Exploring to Train Single-Shot Object Detectors from Scratch", "addresses": [{"name": "University of Chinese Academy of Sciences", "source_name": "University of Chinese Academy of Sciences", "street_adddress": "University of Chinese Academy of Sciences, UCAS, Yuquanlu, \u7389\u6cc9\u8def, \u7530\u6751, \u6d77\u6dc0\u533a, 100049, \u4e2d\u56fd", "lat": "39.90828040", "lng": "116.24585270", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.08425.pdf"], "doi": []}, {"id": "a3c93737a4497350768b0dda08dbc0826670dc5b", "title": "Diagnosing State-Of-The-Art Object Proposal Methods", "addresses": [{"name": "A*STAR", "source_name": "I2R, A*STAR, Singapore", "street_adddress": "1 Fusionopolis Way, #21-01 Connexis, Singapore 138632", "lat": "1.29889260", "lng": "103.78731070", "type": "edu", "country": "Singapore"}, {"name": "Nanyang Technological University", "source_name": "Nanyang Technological University", "street_adddress": "NTU, Faculty Avenue, Jurong West, Southwest, 637460, Singapore", "lat": "1.34841040", "lng": "103.68297965", "type": "edu", "country": "Singapore"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1507.04512.pdf"], "doi": []}, {"id": "bc2856e70ad3c8fe439dec6cc6a2e03d6e090fb7", "title": "What value high level concepts in vision to language problems ?", "addresses": [{"name": "University of Adelaide", "source_name": "University of Adelaide", "street_adddress": "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu", "country": "Australia"}], "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/ffcc/bb8218b3af88fb7ea9dcd89557cd0156fba7.pdf"], "doi": []}, {"id": "365117e2e47b83ec70014058de13d167619094ad", "title": "Adaptive Object Detection Using Adjacency and Zoom Prediction", "addresses": [{"name": "University of California, San Diego", "source_name": "University of California, San Diego", "street_adddress": "UCSD, 9500, Gilman Drive, Sixth College, University City, San Diego, San Diego County, California, 92093, USA", "lat": "32.87935255", "lng": "-117.23110049", "type": "edu", "country": "United States"}, {"name": "University of Illinois, Urbana-Champaign", "source_name": "University of Illinois, Urbana-Champaign", "street_adddress": "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1512.07711.pdf"], "doi": []}, {"id": "ad5950257e053b08657ea298f7b89ba358b8bfcf", "title": "Textually Enriched Neural Module Networks for Visual Question Answering", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.08697.pdf"], "doi": []}, {"id": "01efec88d36070dc3bc49f341a77476f74d373bc", "title": "Generation and Comprehension of Unambiguous Object Descriptions", "addresses": [{"name": "Google", "source_name": "Google, Inc.", "street_adddress": "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "lat": "37.42199990", "lng": "-122.08405750", "type": "company", "country": "United States"}, {"name": "UCLA", "source_name": "University of California, Los Angeles", "street_adddress": "Los Angeles, CA 90095, USA", "lat": "34.06892100", "lng": "-118.44518110", "type": "edu", "country": "United States"}, {"name": "University of Oxford", "source_name": "University of Oxford", "street_adddress": "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "lat": "51.75345380", "lng": "-1.25400997", "type": "edu", "country": "United Kingdom"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1511.02283.pdf"], "doi": []}, {"id": "2c3e7392b865b228f5d56ab025cd3123554be5e1", "title": "Linguistic Unit Discovery from Multi-Modal Inputs in Unwritten Languages: Summary of the \u201cSpeaking Rosetta\u201d JSALT 2017 Workshop", "addresses": [{"name": "Radboud University", "source_name": "Radboud University, Nijmegen, Netherlands", "street_adddress": "Houtlaan 4, 6525 XZ Nijmegen, Netherlands", "lat": "51.81670100", "lng": "5.86527200", "type": "edu", "country": "Netherlands"}, {"name": "University of Illinois", "source_name": "Advanced Digital Sciences Center (ADSC) of the University of Illinois, Singapore, Singapore", "street_adddress": "1 Create Way, 14-02 Create Tower, Singapore 138602", "lat": "1.30372570", "lng": "103.77377630", "type": "edu", "country": "Singapore"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.05092.pdf"], "doi": []}, {"id": "8b6493a65285fb72252221e7ef8ad1091bd96b32", "title": "TRAFFIC ANALYSIS USING VISUAL OBJECT DETECTION AND TRACKING", "addresses": [{"name": "University at Albany", "source_name": "University at Albany, SUNY, 12222, United States", "street_adddress": "1400 Washington Ave, Albany, NY 12222, USA", "lat": "42.68502730", "lng": "-73.82479030", "type": "edu", "country": "United States"}, {"name": "University of Chinese Academy of Sciences", "source_name": "University of Chinese Academy of Sciences", "street_adddress": "University of Chinese Academy of Sciences, UCAS, Yuquanlu, \u7389\u6cc9\u8def, \u7530\u6751, \u6d77\u6dc0\u533a, 100049, \u4e2d\u56fd", "lat": "39.90828040", "lng": "116.24585270", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/8b64/93a65285fb72252221e7ef8ad1091bd96b32.pdf"], "doi": []}, {"id": "7ce9e79cb63e33faa3be0c534664076e420dd7a1", "title": "Semantic Segmentation of Complex Road Environments from Aerial Images Using Convolutional Neural Networks", "addresses": [{"name": "US Army Engineer Research and Development Center, Vicksburg, MS", "source_name": "Information Technology Laboratory, U.S. Army Engineer Research and Development Center, Vicksburg, MS, United States", "street_adddress": "3909 Halls Ferry Rd, Vicksburg, MS 39180, USA", "lat": "32.30127170", "lng": "-90.87140670", "type": "mil", "country": "United States"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8622284", "http://doi.org/10.1109/BigData.2018.8622284"]}, {"id": "2281d8282dc6315eaa5c31821310c1a349ea18b0", "title": "Fast Efficient Object Detection Using Selective Attention", "addresses": [{"name": "RMIT University", "source_name": "RMIT University", "street_adddress": "RMIT University, 124, La Trobe Street, Melbourne City, City of Melbourne, Victoria, 3000, Australia", "lat": "-37.80874650", "lng": "144.96388750", "type": "edu", "country": "Australia"}, {"name": "University of Tokyo", "source_name": "University of Tokyo", "street_adddress": "\u6771\u4eac\u5927\u5b66 \u67cf\u30ad\u30e3\u30f3\u30d1\u30b9, \u5b66\u878d\u5408\u306e\u9053, \u67cf\u5e02, \u5343\u8449\u770c, \u95a2\u6771\u5730\u65b9, 277-8583, \u65e5\u672c", "lat": "35.90204480", "lng": "139.93622009", "type": "edu", "country": "Japan"}, {"name": "IBM Research, North Carolina", "source_name": "IBM Research", "street_adddress": "IBM, East Cornwallis Road, Research Triangle Park, Nelson, Durham County, North Carolina, 27709, USA", "lat": "35.90422720", "lng": "-78.85565763", "type": "company", "country": "United States"}, {"name": "University of Sydney", "source_name": "University of Sydney", "street_adddress": "USyd, Fisher Road, Camperdown, Sydney, NSW, 2006, Australia", "lat": "-33.88890695", "lng": "151.18943366", "type": "edu", "country": "Australia"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.07502.pdf"], "doi": []}, {"id": "7bfa04eb7ba2830a682a15206370abec49cffd2a", "title": "Learning Semantic Segmentation from Synthetic Data: A Geometrically Guided Input-Output Adaptation Approach", "addresses": [{"name": "Computer Vision Laboratory, ETH Zurich", "source_name": "Computer Vision Laboratory ETH Zurich, UK", "street_adddress": "Sternwartstrasse 7, 8092 Z\u00fcrich, Switzerland", "lat": "47.37723980", "lng": "8.55216180", "type": "edu", "country": "Switzerland"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.05040.pdf"], "doi": []}, {"id": "0871062654a6ddd18dba940009676aaa1230f879", "title": "Road Damage Detection And Classification In Smartphone Captured Images Using Mask R-CNN", "addresses": [{"name": "Indian Institute of Science Bangalore", "source_name": "Indian Institute of Science Bangalore", "street_adddress": "IISc, Gulmohar Marg, RMV Stage II - 1st Block, Aramane Nagara Ward, West Zone, Bengaluru, Bangalore Urban, Karnataka, 560012, India", "lat": "13.02223470", "lng": "77.56718325", "type": "edu", "country": "India"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.04535.pdf"], "doi": []}, {"id": "ce142b327974580b297fb84c2c1c799f838bdda5", "title": "VADRA: Visual Adversarial Domain Randomization and Augmentation", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.00491.pdf"], "doi": []}, {"id": "6b6afc9557dc0670bf2792bde4c4389ac52c707f", "title": "What Action Causes This? Towards Naive Physical Action-Effect Prediction", "addresses": [{"name": "Michigan State University", "source_name": "Michigan State University", "street_adddress": "Michigan State University, Farm Lane, East Lansing, Ingham County, Michigan, 48824, USA", "lat": "42.71856800", "lng": "-84.47791571", "type": "edu", "country": "United States"}, {"name": "Microsoft", "source_name": "Microsoft Corporation, Redmond, WA, USA", "street_adddress": "One Microsoft Way, Redmond, WA 98052, USA", "lat": "47.64233180", "lng": "-122.13693020", "type": "company", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/fa4f/7ec0d1a3e67c6170638a9502cbad81873b9c.pdf"], "doi": []}, {"id": "1536579229a334640735725e0b886f8d03aca1e8", "title": "Rank of Experts: Detection Network Ensemble", "addresses": [{"name": "Incheon National University", "source_name": "Incheon National University, Incheon, South Korea", "street_adddress": "119 Academy-ro, Songdo 1(il)-dong, Yeonsu-gu, Incheon, South Korea", "lat": "37.37505480", "lng": "126.63289980", "type": "edu", "country": "South Korea"}, {"name": "Electronics and Telecommunications Research Institute, Daejeon, South Korea", "source_name": "Electronics and Telecommunications Research Institute, Daejeon, South Korea", "street_adddress": "Electronics and Telecommunications Research Institute, Sinseong-dong, Daejeon, South Korea", "lat": "36.38376500", "lng": "127.36694000", "type": "edu", "country": "South Korea"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1712.00185.pdf"], "doi": []}, {"id": "19441b8be551e8134dd9eb33238309bc2de0a42f", "title": "Playing for Benchmarks", "addresses": [{"name": "TU Darmstadt", "source_name": "TU Darmstadt", "street_adddress": "Karolinenpl. 5, 64289 Darmstadt, Germany", "lat": "49.87482770", "lng": "8.65632810", "type": "edu", "country": "Germany"}, {"name": "Intel Labs", "source_name": "Intel Labs", "street_adddress": "4720 Forbes Ave, Pittsburgh, PA 15213, USA", "lat": "40.44397890", "lng": "-79.94646340", "type": "company", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1709.07322.pdf"], "doi": []}, {"id": "597bca76d9c983f0b71ff1143d80ea91bf97cb25", "title": "Semi-automatic video object segmentation by advanced manipulation of segmentation hierarchies", "addresses": [{"name": "Disney Research Zurich", "source_name": "Disney Research Zurich", "street_adddress": "Stampfenbachstrasse 48, 8006 Z\u00fcrich, Switzerland", "lat": "47.38047690", "lng": "8.54299640", "type": "company", "country": "Switzerland"}], "year": "2015", "pdf": ["http://www.disneyresearch.com/wp-content/uploads/Semi-Automatic-Video-Object-Segmentation-by-Advanced-Manipulation-of-Segmentation-Hierarchies-Paper.pdf", "https://s3-us-west-1.amazonaws.com/disneyresearch/wp-content/uploads/20150605225535/Semi-Automatic-Video-Object-Segmentation-by-Advanced-Manipulation-of-Segmentation-Hierarchies-Paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7153600", "http://doi.org/10.1109/CBMI.2015.7153600"]}, {"id": "db7e48d2655521c1a89b579d8cb839a95d6e6a14", "title": "Boosted Attention: Leveraging Human Attention for Image Captioning", "addresses": [{"name": "University of Minnesota", "source_name": "University of Minnesota", "street_adddress": "WeismanArt, 333, East River Parkway, Marcy-Holmes, Phillips, Minneapolis, Hennepin County, Minnesota, 55455, USA", "lat": "44.97308605", "lng": "-93.23708813", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/db7e/48d2655521c1a89b579d8cb839a95d6e6a14.pdf"], "doi": []}, {"id": "28bf62416b5b0f3ca87332b83c3944f515505f66", "title": "Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks", "addresses": [{"name": "University of Oxford", "source_name": "University of Oxford", "street_adddress": "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "lat": "51.75345380", "lng": "-1.25400997", "type": "edu", "country": "United Kingdom"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.12348.pdf"], "doi": []}, {"id": "3081b725e1764ec754bee1fe5487000b7adf7936", "title": "Slum Segmentation and Change Detection : A Deep Learning Approach", "addresses": [{"name": "Indian Institute of Science Bangalore", "source_name": "Indian Institute of Science Bangalore", "street_adddress": "IISc, Gulmohar Marg, RMV Stage II - 1st Block, Aramane Nagara Ward, West Zone, Bengaluru, Bangalore Urban, Karnataka, 560012, India", "lat": "13.02223470", "lng": "77.56718325", "type": "edu", "country": "India"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.07896.pdf"], "doi": []}, {"id": "35159d9a4b77f5f8ec63f96822316eb4f7aacb1b", "title": "Training Deep Networks with Structured Layers by Matrix Backpropagation", "addresses": [{"name": "Lund University", "source_name": "Lund University", "street_adddress": "TEM at Lund University, 9, Klostergatan, Stadsk\u00e4rnan, Centrum, Lund, Sk\u00e5ne, G\u00f6taland, 22222, Sverige", "lat": "55.70395710", "lng": "13.19020110", "type": "edu", "country": "Sweden"}, {"name": "University of Bonn", "source_name": "University of Bonn", "street_adddress": "Rheinische Friedrich-Wilhelms-Universit\u00e4t Bonn, Arkadenhof, Bonn-Zentrum, Stadtbezirk Bonn, Bonn, Regierungsbezirk K\u00f6ln, Nordrhein-Westfalen, 53113, Deutschland", "lat": "50.73381240", "lng": "7.10224650", "type": "edu", "country": "Germany"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1509.07838.pdf"], "doi": []}, {"id": "c32b09f20badd9ce04309d7c5ebea88336a3345a", "title": "Token-level and sequence-level loss smoothing for RNN language models", "addresses": [{"name": "INRIA", "source_name": "INRIA Grenoble Rhone-Alpes, Grenoble, France", "street_adddress": "655 Avenue de l'Europe, 38330 Montbonnot-Saint-Martin, France", "lat": "45.21788600", "lng": "5.80736900", "type": "edu", "country": "France"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.05062.pdf"], "doi": []}, {"id": "4cb2d5ea093d52a9dbb5141bde20cbea576efa24", "title": "A cascaded long short-term memory (LSTM) driven generic visual question answering (VQA)", "addresses": [{"name": "Queensland University of Technology", "source_name": "Queensland University of Technology", "street_adddress": "Queensland University of Technology, Macgregor Lane, Merthyr, South Brisbane, Brisbane, QLD, 4000, Australia", "lat": "-27.47715625", "lng": "153.02841004", "type": "edu", "country": "Australia"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8296600", "http://doi.org/10.1109/ICIP.2017.8296600"]}, {"id": "c45681fa9d9c36a6a196017ef283ac38904f91bb", "title": "Pixel-wise object tracking", "addresses": [{"name": "New York University", "source_name": "New York University", "street_adddress": "NYU, West 4th Street, NoHo Historic District, NoHo, Manhattan, Manhattan Community Board 2, New York County, NYC, New York, 10012, USA", "lat": "40.72925325", "lng": "-73.99625394", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1711.07377.pdf"], "doi": []}, {"id": "27e15e5ae496a228653b69195e7d62a758b73cfa", "title": "Adversarial Removal of Gender from Deep Image Representations", "addresses": [{"name": "University of Virginia", "source_name": "University of Virginia", "street_adddress": "University of Virginia, Rotunda Alley, Carr's Hill, Albemarle County, Virginia, 22904-4119, USA", "lat": "38.03536820", "lng": "-78.50353220", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.08489.pdf"], "doi": []}, {"id": "eddd45f8b2febf3800db7642357731cb63116acc", "title": "On the Effects of Spam Filtering and Incremental Learning for Web-Supervised Visual Concept Classification", "addresses": [{"name": "Leibniz Universit\u00e4t Hannover, Hannover, Germany", "source_name": "Leibniz Universit\u00e4t Hannover, Hannover, Germany", "street_adddress": "Welfengarten 1, 30167 Hannover, Germany", "lat": "52.38296410", "lng": "9.71969890", "type": "edu", "country": "Germany"}], "year": "2016", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=2912072"]}, {"id": "f2653257faa6d1b718a4cff004f4c7ad66d89c55", "title": "Advances in deep learning approaches for image tagging", "addresses": [{"name": "Microsoft", "source_name": "Microsoft Corporation, Redmond, WA, USA", "street_adddress": "One Microsoft Way, Redmond, WA 98052, USA", "lat": "47.64233180", "lng": "-122.13693020", "type": "company", "country": "United States"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/f265/3257faa6d1b718a4cff004f4c7ad66d89c55.pdf"], "doi": []}, {"id": "5b610d9492a940d3e64bbf0cea8de4622e07d8b4", "title": "Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning", "addresses": [{"name": "Cornell University", "source_name": "Cornell University", "street_adddress": "Cornell University, Forest Home Drive, Forest Home, Tompkins County, New York, 14853, USA", "lat": "42.45055070", "lng": "-76.47835130", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.06193.pdf"], "doi": []}, {"id": "0ab65b963f8b71e31bfec188056023147f75303e", "title": "SPNet: Superpixel Pyramid Network for Scene Parsing", "addresses": [{"name": "Beijing University of Technologyy", "source_name": "Faculty of Information Technology, Beijing University of Technologyy, Beijing, 100124, China", "street_adddress": "Chaoyang, China, 100124", "lat": "39.87161100", "lng": "116.47952900", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8623025"]}, {"id": "98025d3d44e9379736adb1228919272ded9298ae", "title": "Visual Question Answering Dataset for Bilingual Image Understanding: A Study of Cross-Lingual Transfer Using Attention Maps", "addresses": [{"name": "Tokyo Institute of Technology", "source_name": "Tokyo Institute of Technology", "street_adddress": "\u6771\u4eac\u5de5\u696d\u5927\u5b66, \u539a\u6728\u8857\u9053, \u7dd1\u533a, \u753a\u7530\u5e02, \u795e\u5948\u5ddd\u770c, \u95a2\u6771\u5730\u65b9, 226-0026, \u65e5\u672c", "lat": "35.51675380", "lng": "139.48342251", "type": "edu", "country": "Japan"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/9802/5d3d44e9379736adb1228919272ded9298ae.pdf"], "doi": []}, {"id": "eea248baa16162da661fbb9255e2cfcd5b9f0c05", "title": "Bachelor Project Image Captioning with Convolutional Neural Networks", "addresses": [{"name": "Czech Technical University", "source_name": "Czech Technical University", "street_adddress": "\u010cesk\u00e9 vysok\u00e9 u\u010den\u00ed technick\u00e9 v Praze, Resslova, Nov\u00e9 M\u011bsto, Praha, okres Hlavn\u00ed m\u011bsto Praha, Hlavn\u00ed m\u011bsto Praha, Praha, 11121, \u010cesko", "lat": "50.07642960", "lng": "14.41802312", "type": "edu", "country": "Czech Republic"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/eea2/48baa16162da661fbb9255e2cfcd5b9f0c05.pdf"], "doi": []}, {"id": "cc5d91b20c8769d1f040ff9a5166f76cc19d2d55", "title": "Self-Supervised Learning of Visual Features through Embedding Images into Text Topic Spaces", "addresses": [{"name": "CVIT, KCIS, IIIT Hyderabad, India", "source_name": "CVIT, KCIS, IIIT Hyderabad, India", "street_adddress": "IIIT, Gachibowli, Gachibowli, Hyderabad, Telangana 500032, India", "lat": "17.44509810", "lng": "78.34976780", "type": "edu", "country": "India"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.08631.pdf"], "doi": []}, {"id": "233b52f79d37363d924041e047c6b9d9609cbb17", "title": "Refining faster-RCNN for accurate object detection", "addresses": [{"name": "Kakao Corp.", "source_name": "Kakao corp., 242, Cheomdan-ro, Jeju-si, Jeju-do, Korea", "street_adddress": "242 Cheomdan-ro, Ara-dong, Cheju, Jeju-do, South Korea", "lat": "33.45073890", "lng": "126.57079340", "type": "company", "country": "South Korea"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7986913"]}, {"id": "32bc9334ad0edaec29540320b9f00c9a7aab81f8", "title": "Zero-Shot Object Detection", "addresses": [{"name": "University of Maryland", "source_name": "University of Maryland", "street_adddress": "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu", "country": "United States"}, {"name": "SRI International", "source_name": "SRI International", "street_adddress": "SRI International Building, West 1st Street, Menlo Park, San Mateo County, California, 94025, USA", "lat": "37.45857960", "lng": "-122.17560525", "type": "edu", "country": "United States"}, {"name": "NEC Labs, Cupertino, CA", "source_name": "NEC Labs, Cupertino, CA", "street_adddress": "10080 N Wolfe Rd # Sw3350, Cupertino, CA 95014, USA", "lat": "37.32391770", "lng": "-122.01296930", "type": "company", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.04340.pdf"], "doi": []}, {"id": "2d541bf669dda499f86b4dd2ac4e263134a3cd4c", "title": "Pixel Objectness", "addresses": [{"name": "University of Texas at Austin", "source_name": "University of Texas at Austin", "street_adddress": "University of Texas at Austin, 1, East 23rd Street, The Drag, Austin, Travis County, Texas, 78712, USA", "lat": "30.28415100", "lng": "-97.73195598", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1701.05349.pdf"], "doi": []}, {"id": "b9dc8cc479cacda1f23b91df00eb03f88cc0c260", "title": "Event Specific Multimodal Pattern Mining for Knowledge Base Construction", "addresses": [{"name": "Columbia Univeristy, New York, NY, USA", "source_name": "Columbia Univeristy, New York, NY, USA", "street_adddress": "116th St & Broadway, New York, NY 10027, United States", "lat": "40.80753550", "lng": "-73.96257270", "type": "edu", "country": "United States"}, {"name": "Rensselaer Polytechnic Institute", "source_name": "Rensselaer Polytechnic Institute", "street_adddress": "Rensselaer Polytechnic Institute, Sage Avenue, Downtown, City of Troy, Rensselaer County, New York, 12180, USA", "lat": "42.72984590", "lng": "-73.67950216", "type": "edu", "country": "United States"}], "year": "2016", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=2964287"]}, {"id": "9528e2e8c20517ab916f803c0371abb4f0ed488b", "title": "Shallow and Deep Convolutional Networks for Saliency Prediction", "addresses": [{"name": "Universitat Politecnica de Catalunya", "source_name": "Universitat Politcnica de Catalunya, EU, Spain", "street_adddress": "Campus Nord, Carrer de Jordi Girona, 1, 3, 08034 Barcelona, Spain", "lat": "41.38800400", "lng": "2.11328040", "type": "edu", "country": "Spain"}, {"name": "Dublin City University", "source_name": "DUBLIN CITY UNIVERSITY", "street_adddress": "Dublin City University Glasnevin Campus, Lower Car Park, Wad, Whitehall A ED, Dublin 9, Dublin, County Dublin, Leinster, D09 FW22, Ireland", "lat": "53.38522185", "lng": "-6.25740874", "type": "edu", "country": "Ireland"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1603.00845.pdf"], "doi": []}, {"id": "3ea8d289313b0fe14031ea0d29f517f92a3b0fd3", "title": "Probability-based Detection Quality (PDQ): A Probabilistic Approach to Detection Evaluation", "addresses": [{"name": "Queensland University of Technology (QUT)", "source_name": "Queensland University of Technology (QUT)", "street_adddress": "2 George St, Brisbane City QLD 4000, Australia", "lat": "-27.47735700", "lng": "153.02841500", "type": "edu", "country": "Australia"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.10800.pdf"], "doi": []}, {"id": "98735e57075ed6e8ef9d98d7ca4895013492e35b", "title": "Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbation", "addresses": [{"name": "Pennsylvania State University", "source_name": "Pennsylvania State University", "street_adddress": "Old Main, State College, PA 16801, USA", "lat": "40.79821330", "lng": "-77.85990840", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.10307.pdf"], "doi": []}, {"id": "36679b7ea9eb8418410db7a6e2f15aeaf1b8e059", "title": "Weakly Supervised Vehicle Detection in Satellite Images via Multiple Instance Ranking", "addresses": [{"name": "Xiamen University", "source_name": "Xiamen University", "street_adddress": "\u53a6\u95e8\u5927\u5b66, \u601d\u660e\u5357\u8def Siming South Road, \u601d\u660e\u533a, \u601d\u660e\u533a (Siming), \u53a6\u95e8\u5e02 / Xiamen, \u798f\u5efa\u7701, 361005, \u4e2d\u56fd", "lat": "24.43994190", "lng": "118.09301781", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8546267", "http://doi.ieeecomputersociety.org/10.1109/ICPR.2018.8546267", "http://doi.org/10.1109/ICPR.2018.8546267"]}, {"id": "0e0fbead3da9e16b03894b63efc6816fa3ef6d0e", "title": "Open-vocabulary Phrase Detection", "addresses": [{"name": "Boston University", "source_name": "Boston University", "street_adddress": "BU, Bay State Road, Fenway, Boston, Suffolk County, Massachusetts, 02215, USA", "lat": "42.35042530", "lng": "-71.10056114", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.07212.pdf"], "doi": []}, {"id": "51f5e7b847e65a4cd0634ed9efc6b19819742b70", "title": "End-to-End Airplane Detection Using Transfer Learning in Remote Sensing Images", "addresses": [{"name": "Huazhong University of Science and Technology", "source_name": "Huazhong University of Science and Technology", "street_adddress": "\u534e\u4e2d\u5927, \u73de\u55bb\u8def, \u4e1c\u6e56\u65b0\u6280\u672f\u5f00\u53d1\u533a, \u5173\u4e1c\u8857\u9053, \u4e1c\u6e56\u65b0\u6280\u672f\u5f00\u53d1\u533a\uff08\u6258\u7ba1\uff09, \u6d2a\u5c71\u533a (Hongshan), \u6b66\u6c49\u5e02, \u6e56\u5317\u7701, 430074, \u4e2d\u56fd", "lat": "30.50975370", "lng": "114.40628810", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/51f5/e7b847e65a4cd0634ed9efc6b19819742b70.pdf"], "doi": []}, {"id": "18f9a6045ba01cb079c4fa49a630d71bbd27cd92", "title": "A dataset of clinically generated visual questions and answers about radiology images", "addresses": [{"name": "Lister Hill National Center for Biomedical Communications", "source_name": "Lister Hill National Center for Biomedical Communications, U.S. National Library of Medicine, Bethesda, MD, USA", "street_adddress": "8600 Rockville Pike, Bethesda, MD 20894, USA", "lat": "38.99595080", "lng": "-77.09883230", "type": "gov", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/18f9/a6045ba01cb079c4fa49a630d71bbd27cd92.pdf"], "doi": []}, {"id": "1aac36122c07ecccfd59d912c22865801f096190", "title": "Face2Text: Collecting an Annotated Image Description Corpus for the Generation of Rich Face Descriptions", "addresses": [{"name": "University of Malta", "source_name": "University of Malta", "street_adddress": "University of Malta, Ring Road, Japanese Garden, L-Imsida, Malta, MSD 9027, Malta", "lat": "35.90232260", "lng": "14.48341890", "type": "edu", "country": "Malta"}, {"name": "University of Copenhagen", "source_name": "University of Copenhagen", "street_adddress": "K\u00f8benhavns Universitet, Krystalgade, K\u00f8dbyen, Vesterbro, K\u00f8benhavn, K\u00f8benhavns Kommune, Region Hovedstaden, 1165, Danmark", "lat": "55.68015020", "lng": "12.57232700", "type": "edu", "country": "Denmark"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.03827.pdf"], "doi": []}, {"id": "4c7659079b3df5bc746f76b2b1685b0b539832d6", "title": "Domain Adaptive Faster R-CNN for Object Detection in the Wild", "addresses": [{"name": "ETH Zurich", "source_name": "ETH Zurich", "street_adddress": "R\u00e4mistrasse 101, 8092 Z\u00fcrich, Switzerland", "lat": "47.37631300", "lng": "8.54766990", "type": "edu", "country": "Switzerland"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.03243.pdf"], "doi": []}, {"id": "3e16de062b9cdeecfcbda0de022f1fc4e741a2e6", "title": "Learning Visually-Grounded Semantics from Contrastive Adversarial Samples", "addresses": [{"name": "Peking University", "source_name": "Peking University", "street_adddress": "\u5317\u4eac\u5927\u5b66, 5\u53f7, \u9890\u548c\u56ed\u8def, \u7a3b\u9999\u56ed\u5357\u793e\u533a, \u6d77\u6dc0\u533a, \u5317\u4eac\u5e02, 100871, \u4e2d\u56fd", "lat": "39.99223790", "lng": "116.30393816", "type": "edu", "country": "China"}, {"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.10348.pdf"], "doi": []}, {"id": "838420cebfdad4e93221f8fe203c09155983141a", "title": "Subspace Alignment Based Domain Adaptation for RCNN Detector", "addresses": [{"name": "IIT Kanpur", "source_name": "IIT Kanpur", "street_adddress": "Kalyanpur, Kanpur, Uttar Pradesh 208016, India", "lat": "26.51233880", "lng": "80.23290000", "type": "edu", "country": "India"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1507.05578.pdf"], "doi": []}, {"id": "80eab89ff1c5c2cfc1ea62e2088cfc9b62de8d35", "title": "Emergent Translation in Multi-Agent Communication", "addresses": [{"name": "New York University", "source_name": "New York University", "street_adddress": "NYU, West 4th Street, NoHo Historic District, NoHo, Manhattan, Manhattan Community Board 2, New York County, NYC, New York, 10012, USA", "lat": "40.72925325", "lng": "-73.99625394", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1710.06922.pdf"], "doi": []}, {"id": "d983ce0a7d249bb85d14a66a89225a7136cc783b", "title": "A Single-shot Object Detector with Feature Aggragation and Enhancement", "addresses": [{"name": "Xi\u2019an Jiaotong University", "source_name": "Institute of Information and System Sciences, Faculty of Mathematics and Statistics, Xi\u2019an Jiaotong University, Xi\u2019an, China", "street_adddress": "28 Xianning W Rd, JiaoDa ShangYe JieQu, Beilin Qu, Xian Shi, Shaanxi Sheng, China", "lat": "34.25080300", "lng": "108.98369300", "type": "edu", "country": "China"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1902.02923.pdf"], "doi": []}, {"id": "e05b4f3757a3b33324e96f8b9b71e7d4eb5a1fa9", "title": "Controllable Top-down Feature Transformer", "addresses": [{"name": "University of California, San Diego", "source_name": "University of California, San Diego", "street_adddress": "UCSD, 9500, Gilman Drive, Sixth College, University City, San Diego, San Diego County, California, 92093, USA", "lat": "32.87935255", "lng": "-117.23110049", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1712.02400.pdf"], "doi": []}, {"id": "35498b80ee457e409c0962e03a6e170a917c83af", "title": "Look into Person: Self-Supervised Structure-Sensitive Learning and a New Benchmark for Human Parsing", "addresses": [{"name": "Sun Yat-Sen University", "source_name": "Sun Yat-Sen University", "street_adddress": "\u4e2d\u5927, \u65b0\u6e2f\u897f\u8def, \u9f99\u8239\u6ed8, \u5eb7\u4e50, \u6d77\u73e0\u533a (Haizhu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510105, \u4e2d\u56fd", "lat": "23.09461185", "lng": "113.28788994", "type": "edu", "country": "China"}, {"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.05446.pdf"], "doi": []}, {"id": "ba7890a5e9e51bf6181cc3c03144796cb3e5e254", "title": "Query : \" A man in a red sweatshirt performing breakdance \"", "addresses": [{"name": "Max Planck Institute for Informatics", "source_name": "Max Planck Institute for Informatics", "street_adddress": "MPII, E1 4, Campus, Universit\u00e4t, Sankt Johann, Bezirk Mitte, Saarbr\u00fccken, Regionalverband Saarbr\u00fccken, Saarland, 66123, Deutschland", "lat": "49.25795660", "lng": "7.04577417", "type": "edu", "country": "Germany"}, {"name": "University of California, Berkeley", "source_name": "University of California, Berkeley", "street_adddress": "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "lat": "37.86871260", "lng": "-122.25586815", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/ba78/90a5e9e51bf6181cc3c03144796cb3e5e254.pdf"], "doi": []}, {"id": "24ff2797234e26bb2ffd4558eb4412df0625687e", "title": "Mind Your Language: Abuse and Offense Detection for Code-Switched Languages", "addresses": [{"name": "Adobe Systems", "source_name": "Adobe Systems", "street_adddress": "343 Preston St, Ottawa, ON K1S 1N4, Canada", "lat": "45.40242130", "lng": "-75.70955410", "type": "edu", "country": "South Korea"}, {"name": "IIIT, Delhi", "source_name": "IIIT, Delhi", "street_adddress": "Okhla Industrial Estate, Phase III, Near Govind Puri Metro Station, New Delhi, Delhi 110020, India", "lat": "28.54562820", "lng": "77.27315050", "type": "edu", "country": "India"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.08652.pdf"], "doi": []}, {"id": "d31d4bb58f5dd67016e77352ac7600e2ba71e38f", "title": "Deep Learning Object Detection Methods for Ecological Camera Trap Data", "addresses": [{"name": "University of Guelph", "source_name": "University of Guelph, Guelph, Ontario, Canada", "street_adddress": "University of Guelph, Guelph, ON N1G 1Y4, Canada", "lat": "43.52937320", "lng": "-80.22525020", "type": "edu", "country": "Canada"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.10842.pdf"], "doi": []}, {"id": "faf73a84c9ce13cdfc9014fa89ecde9927c8c84a", "title": "Meta Networks for Neural Style Transfer", "addresses": [{"name": "Peking University", "source_name": "Peking University", "street_adddress": "\u5317\u4eac\u5927\u5b66, 5\u53f7, \u9890\u548c\u56ed\u8def, \u7a3b\u9999\u56ed\u5357\u793e\u533a, \u6d77\u6dc0\u533a, \u5317\u4eac\u5e02, 100871, \u4e2d\u56fd", "lat": "39.99223790", "lng": "116.30393816", "type": "edu", "country": "China"}, {"name": "National University of Singapore", "source_name": "National University of Singapore", "street_adddress": "NUS, Former 1936 British Outpost, Nepal Hill, Clementi, Southwest, 117542, Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu", "country": "Singapore"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1709.04111.pdf"], "doi": []}, {"id": "0020784920bf7ff6cb51d0b6061b99fd77161c3e", "title": "Learning Instance-Aware Object Detection Using Determinantal Point Processes", "addresses": [{"name": "Seoul National University", "source_name": "Seoul National University", "street_adddress": "\uc11c\uc6b8\ub300\ud559\uad50, \uc11c\ud638\ub3d9\ub85c, \uc11c\ub454\ub3d9, \uad8c\uc120\uad6c, \uc218\uc6d0\uc2dc, \uacbd\uae30, 16614, \ub300\ud55c\ubbfc\uad6d", "lat": "37.26728000", "lng": "126.98411510", "type": "edu", "country": "South Korea"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.10765.pdf"], "doi": []}, {"id": "d7ed61f57d26c192a75d088854d937d549efa37c", "title": "A Multi-Layer Approach to Superpixel-based Higher-order Conditional Random Field for Semantic Image Segmentation", "addresses": [{"name": "University of Texas at Arlington", "source_name": "University of Texas at Arlington", "street_adddress": "University of Texas at Arlington, South Nedderman Drive, Arlington, Tarrant County, Texas, 76010, USA", "lat": "32.72836830", "lng": "-97.11201835", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.02032.pdf"], "doi": []}, {"id": "528d1ad4725277b25f17c951c7aa637f58da1c9e", "title": "Text and Object Detection on Billboards", "addresses": [{"name": "Faculty of Information Technology, King Mongkut\u2019s Institute of Technology Ladkrabang, Bangkok, 10520, Thailand", "source_name": "Faculty of Information Technology, King Mongkut\u2019s Institute of Technology Ladkrabang, Bangkok, 10520, Thailand", "street_adddress": "1 Thanon Chalong Krung, Lat Krabang, Khet Lat Krabang, Krung Thep Maha Nakhon 10520, Thailand", "lat": "13.73095530", "lng": "100.78117740", "type": "edu", "country": "Thailand"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8534879", "http://doi.org/10.1109/iciteed.2018.8534879"]}, {"id": "0c5f9f5083b9fca4dcdbc4b122099ac1f630728b", "title": "Visual Semantic Role Labeling", "addresses": [{"name": "UC Berkeley", "source_name": "UC Berkeley", "street_adddress": "Berkeley, CA, USA", "lat": "37.87189920", "lng": "-122.25853990", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1505.04474.pdf"], "doi": []}, {"id": "f4af49a1ead3c81cc5d023878cb67c5646dd8a04", "title": "Learning a Recurrent Visual Representation for Image Caption Generation", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}, {"name": "Microsoft", "source_name": "Microsoft Corporation, Redmond, WA, USA", "street_adddress": "One Microsoft Way, Redmond, WA 98052, USA", "lat": "47.64233180", "lng": "-122.13693020", "type": "company", "country": "United States"}], "year": "2014", "pdf": ["https://arxiv.org/pdf/1411.5654.pdf"], "doi": []}, {"id": "73b5261948b9b1e998bc84edf061efd354dac479", "title": "Watching the TV Watchers", "addresses": [{"name": "Georgia Institute of Technology", "source_name": "Georgia Institute of Technology", "street_adddress": "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu", "country": "United States"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3214291"]}, {"id": "9d27197ecc73ac0c3a664499c62975068251bf9c", "title": "Studying Object Naming with Online Photos and Caption", "addresses": [{"name": "Australian National University", "source_name": "Australian National University", "street_adddress": "Canberra ACT 0200, Australia", "lat": "-35.27769990", "lng": "149.11852700", "type": "edu", "country": "Australia"}, {"name": "NICTA / Australian National University", "source_name": "NICTA / Australian National University, Canberra, Australia", "street_adddress": "Canberra ACT 0200, Australia", "lat": "-35.27769990", "lng": "149.11852700", "type": "edu", "country": "Australia"}], "year": "2015", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=2814817"]}, {"id": "72d7c465ef199a9670b3da7a318b0227f5cc3229", "title": "Visual Referring Expression Recognition: What Do Systems Actually Learn?", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.11818.pdf"], "doi": []}, {"id": "2c761495cf3dd320e229586f80f868be12360d4e", "title": "Revisiting Unreasonable Effectiveness of Data in Deep Learning Era", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.02968.pdf"], "doi": []}, {"id": "c0006a2268d299644e9f1b455601bcbe89ddc2b5", "title": "Semantic Video Segmentation by Gated Recurrent Flow Propagation", "addresses": [{"name": "Lund University", "source_name": "Lund University", "street_adddress": "TEM at Lund University, 9, Klostergatan, Stadsk\u00e4rnan, Centrum, Lund, Sk\u00e5ne, G\u00f6taland, 22222, Sverige", "lat": "55.70395710", "lng": "13.19020110", "type": "edu", "country": "Sweden"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1612.08871.pdf"], "doi": []}, {"id": "52a08919efb7a1d0f28eda82bacd9d495639a6b3", "title": "Neighbourhood Watch: Referring Expression Comprehension via Language-guided Graph Attention Networks", "addresses": [{"name": "University of Adelaide", "source_name": "University of Adelaide", "street_adddress": "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu", "country": "Australia"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.04794.pdf"], "doi": []}, {"id": "96fdc0131dc80ffa6d7b9c526e07f080414c54ec", "title": "1 Paying More A ention to Saliency : Image Captioning with Saliency and Context A ention", "addresses": [{"name": "University of Modena and Reggio Emilia", "source_name": "University of Modena and Reggio Emilia 41125, Modena, Italy", "street_adddress": "Via Universit\u00e0, 4, 41121 Modena MO, Italy", "lat": "44.64510460", "lng": "10.92792680", "type": "edu", "country": "Italy"}, {"name": "University of Udine", "source_name": "University of Udine, Italy", "street_adddress": "Universit\u00e0 degli Studi di Udine, Via delle Scienze, 206, 33100 Udine UD, Italy", "lat": "46.08107230", "lng": "13.21194740", "type": "edu", "country": "Italy"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/96fd/c0131dc80ffa6d7b9c526e07f080414c54ec.pdf"], "doi": []}, {"id": "59d0d7ccec2db66cad20cac5721ce54a8a058294", "title": "Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference", "addresses": [{"name": "Google", "source_name": "Google, Inc.", "street_adddress": "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "lat": "37.42199990", "lng": "-122.08405750", "type": "company", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1712.05877.pdf"], "doi": []}, {"id": "cb8f0d0e529e27c67f04e748266f084c07679755", "title": "Scene Image Synthesis from Natural Sentences Using Hierarchical Syntactic Analysis", "addresses": [{"name": "University of Tokyo", "source_name": "University of Tokyo", "street_adddress": "\u6771\u4eac\u5927\u5b66 \u67cf\u30ad\u30e3\u30f3\u30d1\u30b9, \u5b66\u878d\u5408\u306e\u9053, \u67cf\u5e02, \u5343\u8449\u770c, \u95a2\u6771\u5730\u65b9, 277-8583, \u65e5\u672c", "lat": "35.90204480", "lng": "139.93622009", "type": "edu", "country": "Japan"}], "year": "2016", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=2967193"]}, {"id": "a875c22ca30a99a013d728313420e418e398fafd", "title": "Strong-Weak Distribution Alignment for Adaptive Object Detection.", "addresses": [{"name": "Boston University", "source_name": "Boston University", "street_adddress": "BU, Bay State Road, Fenway, Boston, Suffolk County, Massachusetts, 02215, USA", "lat": "42.35042530", "lng": "-71.10056114", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.04798.pdf"], "doi": []}, {"id": "eb7ddda1bfa709497af9d0b2010d61d659a1816f", "title": "Training CNNs from Synthetic Data for Part Handling in Industrial Environments", "addresses": [{"name": "BTU Cottbus-Senftenberg, Cottbus, Germany", "source_name": "BTU Cottbus-Senftenberg, Chair of Automation Technology, Cottbus, Germany", "street_adddress": "Platz der Deutschen Einheit 1, 03046 Cottbus, Germany", "lat": "51.76698700", "lng": "14.32695000", "type": "edu", "country": "Germany"}, {"name": "Mercedes-Benz-Cars Daimler AG, Stuttgart, Germany", "source_name": "Mercedes-Benz-Cars Daimler AG, Stuttgart, Germany", "street_adddress": "Stuttgarter Str. 90, 70736 Fellbach, Germany", "lat": "48.81313800", "lng": "9.26374900", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8560470", "http://doi.org/10.1109/COASE.2018.8560470"]}, {"id": "3f93ad8732ed2e92f09536ad744d1111cab93522", "title": "Weakly Supervised Attention Learning for Textual Phrases Grounding", "addresses": [{"name": "Arizona State University", "source_name": "Arizona State University", "street_adddress": "Arizona State University Polytechnic campus, East Texas Avenue, Mesa, Maricopa County, Arizona, 85212, USA", "lat": "33.30715065", "lng": "-111.67653157", "type": "edu", "country": "United States"}, {"name": "University of California, Irvine", "source_name": "University of California, Irvine", "street_adddress": "Irvine, CA 92697, USA", "lat": "33.64049520", "lng": "-117.84429620", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.00545.pdf"], "doi": []}, {"id": "1c5b168c29d1c8b3dc753865c741b9f3c56d0555", "title": "Auto-Encoding Scene Graphs for Image Captioning", "addresses": [{"name": "Nanyang Technological University", "source_name": "Nanyang Technological University", "street_adddress": "NTU, Faculty Avenue, Jurong West, Southwest, 637460, Singapore", "lat": "1.34841040", "lng": "103.68297965", "type": "edu", "country": "Singapore"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.02378.pdf"], "doi": []}, {"id": "20af3b2a011eabfdc3021a5e78995c5ce592575c", "title": "Learning to Classify Fine-Grained Categories with Privileged Visual-Semantic Misalignment", "addresses": [{"name": "Tampere University of Technology", "source_name": "Tampere University of Technology", "street_adddress": "TTY, 10, Korkeakoulunkatu, Finninm\u00e4ki, Hervanta, Tampere, Tampereen seutukunta, Pirkanmaa, L\u00e4nsi- ja Sis\u00e4-Suomen aluehallintovirasto, L\u00e4nsi-Suomi, Manner-Suomi, 33720, Suomi", "lat": "61.44964205", "lng": "23.85877462", "type": "edu", "country": "Finland"}, {"name": "Chinese Academy of Sciences", "source_name": "Chinese Academy of Sciences", "street_adddress": "\u4e2d\u56fd\u79d1\u5b66\u9662\u5fc3\u7406\u7814\u7a76\u6240, 16, \u6797\u8403\u8def, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100101, \u4e2d\u56fd", "lat": "40.00447950", "lng": "116.37023800", "type": "edu", "country": "China"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7552556", "http://doi.ieeecomputersociety.org/10.1109/TBDATA.2016.2602231", "http://doi.org/10.1109/TBDATA.2016.2602231"]}, {"id": "193a69489230de1013dff9af1232e5379cc5282f", "title": "Intelligent Multimodal Framework for Human Assistive Robotics Based on Computer Vision Algorithms", "addresses": [{"name": "Universitat Polit\u00e8cnica de Val\u00e8ncia", "source_name": "Integrated Management Coastal Research Institute, Universitat Polit\u00e8cnica de Val\u00e8ncia, Val\u00e8ncia, Spain", "street_adddress": "Cam\u00ed de Vera, s/n, 46022 Val\u00e8ncia, Valencia, Spain", "lat": "39.48083760", "lng": "-0.34095220", "type": "edu", "country": "Spain"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/193a/69489230de1013dff9af1232e5379cc5282f.pdf"], "doi": []}, {"id": "f9f01af981f8d25f0c96ea06d88be62dabb79256", "title": "Terahertz Image Detection with the Improved Faster Region-Based Convolutional Neural Network", "addresses": [{"name": "Xidian University", "source_name": "Xidian University", "street_adddress": "Xidian University (New Campus), 266\u53f7, \u94f6\u674f\u5927\u9053, \u5357\u96f7\u6751, \u957f\u5b89\u533a (Chang'an), \u897f\u5b89\u5e02, \u9655\u897f\u7701, 710126, \u4e2d\u56fd", "lat": "34.12358250", "lng": "108.83546000", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/f9f0/1af981f8d25f0c96ea06d88be62dabb79256.pdf"], "doi": []}, {"id": "3b8a3b4ed02a15b2ba329727596b704889123a39", "title": "Deep affordance learning for single- and multiple-instance object detection", "addresses": [{"name": "Institute for Infocomm Research Agency for Science, Technology and Research (A\u2217STAR) 1 Fusionopolis Way, #21-01 Connexis (South Tower) Singapore 138632", "source_name": "Institute for Infocomm Research Agency for Science, Technology and Research (A\u2217STAR) 1 Fusionopolis Way, #21-01 Connexis (South Tower) Singapore 138632", "street_adddress": "1 Fusionopolis Way, #21-01 Connexis, Singapore 138632", "lat": "1.29889260", "lng": "103.78731070", "type": "edu", "country": "Singapore"}], "year": "2017", "pdf": ["https://oar.a-star.edu.sg/jspui/bitstream/123456789/2242/1/1570379510(2).pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8227883"]}, {"id": "ade2266f249f91767b0949ae600fe1048237e567", "title": "Maya Codical Glyph Segmentation: A Crowdsourcing Approach", "addresses": [{"name": "IDIAP Research Institute", "source_name": "IDIAP Research Institute", "street_adddress": "Idiap Research Institute, Parking Centre du parc, Martigny, Valais/Wallis, 1920, Schweiz/Suisse/Svizzera/Svizra", "lat": "46.10923700", "lng": "7.08453549", "type": "edu", "country": "Switzerland"}], "year": "2018", "pdf": ["http://publications.idiap.ch/downloads/papers/2017/Can_IEEETMM_2017.pdf", "http://publications.idiap.ch/downloads/reports/2016/Can_Idiap-RR-01-2017.pdf", "http://publications.idiap.ch/downloads/reports/2017/Can_Idiap-RR-01-2017.pdf", "https://infoscience.epfl.ch/record/225945/files/Can_Idiap-RR-01-2017.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8048535", "http://doi.org/10.1109/TMM.2017.2755985"]}, {"id": "989282f579fdca0ebdc890cf05cac88c29f9eb49", "title": "Benchmarking and Error Diagnosis in Multi-instance Pose Estimation", "addresses": [{"name": "California Institute of Technology", "source_name": "California Institute of Technology", "street_adddress": "California Institute of Technology, San Pasqual Walk, Madison Heights, Pasadena, Los Angeles County, California, 91126, USA", "lat": "34.13710185", "lng": "-118.12527487", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.05388.pdf"], "doi": []}, {"id": "403537a81f9c295ab5770fd82abe4f7542be9200", "title": "Driver Pose Estimation by Hybrid Convolutional Network Architecture", "addresses": [{"name": "National Engineering Laboratory for Visual Information Processing and Applications, Xi'an, China", "source_name": "National Engineering Laboratory for Visual Information Processing and Applications, Xi'an, Shaanxi, 710049, China", "street_adddress": "Jiaoda Commerce Block, Beilin, Xi'an, Shaanxi, China, 710049", "lat": "34.24845540", "lng": "108.98873940", "type": "gov", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8623392"]}, {"id": "1695d0112d2e2c6df8bbe1d6abe18a457eba90dc", "title": "Classification of Crash and Near-Crash Events from Dashcam Videos and Telematics", "addresses": [{"name": "Verizon Connect Research, Florence, Italy", "source_name": "Verizon Connect Research, via Paisiello 16-20, Florence, 50144, Italy", "street_adddress": "Via Giovanni Paisiello, 20, 50144 Firenze FI, Italy", "lat": "43.78205540", "lng": "11.23259400", "type": "edu", "country": "Italy"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8569952", "http://doi.org/10.1109/ITSC.2018.8569952"]}, {"id": "2fc6647858a1c7d6f51c4c57368e50677f30c0a9", "title": "Simultaneous object detection and localization using convolutional neural networks", "addresses": [{"name": "Mohammed V University in Rabat", "source_name": "LRIT-CNRST URAC 29, Mohammed V University in Rabat, Faculty of Sciences Rabat, Morocco", "street_adddress": "Angle avenues des FAR et Allal El Fassi, Hay Ryad, B.P. 8027 N.U.\u060c Rabat 10102, Morocco", "lat": "33.97023350", "lng": "-6.87447300", "type": "edu", "country": "Morocco"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8354045"]}, {"id": "4066f186ff58d300090c652925ed0aed3355efec", "title": "Solving Visual Madlibs with Multiple Cues", "addresses": [{"name": "University of Illinois, Urbana-Champaign", "source_name": "University of Illinois, Urbana-Champaign", "street_adddress": "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1608.03410.pdf"], "doi": []}, {"id": "5de5848dc3fc35e40420ffec70a407e4770e3a8d", "title": "WebVision Database: Visual Learning and Understanding from Web Data", "addresses": [{"name": "Computer Vision Laboratory, ETH Zurich", "source_name": "Computer Vision Laboratory ETH Zurich, UK", "street_adddress": "Sternwartstrasse 7, 8092 Z\u00fcrich, Switzerland", "lat": "47.37723980", "lng": "8.55216180", "type": "edu", "country": "Switzerland"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.02862.pdf"], "doi": []}, {"id": "7897f6a19d5211bf6387f5c9e141c90a0cc84566", "title": "One-shot Texture Segmentation", "addresses": [{"name": "University of T\u00fcbingen", "source_name": "University of T\u00fcbingen", "street_adddress": "Geschwister-Scholl-Platz, 72074 T\u00fcbingen, Germany", "lat": "48.52947820", "lng": "9.04377400", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.02654.pdf"], "doi": []}, {"id": "947f2d465df60ec49f441f02733edbeb81dde2f2", "title": "Fast Object Localization Using a CNN Feature Map Based Multi-Scale Search", "addresses": [{"name": "U.S. Army Research Laboratory, Adelphi, MD, USA", "source_name": "U.S. Army Research Laboratory, Adelphi, MD, USA", "street_adddress": "2800 Powder Mill Rd, Adelphi, MD 20783, USA", "lat": "39.02985870", "lng": "-76.96380270", "type": "mil", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1604.03517.pdf"], "doi": []}, {"id": "5b1e42e0ff78880dccdf4d90cfd5c6e3e577f923", "title": "Deep Feature Pyramid Reconfiguration for Object Detection", "addresses": [{"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.07993.pdf"], "doi": []}, {"id": "d7221695df4de3f34d5e4a877b71c14bc88760d2", "title": "Proposal Incorporating Structural Bias into Neural Networks", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/d722/1695df4de3f34d5e4a877b71c14bc88760d2.pdf"], "doi": []}, {"id": "dc5fc803b64b49217babab378efe29f35b697d2f", "title": "Directional Edge Boxes: Exploiting Inner Normal Direction Cues for Effective Object Proposal Generation", "addresses": [{"name": "Shanghai University", "source_name": "Shanghai University", "street_adddress": "\u4e0a\u6d77\u5927\u5b66, \u9526\u79cb\u8def, \u5927\u573a\u9547, \u5b9d\u5c71\u533a (Baoshan), \u4e0a\u6d77\u5e02, 201906, \u4e2d\u56fd", "lat": "31.32235655", "lng": "121.38400941", "type": "edu", "country": "China"}, {"name": "Huazhong University of Science and Technology", "source_name": "Huazhong University of Science and Technology", "street_adddress": "\u534e\u4e2d\u5927, \u73de\u55bb\u8def, \u4e1c\u6e56\u65b0\u6280\u672f\u5f00\u53d1\u533a, \u5173\u4e1c\u8857\u9053, \u4e1c\u6e56\u65b0\u6280\u672f\u5f00\u53d1\u533a\uff08\u6258\u7ba1\uff09, \u6d2a\u5c71\u533a (Hongshan), \u6b66\u6c49\u5e02, \u6e56\u5317\u7701, 430074, \u4e2d\u56fd", "lat": "30.50975370", "lng": "114.40628810", "type": "edu", "country": "China"}], "year": "2017", "pdf": [], "doi": ["http://doi.org/10.1007/s11390-017-1752-9"]}, {"id": "4f69ad0e52e37ba06db1c2b89c180f3ba331cc4a", "title": "Automatic Generation of Grounded Visual Questions", "addresses": [{"name": "Tianjin University", "source_name": "Tianjin University", "street_adddress": "\u6cf0\u5c71\u822a\u7a7a\u6e2f/\u5929\u6d25\u5927\u53a6, \u67a3\u884c\u8def, \u67a3\u884c \u9ad8\u738b\u5bfa, \u957f\u57ce\u8def, \u5927\u6cb3, \u5cb1\u5cb3\u533a (Daiyue), \u6cf0\u5b89\u5e02, \u5c71\u4e1c\u7701, 271000, \u4e2d\u56fd", "lat": "36.20304395", "lng": "117.05842113", "type": "edu", "country": "China"}, {"name": "NanKai University", "source_name": "College of Information Technical Science, NanKai University, CITS, TianJin, China", "street_adddress": "China, Tianjin, Nankai, Lequn N Rd, \u5357\u5f00\u5927\u5b66\u7efc\u5408\u5b9e\u9a8c\u697cA\u533a604", "lat": "39.10335500", "lng": "117.16492700", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1612.06530.pdf"], "doi": []}, {"id": "8060ae8621a20e5cbf6e974aab12ad34c37e9651", "title": "Intelligent surveillance system for abandoned luggage", "addresses": [{"name": "Orta Do\u011fu Teknik \u00dcniversitesi", "source_name": "Bilgisayar M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc, Orta Do\u011fu Teknik \u00dcniversitesi, Kuzey K\u0131br\u0131s Kamp\u00fcs\u00fc, Kalkanl\u0131, Kuzey K\u0131br\u0131s", "street_adddress": "Kalkanl\u0131, G\u00fczelyurt", "lat": "35.24908700", "lng": "33.02407600", "type": "edu", "country": "Turkey"}, {"name": "Elektrik - Elektronik M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc, Orta Do\u011fu Teknik \u00dcniversitesi, Kuzey K\u0131br\u0131s Kamp\u00fcs\u00fc, Kalkanl\u0131, Kuzey K\u0131br\u0131s", "source_name": "Elektrik - Elektronik M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc, Orta Do\u011fu Teknik \u00dcniversitesi, Kuzey K\u0131br\u0131s Kamp\u00fcs\u00fc, Kalkanl\u0131, Kuzey K\u0131br\u0131s", "street_adddress": "Kalkanl\u0131, G\u00fczelyurt", "lat": "35.24908700", "lng": "33.02407600", "type": "edu", "country": "Turkey"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8404327", "http://doi.org/10.1109/SIU.2018.8404327"]}, {"id": "87fa9d667f8f41eb04831356dc8d68b190693e5e", "title": "Chat-crowd: A Dialog-based Platform for Visual Layout Composition", "addresses": [{"name": "University of Virginia", "source_name": "University of Virginia", "street_adddress": "University of Virginia, Rotunda Alley, Carr's Hill, Albemarle County, Virginia, 22904-4119, USA", "lat": "38.03536820", "lng": "-78.50353220", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.04081.pdf"], "doi": []}, {"id": "250c0c37947d6dc32e1923c8df99bf64dc5d7e10", "title": "Implicit Negative Sub-Categorization and Sink Diversion for Object Detection", "addresses": [{"name": "360 AI Institute, Beijing, China", "source_name": "360 AI Institute, Beijing, China", "street_adddress": "Beijing, China", "lat": "39.90419990", "lng": "116.40739630", "type": "edu", "country": "China"}, {"name": "Chinese Academy of Sciences", "source_name": "Chinese Academy of Sciences", "street_adddress": "\u4e2d\u56fd\u79d1\u5b66\u9662\u5fc3\u7406\u7814\u7a76\u6240, 16, \u6797\u8403\u8def, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100101, \u4e2d\u56fd", "lat": "40.00447950", "lng": "116.37023800", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8125749", "http://doi.org/10.1109/TIP.2017.2779270", "https://www.ncbi.nlm.nih.gov/pubmed/29324412", "https://www.wikidata.org/entity/Q50087459"]}, {"id": "9bda68ea52bddf5365e3230761c95424ff1ddec5", "title": "SSP: Supervised Sparse Projections for Large-Scale Retrieval in High Dimensions", "addresses": [{"name": "University of British Columbia", "source_name": "University of British Columbia", "street_adddress": "University of British Columbia, Eagles Drive, Hawthorn Place, University Endowment Lands, Metro Vancouver, British Columbia, V6T, Canada", "lat": "49.25839375", "lng": "-123.24658161", "type": "edu", "country": "Canada"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/9bda/68ea52bddf5365e3230761c95424ff1ddec5.pdf"], "doi": []}, {"id": "b674dae73fcb236ee951d8ae8a36be527d232678", "title": "A sequential guiding network with attention for image captioning", "addresses": [{"name": "Beihang University", "source_name": "Beihang University", "street_adddress": "\u5317\u4eac\u822a\u7a7a\u822a\u5929\u5927\u5b66, 37, \u5b66\u9662\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100083, \u4e2d\u56fd", "lat": "39.98083330", "lng": "116.34101249", "type": "edu", "country": "China"}, {"name": "North China Electric Power University", "source_name": "North China Electric Power University", "street_adddress": "\u534e\u5317\u7535\u529b\u5927\u5b66, \u6c38\u534e\u5317\u5927\u8857, \u83b2\u6c60\u533a, \u4fdd\u5b9a\u5e02, \u83b2\u6c60\u533a (Lianchi), \u4fdd\u5b9a\u5e02, \u6cb3\u5317\u7701, 071000, \u4e2d\u56fd", "lat": "38.87604460", "lng": "115.49738730", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.00228.pdf"], "doi": []}, {"id": "9ded64e83d3ba51513ea00de27c0c770a02b0cf4", "title": "Image Classification using Transfer Learning from Siamese Networks based on Text Metadata Similarity", "addresses": [{"name": "Stanford University", "source_name": "Stanford University", "street_adddress": "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/9ded/64e83d3ba51513ea00de27c0c770a02b0cf4.pdf"], "doi": []}, {"id": "5fedae3bccf86052ed725e5925bb4ef47f9389c1", "title": "Word Prior Detection Segmentation Input \" The left guy \" Image : Query : a guy left the youth Energy", "addresses": [{"name": "University of Illinois, Urbana-Champaign", "source_name": "University of Illinois, Urbana-Champaign", "street_adddress": "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu", "country": "United States"}, {"name": "IBM T.J. Watson Research Center", "source_name": "IBM T. J. Watson Research, Center, New York, USA", "street_adddress": "1101 Kitchawan Rd, Yorktown Heights, NY 10598, USA", "lat": "41.20975160", "lng": "-73.80264670", "type": "company", "country": "United States"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/5fed/ae3bccf86052ed725e5925bb4ef47f9389c1.pdf"], "doi": []}, {"id": "5d1d45c89ec13f3b0a83078759bb1dfbac695102", "title": "Segmentation of Nuclei in Histopathology Images by Deep Regression of the Distance Map", "addresses": [{"name": "PSL Research University", "source_name": "MINES ParisTech, PSL Research University, CAOR - Centre de Robotique, 60 Bd St Michel 75006. Paris, France", "street_adddress": "60 Boulevard Saint-Michel, 75006 Paris, France", "lat": "48.84496370", "lng": "2.33961050", "type": "edu", "country": "France"}], "year": "2019", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8438559"]}, {"id": "8e368144360042aad69703a6bffd56e1e72f2af4", "title": "Revisiting Graph Construction for Fast Image Segmentation", "addresses": [{"name": "University of Florida", "source_name": "University of Florida", "street_adddress": "University of Florida, Southwest 16th Avenue, Diamond Village Apartments, City of Gainesville Municipal Boundaries, Alachua County, Florida, 32611, USA", "lat": "29.63287840", "lng": "-82.34901330", "type": "edu", "country": "United States"}, {"name": "University of Colorado, Denver", "source_name": "University of Colorado Denver", "street_adddress": "University of Colorado (Denver Auraria campus), Lawrence Way, Auraria, Denver, Denver County, Colorado, 80217, USA", "lat": "39.74287785", "lng": "-105.00596398", "type": "edu", "country": "United States"}, {"name": "Xiamen University", "source_name": "Xiamen University", "street_adddress": "\u53a6\u95e8\u5927\u5b66, \u601d\u660e\u5357\u8def Siming South Road, \u601d\u660e\u533a, \u601d\u660e\u533a (Siming), \u53a6\u95e8\u5e02 / Xiamen, \u798f\u5efa\u7701, 361005, \u4e2d\u56fd", "lat": "24.43994190", "lng": "118.09301781", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1702.05650.pdf"], "doi": []}, {"id": "82317f5ac40e982b8ec5b2634f1214db259ca325", "title": "Multi-oriented Scene Text Detection via Corner Localization and Region Segmentation", "addresses": [{"name": "Huazhong University of Science and Technology", "source_name": "Huazhong University of Science and Technology", "street_adddress": "\u534e\u4e2d\u5927, \u73de\u55bb\u8def, \u4e1c\u6e56\u65b0\u6280\u672f\u5f00\u53d1\u533a, \u5173\u4e1c\u8857\u9053, \u4e1c\u6e56\u65b0\u6280\u672f\u5f00\u53d1\u533a\uff08\u6258\u7ba1\uff09, \u6d2a\u5c71\u533a (Hongshan), \u6b66\u6c49\u5e02, \u6e56\u5317\u7701, 430074, \u4e2d\u56fd", "lat": "30.50975370", "lng": "114.40628810", "type": "edu", "country": "China"}, {"name": "National University of Singapore", "source_name": "National University of Singapore", "street_adddress": "NUS, Former 1936 British Outpost, Nepal Hill, Clementi, Southwest, 117542, Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu", "country": "Singapore"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.08948.pdf"], "doi": []}, {"id": "205e895e03969c96f3c482b0bd26308b16a12bd0", "title": "Image Captioning with an Intermediate Attributes Layer", "addresses": [{"name": "University of Adelaide", "source_name": "University of Adelaide", "street_adddress": "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu", "country": "Australia"}], "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/205e/895e03969c96f3c482b0bd26308b16a12bd0.pdf"], "doi": []}, {"id": "8b485d7683e54d2b9c5d5ddf4ed31770bb323dbe", "title": "Hybrid Task Cascade for Instance Segmentation", "addresses": [{"name": "Chinese University of Hong Kong", "source_name": "Chinese University of Hong Kong", "street_adddress": "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "lat": "22.41626320", "lng": "114.21093180", "type": "edu", "country": "China"}, {"name": "University of Sydney", "source_name": "University of Sydney", "street_adddress": "USyd, Fisher Road, Camperdown, Sydney, NSW, 2006, Australia", "lat": "-33.88890695", "lng": "151.18943366", "type": "edu", "country": "Australia"}, {"name": "SenseTime", "source_name": "SenseTime", "street_adddress": "China, Beijing Shi, Haidian Qu, WuDaoKou, Zhongguancun E Rd, 1\u53f7-7", "lat": "39.99300800", "lng": "116.32988200", "type": "company", "country": "China"}, {"name": "Nanyang Technological University", "source_name": "Nanyang Technological University", "street_adddress": "NTU, Faculty Avenue, Jurong West, Southwest, 637460, Singapore", "lat": "1.34841040", "lng": "103.68297965", "type": "edu", "country": "Singapore"}, {"name": "Zhejiang University", "source_name": "Zhejiang University", "street_adddress": "\u6d59\u6c5f\u5927\u5b66\u4e4b\u6c5f\u6821\u533a, \u4e4b\u6c5f\u8def, \u8f6c\u5858\u8857\u9053, \u897f\u6e56\u533a (Xihu), \u676d\u5dde\u5e02 Hangzhou, \u6d59\u6c5f\u7701, 310008, \u4e2d\u56fd", "lat": "30.19331415", "lng": "120.11930822", "type": "edu", "country": "China"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.07518.pdf"], "doi": []}, {"id": "637648198f9e91654ce27eaaa40512f2dc870fc1", "title": "Survey of Visual Question Answering: Datasets and Techniques", "addresses": [{"name": "Indian Institute of Technology Delhi", "source_name": "IIIT-Delhi, India", "street_adddress": "IIIT-Delhi, Mathura Road, Friends Colony, South East Delhi, Delhi, 110020, India", "lat": "28.54632595", "lng": "77.27325504", "type": "edu", "country": "India"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.03865.pdf"], "doi": []}, {"id": "b99588bd0393a60a0c627970ab6cab7338d08ca6", "title": "Semantic segmentation based on iterative contraction and merging", "addresses": [{"name": "National Chiao Tung University", "source_name": "National Chiao Tung University", "street_adddress": "NCTU;\u4ea4\u5927;\u4ea4\u901a\u5927\u5b78;\u4ea4\u5927\u5149\u5fa9\u6821\u5340;\u4ea4\u901a\u5927\u5b78\u5149\u5fa9\u6821\u5340, 1001, \u5927\u5b78\u8def, \u5149\u660e\u91cc, \u8d64\u571f\u5d0e, \u6771\u5340, \u65b0\u7af9\u5e02, 30010, \u81fa\u7063", "lat": "24.78676765", "lng": "120.99724412", "type": "edu", "country": "Taiwan"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8296488", "http://doi.org/10.1109/ICIP.2017.8296488"]}, {"id": "bb127015474fdc51d4cd6b4dda7176a8c778ea49", "title": "Examining the Impact of Blur on Recognition by Convolutional Networks.", "addresses": [{"name": "University of Chicago", "source_name": "THE UNIVERSITY OF CHICAGO", "street_adddress": "University of Chicago, South Ellis Avenue, Woodlawn, Chicago, Cook County, Illinois, 60637, USA", "lat": "41.78468745", "lng": "-87.60074933", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1611.05760.pdf"], "doi": []}, {"id": "e10ca043fae02972f19292efacddd8e0f216b70c", "title": "Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel Concepts", "addresses": [{"name": "Australian National University", "source_name": "Australian National University", "street_adddress": "Canberra ACT 0200, Australia", "lat": "-35.27769990", "lng": "149.11852700", "type": "edu", "country": "Australia"}, {"name": "CSIRO", "source_name": "CSIRO-Data61, Canberra, Australia", "street_adddress": "North Road Australian National University, The Australian National University, Acton ACT 2601, Australia", "lat": "-35.27769990", "lng": "149.11852700", "type": "edu", "country": "Australia"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.06049.pdf"], "doi": []}, {"id": "030ab7710a1307cfa2159686dabd07e2b239fb10", "title": "Crowd-Guided Ensembles: How Can We Choreograph Crowd Workers for Video Segmentation?", "addresses": [{"name": "Massachusetts Institute of Technology & ETH Z\u00fcrich", "source_name": "Massachusetts Institute of Technology & ETH Z\u00fcrich, Cambridge, MA, USA", "street_adddress": "77 Massachusetts Ave, Cambridge, MA 02139, USA", "lat": "42.36009100", "lng": "-71.09416000", "type": "edu", "country": "United States"}, {"name": "MIT", "source_name": "Massachusetts Institute", "street_adddress": "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu", "country": "United States"}, {"name": "Microsoft", "source_name": "Microsoft Corporation, Redmond, WA, USA", "street_adddress": "One Microsoft Way, Redmond, WA 98052, USA", "lat": "47.64233180", "lng": "-122.13693020", "type": "company", "country": "United States"}, {"name": "Qatar Computing Research Institute, Doha, Qatar", "source_name": "Qatar Computing Research Institute, Doha, Qatar", "street_adddress": "Ar-Rayyan, Qatar", "lat": "25.32159140", "lng": "51.42577380", "type": "company", "country": "Qatar"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3173685"]}, {"id": "a3d96844dc4fc3b51f3b8361c72f156800794251", "title": "BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation", "addresses": [{"name": "Microsoft", "source_name": "Microsoft Corporation, Redmond, WA, USA", "street_adddress": "One Microsoft Way, Redmond, WA 98052, USA", "lat": "47.64233180", "lng": "-122.13693020", "type": "company", "country": "United States"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1503.01640.pdf"], "doi": []}, {"id": "cf2ab0e639c19877596036603a3000ce7a1deb35", "title": "Self-supervised Learning of Motion Capture", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}, {"name": "University of Pittsburgh", "source_name": "University of Pittsburgh", "street_adddress": "University of Pittsburgh, Sutherland Drive, West Oakland, PGH, Allegheny County, Pennsylvania, 15240, USA", "lat": "40.44415295", "lng": "-79.96243993", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1712.01337.pdf"], "doi": []}, {"id": "8a12540c85c6835eb6fd36131107d82c50d2b8d0", "title": "Dense Image Representation with Spatial Pyramid VLAD Coding of CNN for Locally Robust Captioning", "addresses": [{"name": "University of Tokyo", "source_name": "University of Tokyo", "street_adddress": "\u6771\u4eac\u5927\u5b66 \u67cf\u30ad\u30e3\u30f3\u30d1\u30b9, \u5b66\u878d\u5408\u306e\u9053, \u67cf\u5e02, \u5343\u8449\u770c, \u95a2\u6771\u5730\u65b9, 277-8583, \u65e5\u672c", "lat": "35.90204480", "lng": "139.93622009", "type": "edu", "country": "Japan"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1603.09046.pdf"], "doi": []}, {"id": "697f0e24f24b016cef9474db485fe61a667f07b8", "title": "VISER: Visual Self-Regularization", "addresses": [{"name": "University of Washington", "source_name": "University of Washington", "street_adddress": "University of Washington, Rainier Vista, Montlake, University District, Seattle, King County, Washington, 98195, USA", "lat": "47.65432380", "lng": "-122.30800894", "type": "edu", "country": "United States"}, {"name": "Yahoo Research", "source_name": "Yahoo Research, USA", "street_adddress": "1680 N Glenville Dr # 100, Richardson, TX 75081, USA", "lat": "32.97000100", "lng": "-96.70543110", "type": "company", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.02568.pdf"], "doi": []}, {"id": "9138045b7164876f9c2d6c5891d1f3d13a147d84", "title": "Combining Weakly and Webly Supervised Learning for Classifying Food Images", "addresses": [{"name": "Rutgers University", "source_name": "Rutgers University", "street_adddress": "Rutgers Cook Campus - North, Biel Road, New Brunswick, Middlesex County, New Jersey, 08901, USA", "lat": "40.47913175", "lng": "-74.43168868", "type": "edu", "country": "United States"}, {"name": "SRI International", "source_name": "SRI International", "street_adddress": "SRI International Building, West 1st Street, Menlo Park, San Mateo County, California, 94025, USA", "lat": "37.45857960", "lng": "-122.17560525", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1712.08730.pdf"], "doi": []}, {"id": "0ee3aa2a78f9680bb65a823bd9195c879572ec1c", "title": "What Makes an Object Memorable?", "addresses": [{"name": "King Abdullah University of Science and Technology", "source_name": "King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia", "street_adddress": "Thuwal 23955, Saudi Arabia", "lat": "22.30946500", "lng": "39.10469700", "type": "edu", "country": "Saudi Arabia"}, {"name": "University of California, Berkeley", "source_name": "University of California, Berkeley", "street_adddress": "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "lat": "37.86871260", "lng": "-122.25586815", "type": "edu", "country": "United States"}, {"name": "MIT", "source_name": "Massachusetts Institute", "street_adddress": "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu", "country": "United States"}, {"name": "University of California, Merced", "source_name": "University of California, Merced", "street_adddress": "University of California, Merced, Ansel Adams Road, Merced County, California, USA", "lat": "37.36566745", "lng": "-120.42158888", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["http://faculty.ucmerced.edu/mhyang/papers/iccv15_memorability.pdf", "http://openaccess.thecvf.com/content_iccv_2015/papers/Dubey_What_Makes_an_ICCV_2015_paper.pdf", "http://people.csail.mit.edu/khosla/papers/iccv2015_dubey.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Dubey_What_Makes_an_ICCV_2015_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410487", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2015.130", "http://doi.org/10.1109/ICCV.2015.130"]}, {"id": "bddf7da5a21a5d1915cc9ee784223adadbe0aec4", "title": "Question action relevance and editing for visual question answering", "addresses": [{"name": "George Mason University", "source_name": "George Mason University", "street_adddress": "George Mason University, Aquia Creek Lane, Country Club View, Blue Oaks, Fairfax County, Virginia, 22030-9998, USA", "lat": "38.83133325", "lng": "-77.30798839", "type": "edu", "country": "United States"}, {"name": "Dipartimento di Informatica, Universit\u00e0 di Salerno, Fisciano, Italy", "source_name": "Dipartimento di Informatica, Universit\u00e0 di Salerno, Fisciano, Italy", "street_adddress": "Universit\u00e0 di Salerno Via Papa, Via Giovanni Paolo II, 132, 84084 Fisciano SA, Italy", "lat": "40.77434920", "lng": "14.78901500", "type": "edu", "country": "Italy"}], "year": "2018", "pdf": [], "doi": ["http://doi.org/10.1007/s11042-018-6097-z"]}, {"id": "76b6577f47d6782bf75aca04e361a7b7381b4a84", "title": "Measuring and Modifying the Intrinsic Memorability of Images", "addresses": [{"name": "MIT", "source_name": "Massachusetts Institute", "street_adddress": "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/76b6/577f47d6782bf75aca04e361a7b7381b4a84.pdf"], "doi": []}, {"id": "41a96329d93e7b06ebd6b3a761cc0d50375c5f15", "title": "Visual Learning Beyond Direct Supervision", "addresses": [{"name": "University of California at Berkeley", "source_name": "International Computer Science Institute, University of California at Berkeley, Berkeley, USA", "street_adddress": "1947 Center St, Berkeley, CA 94704, USA", "lat": "37.87015430", "lng": "-122.27123120", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://www2.eecs.berkeley.edu/Pubs/TechRpts/2018/EECS-2018-128.pdf"], "doi": ["https://www.base-search.net/Record/2a66cc65fb84214dedf1e3019655a0c160d394ee4e1457c1e1301e57cce6ca94"]}, {"id": "8e325b234e9cb67c285fc256c7e51d5e326952d1", "title": "Single-Shot Bidirectional Pyramid Networks for High-Quality Object Detection", "addresses": [{"name": "Singapore Management University", "source_name": "Singapore Management University", "street_adddress": "Singapore Management University, Fort Canning Tunnel, Clarke Quay, City Hall, Singapore, Central, 178895, Singapore", "lat": "1.29500195", "lng": "103.84909214", "type": "edu", "country": "Singapore"}, {"name": "Zhejiang University", "source_name": "Zhejiang University", "street_adddress": "\u6d59\u6c5f\u5927\u5b66\u4e4b\u6c5f\u6821\u533a, \u4e4b\u6c5f\u8def, \u8f6c\u5858\u8857\u9053, \u897f\u6e56\u533a (Xihu), \u676d\u5dde\u5e02 Hangzhou, \u6d59\u6c5f\u7701, 310008, \u4e2d\u56fd", "lat": "30.19331415", "lng": "120.11930822", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.08208.pdf"], "doi": []}, {"id": "b90efd4e0a2267b1c47d31ead3c860acb4364cee", "title": "MetaAnchor: Learning to Detect Objects with Customized Anchors", "addresses": [{"name": "Fudan University", "source_name": "Fudan University", "street_adddress": "\u590d\u65e6\u5927\u5b66, 220, \u90af\u90f8\u8def, \u4e94\u89d2\u573a\u8857\u9053, \u6768\u6d66\u533a, \u4e0a\u6d77\u5e02, 200433, \u4e2d\u56fd", "lat": "31.30104395", "lng": "121.50045497", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.00980.pdf"], "doi": []}, {"id": "0489a21c77d1646ea3af48d678c3ad9645eef2a9", "title": "Large-Scale Sparse Learning From Noisy Tags for Semantic Segmentation", "addresses": [{"name": "Renmin University of China", "source_name": "Beijing Key Laboratory of Big Data Management and Analysis Methods, Renmin University of China, Beijing, 100872, China", "street_adddress": "59 Zhongguancun St, Haidian Qu, China, 100872", "lat": "39.96960620", "lng": "116.31881450", "type": "edu", "country": "China"}, {"name": "Peking University", "source_name": "Peking University", "street_adddress": "\u5317\u4eac\u5927\u5b66, 5\u53f7, \u9890\u548c\u56ed\u8def, \u7a3b\u9999\u56ed\u5357\u793e\u533a, \u6d77\u6dc0\u533a, \u5317\u4eac\u5e02, 100871, \u4e2d\u56fd", "lat": "39.99223790", "lng": "116.30393816", "type": "edu", "country": "China"}], "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7765089", "https://www.ncbi.nlm.nih.gov/pubmed/27925605"]}, {"id": "fa2d3c78981ef0e19557e51d85b6dda05345c380", "title": "Detection of valuable left-behind items in vehicle cabins", "addresses": [{"name": "Jaguar Land Rover Research, Coventry, UK", "source_name": "Jaguar Land Rover Research, Coventry, UK", "street_adddress": "Viscount Centre C, Milburn Hill Rd, Coventry CV4 7HS, United Kingdom", "lat": "52.38558050", "lng": "-1.56086400", "type": "company", "country": "United Kingdom"}, {"name": "University of Bristol", "source_name": "University of Bristol", "street_adddress": "Victoria Rooms, Whiteladies Road, Cliftonwood, Spike Island, Bristol, City of Bristol, South West England, England, BS8 2PY, UK", "lat": "51.45848370", "lng": "-2.60977520", "type": "edu", "country": "United Kingdom"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7995862", "http://doi.org/10.1109/IVS.2017.7995862"]}, {"id": "0000fcfd467a19cf0e59169c2f07d730a0f3a8b9", "title": "Exploring Visual Relationship for Image Captioning", "addresses": [{"name": "Sun Yat-Sen University", "source_name": "Sun Yat-Sen University", "street_adddress": "\u4e2d\u5927, \u65b0\u6e2f\u897f\u8def, \u9f99\u8239\u6ed8, \u5eb7\u4e50, \u6d77\u73e0\u533a (Haizhu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510105, \u4e2d\u56fd", "lat": "23.09461185", "lng": "113.28788994", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.07041.pdf"], "doi": []}, {"id": "c93e26b52cb22382ed2627bf32f86fa18d034cbf", "title": "Discriminative Learning of Open-Vocabulary Object Retrieval and Localization by Negative Phrase Augmentation", "addresses": [{"name": "University of Tokyo", "source_name": "University of Tokyo", "street_adddress": "\u6771\u4eac\u5927\u5b66 \u67cf\u30ad\u30e3\u30f3\u30d1\u30b9, \u5b66\u878d\u5408\u306e\u9053, \u67cf\u5e02, \u5343\u8449\u770c, \u95a2\u6771\u5730\u65b9, 277-8583, \u65e5\u672c", "lat": "35.90204480", "lng": "139.93622009", "type": "edu", "country": "Japan"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.09509.pdf"], "doi": []}, {"id": "57922243faec5a60473fb9ec32d9adcd94fb6cc8", "title": "Identifying Most Walkable Direction for Navigation in an Outdoor Environment", "addresses": [{"name": "University of Washington", "source_name": "University of Washington", "street_adddress": "University of Washington, Rainier Vista, Montlake, University District, Seattle, King County, Washington, 98195, USA", "lat": "47.65432380", "lng": "-122.30800894", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1711.08040.pdf"], "doi": []}, {"id": "89588a697c8b81e38d3793db5055a65c4abc4845", "title": "Swap Retrieval: Retrieving Images of Cats When the Query Shows a Dog", "addresses": [{"name": "KULeuven, Leuven, Belgium", "source_name": "KULeuven, Leuven, Belgium", "street_adddress": "Oude Markt 13, 3000 Leuven, Belgium", "lat": "50.87795450", "lng": "4.70029530", "type": "edu", "country": "Spain"}], "year": "2015", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=2749373"]}, {"id": "1b793cc5dceb98c95e816aebc2252205bfd71569", "title": "ADNet: A Deep Network for Detecting Adverts", "addresses": [{"name": "Trinity College Dublin", "source_name": "Trinity College Dublin, Dublin 2, Ireland", "street_adddress": "College Green, Dublin 2, Co. Dublin, Ireland", "lat": "53.34379350", "lng": "-6.25457160", "type": "edu", "country": "Ireland"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.04115.pdf"], "doi": []}, {"id": "532c089b43983935e1001c5e35aa35440263beaf", "title": "G-Distillation: Reducing Overconfident Errors on Novel Samples", "addresses": [{"name": "University of Illinois, Urbana-Champaign", "source_name": "University of Illinois, Urbana-Champaign", "street_adddress": "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.03166.pdf"], "doi": []}, {"id": "20e24a40dc855fa69aa3d85b4bfdcfb8c9dadb74", "title": "Multi-Networks Joint Learning for Large-Scale Cross-Modal Retrieval", "addresses": [{"name": "University of Chinese Academy of Sciences", "source_name": "University of Chinese Academy of Sciences", "street_adddress": "University of Chinese Academy of Sciences, UCAS, Yuquanlu, \u7389\u6cc9\u8def, \u7530\u6751, \u6d77\u6dc0\u533a, 100049, \u4e2d\u56fd", "lat": "39.90828040", "lng": "116.24585270", "type": "edu", "country": "China"}, {"name": "University of Texas at San Antonio", "source_name": "University of Texas at San Antonio", "street_adddress": "UTSA, Paseo Principal, San Antonio, Bexar County, Texas, 78249-1620, USA", "lat": "29.58333105", "lng": "-98.61944505", "type": "edu", "country": "United States"}], "year": "2017", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3123317"]}, {"id": "04e2b2eab1966ffb0079685baf169d4d7ad4ec8c", "title": "Detecting Sex From Handwritten Examples", "addresses": [{"name": "Independent University Bangladesh", "source_name": "Fab Lab, Independent University Bangladesh, Dhaka, Bangladesh", "street_adddress": "Independent University, Bangladesh Plot 16, \u0986\u09ab\u09a4\u09be\u09ac \u0989\u09a6\u09cd\u09a6\u09bf\u09a8 \u0986\u09b9\u09ae\u09c7\u09a6 \u09b0\u09cb\u09a1, \u09a2\u09be\u0995\u09be, Bangladesh", "lat": "23.81524690", "lng": "90.42796720", "type": "edu", "country": "Bangladesh"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8541214", "http://doi.org/10.1109/icscan.2018.8541214"]}, {"id": "00e19d93780ecf8f807c510a1105749d5bb1a2f3", "title": "Image Description using Deep Neural Networks", "addresses": [{"name": "Rochester Institute of Technology", "source_name": "Rochester Institute of Technology", "street_adddress": "Rochester Institute of Technology (RIT), 1, Lomb Memorial Drive, Bailey, Henrietta Town, Monroe County, New York, 14623, USA", "lat": "43.08250655", "lng": "-77.67121663", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/00e1/9d93780ecf8f807c510a1105749d5bb1a2f3.pdf"], "doi": []}, {"id": "6f3a1216e984c78e7374b3b7ab05612544d345eb", "title": "DeRPN: Taking a further step toward more general object detection", "addresses": [{"name": "South China University of Technology", "source_name": "South China University of Technology", "street_adddress": "\u534e\u5357\u7406\u5de5\u5927\u5b66, \u5927\u5b66\u57ce\u4e2d\u73af\u4e1c\u8def, \u5e7f\u5dde\u5927\u5b66\u57ce, \u65b0\u9020, \u756a\u79ba\u533a (Panyu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510006, \u4e2d\u56fd", "lat": "23.05020420", "lng": "113.39880323", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.06700.pdf"], "doi": []}, {"id": "e2d1e72fdb7e0b7a3ebb9ddc4cc161566ab74de2", "title": "Person Search via a Mask-Guided Two-Stream CNN Model", "addresses": [{"name": "Nanjing University", "source_name": "Nanjing University", "street_adddress": "NJU, \u4e09\u6c5f\u8def, \u9f13\u697c\u533a, \u5357\u4eac\u5e02, \u6c5f\u82cf\u7701, 210093, \u4e2d\u56fd", "lat": "32.05659570", "lng": "118.77408833", "type": "edu", "country": "China"}, {"name": "University of Sydney", "source_name": "University of Sydney", "street_adddress": "USyd, Fisher Road, Camperdown, Sydney, NSW, 2006, Australia", "lat": "-33.88890695", "lng": "151.18943366", "type": "edu", "country": "Australia"}, {"name": "Tencent", "source_name": "Tencent", "street_adddress": "Ke Ji Zhong Yi Lu, Nanshan Qu, Shenzhen Shi, Guangdong Sheng, China, 518057", "lat": "22.54471540", "lng": "113.93571640", "type": "company", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.08107.pdf"], "doi": []}, {"id": "10706113b871354248beb37fe5bb2f31925f7a68", "title": "A Vision-based Transfer Learning Approach for Recognizing Behavioral Symptoms in People with Dementia", "addresses": [{"name": "Edge Hill University", "source_name": "Edge Hill University", "street_adddress": "Edge Hill University, St Helens Road, West Lancashire, Lancs, North West England, England, L39 4QP, UK", "lat": "53.55821550", "lng": "-2.86904651", "type": "edu", "country": "United Kingdom"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8639371"]}, {"id": "3921afded8bc8471d784df86f64432fb14b8ef58", "title": "Egocentric Gesture Recognition for Head-Mounted AR devices", "addresses": [{"name": "Trinity College Dublin", "source_name": "Trinity College Dublin, Dublin 2, Ireland", "street_adddress": "College Green, Dublin 2, Co. Dublin, Ireland", "lat": "53.34379350", "lng": "-6.25457160", "type": "edu", "country": "Ireland"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.05380.pdf"], "doi": []}, {"id": "d9519d66f9844fcf306cc205593a55cf01090633", "title": "Image2song: Song Retrieval via Bridging Image Content and Lyric Words", "addresses": [{"name": "Chinese Academy of Sciences", "source_name": "Chinese Academy of Sciences", "street_adddress": "\u4e2d\u56fd\u79d1\u5b66\u9662\u5fc3\u7406\u7814\u7a76\u6240, 16, \u6797\u8403\u8def, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100101, \u4e2d\u56fd", "lat": "40.00447950", "lng": "116.37023800", "type": "edu", "country": "China"}, {"name": "Northwestern Polytechnical University", "source_name": "Northwestern Polytechnical University", "street_adddress": "\u897f\u5317\u5de5\u4e1a\u5927\u5b66 \u53cb\u8c0a\u6821\u533a, 127\u53f7, \u53cb\u8c0a\u897f\u8def, \u957f\u5b89\u8def, \u7891\u6797\u533a (Beilin), \u897f\u5b89\u5e02, \u9655\u897f\u7701, 710072, \u4e2d\u56fd", "lat": "34.24691520", "lng": "108.91061982", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.05851.pdf"], "doi": []}, {"id": "b5bfe824fc49fe78b538ac15f21c4cd6a9d44347", "title": "Image Caption with Synchronous Cross-Attention", "addresses": [{"name": "Beijing University of Posts and Telecommunications", "source_name": "Beijing University of Posts and Telecommunications", "street_adddress": "\u5317\u4eac\u90ae\u7535\u5927\u5b66, \u897f\u571f\u57ce\u8def, \u6d77\u6dc0\u533a, \u5317\u4eac\u5e02, 100082, \u4e2d\u56fd", "lat": "39.96014880", "lng": "116.35193921", "type": "edu", "country": "China"}], "year": "2017", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3126714"]}, {"id": "6220d0424bc7357e7e381d59baecdff91062ba81", "title": "A Fully Convolutional Two-Stream Fusion Network for Interactive Image Segmentation", "addresses": [{"name": "Loughborough University", "source_name": "Loughborough University", "street_adddress": "Computer Science, University Road, Charnwood, Leicestershire, East Midlands, England, LE11 3TP, UK", "lat": "52.76635770", "lng": "-1.22924610", "type": "edu", "country": "United Kingdom"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1807.02480.pdf"], "doi": []}, {"id": "c8671a739a95f57946a625c3eada1f4addc60aea", "title": "Transferable Interactiveness Prior for Human-Object Interaction Detection", "addresses": [{"name": "Shanghai Jiao Tong University", "source_name": "Shanghai Jiao Tong University", "street_adddress": "\u4e0a\u6d77\u4ea4\u901a\u5927\u5b66\uff08\u5f90\u6c47\u6821\u533a\uff09, \u6dee\u6d77\u897f\u8def, \u756a\u79ba\u5c0f\u533a, \u5e73\u9634\u6865, \u5f90\u6c47\u533a, \u4e0a\u6d77\u5e02, 200052, \u4e2d\u56fd", "lat": "31.20081505", "lng": "121.42840681", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.08264.pdf"], "doi": []}, {"id": "e38c7d4f8a4399f402ab6bb364ec662fe897bed1", "title": "PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentation", "addresses": [{"name": "RWTH Aachen University", "source_name": "RWTH Aachen University", "street_adddress": "RWTH Aachen, Mies-van-der-Rohe-Stra\u00dfe, K\u00f6nigsh\u00fcgel, Aachen-Mitte, Aachen, St\u00e4dteregion Aachen, Regierungsbezirk K\u00f6ln, Nordrhein-Westfalen, 52074, Deutschland", "lat": "50.77917030", "lng": "6.06728733", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.09190.pdf"], "doi": []}, {"id": "d3bbd57899d938e8c4bcafbbda10ceb59638e4db", "title": "Skip-Thought Vectors", "addresses": [{"name": "University of Toronto", "source_name": "University of Toronto", "street_adddress": "University of Toronto, St. George Street, Bloor Street Culture Corridor, Old Toronto, Toronto, Ontario, M5S 1A5, Canada", "lat": "43.66333345", "lng": "-79.39769975", "type": "edu", "country": "Canada"}, {"name": "MIT", "source_name": "Massachusetts Institute", "street_adddress": "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1506.06726.pdf"], "doi": []}, {"id": "11da2d589485685f792a8ac79d4c2e589e5f77bd", "title": "Show and tell: A neural image caption generator", "addresses": [{"name": "Google", "source_name": "Google, Inc.", "street_adddress": "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "lat": "37.42199990", "lng": "-122.08405750", "type": "company", "country": "United States"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1411.4555.pdf"], "doi": []}, {"id": "0ae247153afd87f98829359a8b5df0f68d788d75", "title": "A Corpus for Reasoning About Natural Language Grounded in Photographs", "addresses": [{"name": "Cornell University", "source_name": "Cornell University", "street_adddress": "Cornell University, Forest Home Drive, Forest Home, Tompkins County, New York, 14853, USA", "lat": "42.45055070", "lng": "-76.47835130", "type": "edu", "country": "United States"}, {"name": "University of Maryland", "source_name": "University of Maryland", "street_adddress": "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.00491.pdf"], "doi": []}, {"id": "30795da8026e875faaffa3d6f2fa03c9c5d14c55", "title": "Richer Semantic Visual and Language Representation for Video Captioning", "addresses": [{"name": "Tongji University", "source_name": "Tongji University", "street_adddress": "\u540c\u6d4e\u5927\u5b66, 1239, \u56db\u5e73\u8def, \u6c5f\u6e7e, \u8679\u53e3\u533a, \u4e0a\u6d77\u5e02, 200092, \u4e2d\u56fd", "lat": "31.28473925", "lng": "121.49694909", "type": "edu", "country": "China"}], "year": "2017", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3127895"]}, {"id": "2675a66b3f8743cf0551f284244af4f24537c19b", "title": "Learning Visually Grounded Sentence Representations", "addresses": [{"name": "UC Berkeley", "source_name": "UC Berkeley", "street_adddress": "Berkeley, CA, USA", "lat": "37.87189920", "lng": "-122.25853990", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1707.06320.pdf"], "doi": []}, {"id": "5f79398057bf0bbda9ff50067bc1f2950c2a2266", "title": "Progressive Neural Architecture Search", "addresses": [{"name": "Johns Hopkins University", "source_name": "Johns Hopkins University", "street_adddress": "Baltimore, MD 21218, USA", "lat": "39.32990130", "lng": "-76.62051770", "type": "edu", "country": "United States"}, {"name": "Stanford University", "source_name": "Stanford University", "street_adddress": "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1712.00559.pdf"], "doi": []}, {"id": "02588064dd2b4b56d1dad214c1af3a7518832a59", "title": "A survey on deep neural network-based image captioning", "addresses": [{"name": "Dalian Maritime University", "source_name": "Dalian Maritime University, Dalian, China", "street_adddress": "1 Linghai Rd, Ganjingzi Qu, Dalian Shi, Liaoning Sheng, China", "lat": "38.87004100", "lng": "121.53414100", "type": "edu", "country": "China"}, {"name": "Shandong University", "source_name": "Shandong University", "street_adddress": "\u5c71\u4e1c\u5927\u5b66, \u6cf0\u5b89\u8857, \u9ccc\u5c71\u536b\u8857\u9053, \u5373\u58a8\u533a, \u9752\u5c9b\u5e02, \u5c71\u4e1c\u7701, 266200, \u4e2d\u56fd", "lat": "36.36934730", "lng": "120.67381800", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://doi.org/10.1007/s00371-018-1566-y"]}, {"id": "bb93c56a44a244601daad96a7bb94e41609afc4d", "title": "Towards Improved Design and Evaluation of Epileptic Seizure Predictors", "addresses": [{"name": "Ghent University", "source_name": "Ghent University", "street_adddress": "St. Pietersnieuwstraat 33, 9000 Gent, Belgium", "lat": "51.04656190", "lng": "3.72791810", "type": "edu", "country": "Belgium"}, {"name": "TU Berlin", "source_name": "TU Berlin", "street_adddress": "Franklinstra\u00dfe 28-29, 10587 Berlin, Germany", "lat": "52.51806410", "lng": "13.32504250", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": ["https://biblio.ugent.be/publication/8519033/file/8520709.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7915772", "http://doi.org/10.1109/TBME.2017.2700086", "https://www.ncbi.nlm.nih.gov/pubmed/28475041", "https://www.wikidata.org/entity/Q38687464"]}, {"id": "19aa506d04d3f7241fc71b595d28b5f1bb99edad", "title": "Compact Generalized Non-local Network", "addresses": [{"name": "Central South University", "source_name": "Central South University, Changsha, People\u2019s Republic of China", "street_adddress": "932 Lushan S Rd, Yuelu Qu, Changsha Shi, Hunan Sheng, China", "lat": "28.16437000", "lng": "112.93251000", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.13125.pdf"], "doi": []}, {"id": "738947f9b0bc50d1b7d5cbe84856bc18fcaee386", "title": "Deep learning-based human head detection and extraction for robotic portrait drawing", "addresses": [{"name": "Northeastern University", "source_name": "Northeastern University", "street_adddress": "Snell Library, 360, Huntington Avenue, Roxbury Crossing, Fenway, Boston, Suffolk County, Massachusetts, 02115, USA", "lat": "42.33836680", "lng": "-71.08793524", "type": "edu", "country": "United States"}, {"name": "Shenzhen Academy of Robotics, Shenzhen, Guangdong, China", "source_name": "Shenzhen Academy of Robotics, Shenzhen, Guangdong, China", "street_adddress": "Shenzhen, Guangdong, China", "lat": "22.54309600", "lng": "114.05786500", "type": "edu", "country": "China"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8324594", "http://doi.org/10.1109/ROBIO.2017.8324594"]}, {"id": "80acc73e29fb324a3e01113bbeddccacaf5283f1", "title": "Generate, Segment and Replace: Towards Generic Manipulation Segmentation.", "addresses": [{"name": "University of Maryland", "source_name": "University of Maryland", "street_adddress": "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.09729.pdf"], "doi": []}, {"id": "b4c48aa7a93f38d2eb60209120a1a8daa61c4545", "title": "Diversity in Object Proposals", "addresses": [{"name": "University of Augsburg", "source_name": "Multimedia Computing Lab, University of Augsburg, Germany", "street_adddress": "Universit\u00e4tsstra\u00dfe 2, 86159 Augsburg, Germany", "lat": "48.33282440", "lng": "10.89656160", "type": "edu", "country": "Germany"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1603.04308.pdf"], "doi": []}, {"id": "26e425781e4090abfae65b5d68eac72282dd2e31", "title": "Image Captioning with Deep Bidirectional LSTMs", "addresses": [{"name": "University of Potsdam", "source_name": "Hasso Plattner Institute, University of Potsdam, Prof.-Dr.-Helmert-Str. 2-3, 14482, Germany", "street_adddress": "Prof.-Dr.-Helmert-Stra\u00dfe 2-3, 14482 Potsdam, Germany", "lat": "52.39399650", "lng": "13.13336570", "type": "edu", "country": "Germany"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1604.00790.pdf"], "doi": []}, {"id": "d6c3f9edf5459db8633f9155f55e6f735dd0ce8b", "title": "Edge-Cloud Collaborative Processing for Intelligent Internet of Things: A Case Study on Smart Surveillance", "addresses": [{"name": "Georgia Institute of Technology", "source_name": "Georgia Institute of Technology", "street_adddress": "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu", "country": "United States"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3196036"]}, {"id": "f831f81f34a9c9dde41c5250b1a9dadf8ec8963b", "title": "Video Object Segmentation with Re-identification", "addresses": [{"name": "Chinese University of Hong Kong", "source_name": "Chinese University of Hong Kong", "street_adddress": "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "lat": "22.41626320", "lng": "114.21093180", "type": "edu", "country": "China"}, {"name": "Harbin Institute of Technology", "source_name": "Harbin Institute of Technology", "street_adddress": "\u54c8\u5c14\u6ee8\u5de5\u4e1a\u5927\u5b66, \u53f8\u4ee4\u8857, \u5357\u5c97\u533a, \u54c8\u5c14\u6ee8\u5e02 / Harbin, \u9ed1\u9f99\u6c5f\u7701, 150000, \u4e2d\u56fd", "lat": "45.74139210", "lng": "126.62552755", "type": "edu", "country": "China"}, {"name": "SenseTime", "source_name": "SenseTime", "street_adddress": "China, Beijing Shi, Haidian Qu, WuDaoKou, Zhongguancun E Rd, 1\u53f7-7", "lat": "39.99300800", "lng": "116.32988200", "type": "company", "country": "China"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.00197.pdf"], "doi": []}, {"id": "b29c83b6ee10857e09ac3503916ae1b129642cae", "title": "Mo 2 Cap 2 : Real-time Mo bile 3 D Mo tion Cap ture with a Cap-mounted Fisheye Camera", "addresses": [{"name": "Stanford University", "source_name": "Stanford University", "street_adddress": "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/b29c/83b6ee10857e09ac3503916ae1b129642cae.pdf"], "doi": []}, {"id": "f3b24cdbd1e7fd94d7ad1fa077dfa051bcc8aa38", "title": "AUTOMATIC IMAGE ANNOTATION MODEL USING LSTM APPROACH", "addresses": [{"name": "Varanasi", "source_name": "Varanasi", "street_adddress": "Varanasi, Uttar Pradesh, India", "lat": "25.31764520", "lng": "82.97391440", "type": "edu", "country": "India"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/f3b2/4cdbd1e7fd94d7ad1fa077dfa051bcc8aa38.pdf"], "doi": []}, {"id": "4f0d7f2926061c9dd6081d95eb9755812f9a16c2", "title": "Videos as Space-Time Region Graphs", "addresses": [{"name": "Robotics Institute", "source_name": "Robotics Institute", "street_adddress": "Institute for Field Robotics, \u0e1b\u0e23\u0e30\u0e0a\u0e32\u0e2d\u0e38\u0e17\u0e34\u0e28, \u0e01\u0e23\u0e38\u0e07\u0e40\u0e17\u0e1e\u0e21\u0e2b\u0e32\u0e19\u0e04\u0e23, \u0e40\u0e02\u0e15\u0e23\u0e32\u0e29\u0e0e\u0e23\u0e4c\u0e1a\u0e39\u0e23\u0e13\u0e30, \u0e01\u0e23\u0e38\u0e07\u0e40\u0e17\u0e1e\u0e21\u0e2b\u0e32\u0e19\u0e04\u0e23, 10140, \u0e1b\u0e23\u0e30\u0e40\u0e17\u0e28\u0e44\u0e17\u0e22", "lat": "13.65450525", "lng": "100.49423171", "type": "edu", "country": "Thailand"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.01810.pdf"], "doi": []}, {"id": "ad6dedc3f56b1ef2c083cb13c2638eddf208d49b", "title": "An object based graph representation for video comparison", "addresses": [{"name": "Chongqing University of Technology", "source_name": "Chongqing University of Technology, China", "street_adddress": "69 Hongguang Ave, Banan Qu, Chongqing Shi, China", "lat": "29.45832600", "lng": "106.52994700", "type": "edu", "country": "China"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8296742", "http://doi.org/10.1109/ICIP.2017.8296742"]}, {"id": "cdabc1f190e8841ec6cd5f7cb4a3cd3016d292de", "title": "Stroke Controllable Fast Style Transfer with Adaptive Receptive Fields", "addresses": [{"name": "Zhejiang University", "source_name": "Zhejiang University", "street_adddress": "\u6d59\u6c5f\u5927\u5b66\u4e4b\u6c5f\u6821\u533a, \u4e4b\u6c5f\u8def, \u8f6c\u5858\u8857\u9053, \u897f\u6e56\u533a (Xihu), \u676d\u5dde\u5e02 Hangzhou, \u6d59\u6c5f\u7701, 310008, \u4e2d\u56fd", "lat": "30.19331415", "lng": "120.11930822", "type": "edu", "country": "China"}, {"name": "Arizona State University", "source_name": "Arizona State University", "street_adddress": "Arizona State University Polytechnic campus, East Texas Avenue, Mesa, Maricopa County, Arizona, 85212, USA", "lat": "33.30715065", "lng": "-111.67653157", "type": "edu", "country": "United States"}, {"name": "University of Sydney", "source_name": "University of Sydney", "street_adddress": "USyd, Fisher Road, Camperdown, Sydney, NSW, 2006, Australia", "lat": "-33.88890695", "lng": "151.18943366", "type": "edu", "country": "Australia"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.07101.pdf"], "doi": []}, {"id": "d9aca4cfe6bf49056c4bc6796414355a59cf5fb5", "title": "3D-SSD: Learning Hierarchical Features from RGB-D Images for Amodal 3D Object Detection", "addresses": [{"name": "Zhejiang University", "source_name": "Zhejiang University", "street_adddress": "\u6d59\u6c5f\u5927\u5b66\u4e4b\u6c5f\u6821\u533a, \u4e4b\u6c5f\u8def, \u8f6c\u5858\u8857\u9053, \u897f\u6e56\u533a (Xihu), \u676d\u5dde\u5e02 Hangzhou, \u6d59\u6c5f\u7701, 310008, \u4e2d\u56fd", "lat": "30.19331415", "lng": "120.11930822", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1711.00238.pdf"], "doi": []}, {"id": "11f515ead5b4a7259668f2620e808fa8ba5ea65c", "title": "Phrase Localization and Visual Relationship Detection with Comprehensive Image-Language Cues", "addresses": [{"name": "University of Illinois, Urbana-Champaign", "source_name": "University of Illinois, Urbana-Champaign", "street_adddress": "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1611.06641.pdf"], "doi": []}, {"id": "d0593359627cd0744740ea50731d2b98ff6b1937", "title": "Short-term memory with read-only unit in neural image caption generator", "addresses": [{"name": "Institute for Informatics and Automation Problems of NAS RA, Yerevan, Armenia", "source_name": "Institute for Informatics and Automation Problems of NAS RA, Yerevan, Armenia", "street_adddress": "62/1 Paruyr Sevak St, Yerevan, Armenia", "lat": "40.21254620", "lng": "44.53266140", "type": "edu", "country": "Armenia"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8312163"]}, {"id": "85e283564fca1d1cf4d142647561901a26f144c6", "title": "On the Origin of Deep Learning On the Origin of Deep Learning", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/85e2/83564fca1d1cf4d142647561901a26f144c6.pdf"], "doi": []}, {"id": "3e198f28343fccf502bc20191660dd090ba5356d", "title": "Accurate License Plate Recognition and Super-Resolution Using a Generative Adversarial Networks on Traffic Surveillance Video", "addresses": [{"name": "Gwangju Institute of Science and Technology", "source_name": "Gwangju Institute of Science and Technology", "street_adddress": "123 Cheomdangwagi-ro, Oryong-dong, Buk-gu, Kwangju, South Korea", "lat": "35.22652880", "lng": "126.83998700", "type": "edu", "country": "South Korea"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8552121", "http://doi.org/10.1109/icce-asia.2018.8552121"]}, {"id": "bc1d609520290e0460c49b685675eb5a57fa5935", "title": "An efficient framework for learning sentence representations", "addresses": [{"name": "University of Michigan", "source_name": "University of Michigan", "street_adddress": "University of Michigan, 500, Hayward Street, Ann Arbor, Washtenaw County, Michigan, 48109, USA", "lat": "42.29421420", "lng": "-83.71003894", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.02893.pdf"], "doi": []}, {"id": "704b46c9c255cd22b4712dcc6bc417d6fefc1e18", "title": "Learning RoI Transformer for Detecting Oriented Objects in Aerial Images", "addresses": [{"name": "Wuhan University of Technology", "source_name": "Wuhan University of Technology", "street_adddress": "\u6b66\u6c49\u7406\u5de5\u5927\u5b66-\u4f59\u5bb6\u5934\u6821\u533a, \u4ea4\u901a\u4e8c\u8def, \u6768\u56ed\u8857\u9053, \u6b66\u660c\u533a (Wuchang), \u6b66\u6c49\u5e02, \u6e56\u5317\u7701, 430062, \u4e2d\u56fd", "lat": "30.60903415", "lng": "114.35142840", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.00155.pdf"], "doi": []}, {"id": "7f1d7688c4923cab09bf0a548e6f1fc1dd916b51", "title": "Boundary aware image segmentation with unsupervised mixture models", "addresses": [{"name": "Technical University Dortmund", "source_name": "Image Analysis Group, Technical University Dortmund, Otto-Hahn-Str. 4, 44227 Dortmund, Germany", "street_adddress": "Emil-Figge-Stra\u00dfe 50, 44227 Dortmund, Germany", "lat": "51.49219020", "lng": "7.41413620", "type": "edu", "country": "Germany"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8296898", "http://doi.org/10.1109/ICIP.2017.8296898"]}, {"id": "0730d5f4408ab3c3bcc316ecbbfdc61cdbf7d813", "title": "Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Video", "addresses": [{"name": "University of Bucharest", "source_name": "University of Bucharest, 14 Academiei Street, Bucharest, Romania", "street_adddress": "Strada Academiei 14, Bucure\u0219ti 010014, Romania", "lat": "44.43546330", "lng": "26.09968830", "type": "edu", "country": "Romania"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.04960.pdf"], "doi": []}, {"id": "3d22f972448a2336677ae6ff2877fae010c7dfa2", "title": "What is the Role of Recurrent Neural Networks (RNNs) in an Image Caption Generator?", "addresses": [{"name": "University of Malta", "source_name": "University of Malta", "street_adddress": "University of Malta, Ring Road, Japanese Garden, L-Imsida, Malta, MSD 9027, Malta", "lat": "35.90232260", "lng": "14.48341890", "type": "edu", "country": "Malta"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.02043.pdf"], "doi": []}, {"id": "c0ef854f4119a74b37211aa4cc36b8c1addd9057", "title": "Training object class detectors with click supervision Dim", "addresses": [{"name": "University of Edinburgh", "source_name": "University of Edinburgh", "street_adddress": "New College, New College Courtyard, The Mound, Old Town, Edinburgh, City of Edinburgh, Scotland, EH1 2LX, UK", "lat": "55.94951105", "lng": "-3.19534913", "type": "edu", "country": "United Kingdom"}], "year": "", "pdf": ["https://pdfs.semanticscholar.org/c0ef/854f4119a74b37211aa4cc36b8c1addd9057.pdf"], "doi": []}, {"id": "0e23229289b1fbea14bc425718bc0a227d100b8e", "title": "Survey of Recent Advances in Visual Question Answering", "addresses": [{"name": "Hyderabad, India", "source_name": "Hyderabad, India", "street_adddress": "Hyderabad, Telangana, India", "lat": "17.38504400", "lng": "78.48667100", "type": "edu", "country": "India"}, {"name": "Adobe Systems", "source_name": "Adobe Systems", "street_adddress": "343 Preston St, Ottawa, ON K1S 1N4, Canada", "lat": "45.40242130", "lng": "-75.70955410", "type": "edu", "country": "South Korea"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1709.08203.pdf"], "doi": []}, {"id": "6950b44613b7a98e860d800fdbbe1693c6444729", "title": "Bottom-up Pose Estimation of Multiple Person with Bounding Box Constraint", "addresses": [{"name": "Zhejiang University", "source_name": "Zhejiang University", "street_adddress": "\u6d59\u6c5f\u5927\u5b66\u4e4b\u6c5f\u6821\u533a, \u4e4b\u6c5f\u8def, \u8f6c\u5858\u8857\u9053, \u897f\u6e56\u533a (Xihu), \u676d\u5dde\u5e02 Hangzhou, \u6d59\u6c5f\u7701, 310008, \u4e2d\u56fd", "lat": "30.19331415", "lng": "120.11930822", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.09972.pdf"], "doi": []}, {"id": "08ff22f76a567fcbc1afec6bfbf957a560cfadc7", "title": "Exploring Person Context and Local Scene Context for Object Detection.", "addresses": [{"name": "UC Berkeley", "source_name": "UC Berkeley", "street_adddress": "Berkeley, CA, USA", "lat": "37.87189920", "lng": "-122.25853990", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1511.08177.pdf"], "doi": []}, {"id": "828ac57f755db989e2886042a85278ae4823297c", "title": "Uncovering the Temporal Context for Video Question Answering", "addresses": [{"name": "University of Technology Sydney", "source_name": "University of Technology Sydney", "street_adddress": "University of Technology Sydney, Omnibus Lane, Ultimo, Sydney, NSW, 2007, Australia", "lat": "-33.88096510", "lng": "151.20107299", "type": "edu", "country": "Australia"}, {"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "2017", "pdf": [], "doi": ["http://doi.org/10.1007/s11263-017-1033-7"]}, {"id": "45e7ddd5248977ba8ec61be111db912a4387d62f", "title": "Adversarial Learning of Structure-Aware Fully Convolutional Networks for Landmark Localization", "addresses": [{"name": "Adelaide University", "source_name": "Adelaide University, Australia", "street_adddress": "Adelaide SA 5005, Australia", "lat": "-34.92060300", "lng": "138.60622770", "type": "edu", "country": "Australia"}, {"name": "Nanjing University", "source_name": "Nanjing University", "street_adddress": "NJU, \u4e09\u6c5f\u8def, \u9f13\u697c\u533a, \u5357\u4eac\u5e02, \u6c5f\u82cf\u7701, 210093, \u4e2d\u56fd", "lat": "32.05659570", "lng": "118.77408833", "type": "edu", "country": "China"}, {"name": "Nanjing University of Science & Technology", "source_name": "Nanjing University of Science & Technology, Nanjing, People\u2019s Republic of China", "street_adddress": "China, Jiangsu, Nanjing, Xuanwu, \u4e2d\u5c71\u95e8\u5916\u5927\u8857", "lat": "32.03522500", "lng": "118.85531700", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1711.00253.pdf"], "doi": []}, {"id": "69c22f1f72de76dfd4f5b90621dad4969674da1e", "title": "Convolution Neural Networks With Two Pathways for Image Style Recognition", "addresses": [{"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}, {"name": "Nanjing University", "source_name": "Nanjing University", "street_adddress": "NJU, \u4e09\u6c5f\u8def, \u9f13\u697c\u533a, \u5357\u4eac\u5e02, \u6c5f\u82cf\u7701, 210093, \u4e2d\u56fd", "lat": "32.05659570", "lng": "118.77408833", "type": "edu", "country": "China"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7945535", "http://doi.org/10.1109/TIP.2017.2710631", "https://www.ncbi.nlm.nih.gov/pubmed/28613168", "https://www.wikidata.org/entity/Q38726144"]}, {"id": "5820ba4c09695ce677a5aca6b0628c024303e60b", "title": "Semantic Correspondence: A Hierarchical Approach", "addresses": [{"name": "Queensland University of Technology", "source_name": "Queensland University of Technology", "street_adddress": "Queensland University of Technology, Macgregor Lane, Merthyr, South Brisbane, Brisbane, QLD, 4000, Australia", "lat": "-27.47715625", "lng": "153.02841004", "type": "edu", "country": "Australia"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.03560.pdf"], "doi": []}, {"id": "2d3d4883350a48708cdc0c260479110e5eed965a", "title": "Leveraging Visual Question Answering for Image-Caption Ranking", "addresses": [{"name": "Virginia Tech", "source_name": "Virginia Tech", "street_adddress": "Blacksburg, VA 24061, USA", "lat": "37.22838430", "lng": "-80.42341670", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1605.01379.pdf"], "doi": []}, {"id": "7a82d83f818cdc4ac714e468446bc2499ff9caa7", "title": "Object Referring in Videos with Language and Human Gaze", "addresses": [{"name": "ETH Zurich", "source_name": "ETH Zurich", "street_adddress": "R\u00e4mistrasse 101, 8092 Z\u00fcrich, Switzerland", "lat": "47.37631300", "lng": "8.54766990", "type": "edu", "country": "Switzerland"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1801.01582.pdf"], "doi": []}, {"id": "1cfbaa9af05f0eea03ac7c28cc0e588687cd8343", "title": "Self-view Grounding Given a Narrated 360{\\deg} Video", "addresses": [{"name": "National Tsing Hua University", "source_name": "National Tsing Hua University", "street_adddress": "\u570b\u7acb\u6e05\u83ef\u5927\u5b78, 101, \u514b\u606d\u6a4b, \u5149\u660e\u91cc, \u8d64\u571f\u5d0e, \u6771\u5340, \u65b0\u7af9\u5e02, 30013, \u81fa\u7063", "lat": "24.79254840", "lng": "120.99511830", "type": "edu", "country": "Taiwan"}, {"name": "Microsoft Research Asia", "source_name": "Microsoft Research Asia", "street_adddress": "1 Memorial Dr, Cambridge, MA 02142, USA", "lat": "42.36142560", "lng": "-71.08120920", "type": "company", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1711.08664.pdf"], "doi": []}, {"id": "a678b68abd4047d5342f64725f57a04647a47711", "title": "From Known to the Unknown: Transferring Knowledge to Answer Questions about Novel Visual and Semantic Concepts", "addresses": [{"name": "Australian National University", "source_name": "Australian National University", "street_adddress": "Canberra ACT 0200, Australia", "lat": "-35.27769990", "lng": "149.11852700", "type": "edu", "country": "Australia"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.12772.pdf"], "doi": []}, {"id": "19d1855e021561d6da9d0200bb18e47f51cddda6", "title": "Visual Storytelling", "addresses": [{"name": "Microsoft", "source_name": "Microsoft Corporation, Redmond, WA, USA", "street_adddress": "One Microsoft Way, Redmond, WA 98052, USA", "lat": "47.64233180", "lng": "-122.13693020", "type": "company", "country": "United States"}, {"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}, {"name": "Virginia Tech", "source_name": "Virginia Tech", "street_adddress": "Blacksburg, VA 24061, USA", "lat": "37.22838430", "lng": "-80.42341670", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1604.03968.pdf"], "doi": []}, {"id": "eecd9a070ed333077a066bfdcf776c51c2c74406", "title": "Deep image representations using caption generators", "addresses": [{"name": "Indian Institute of Science Bangalore", "source_name": "Indian Institute of Science Bangalore", "street_adddress": "IISc, Gulmohar Marg, RMV Stage II - 1st Block, Aramane Nagara Ward, West Zone, Bengaluru, Bangalore Urban, Karnataka, 560012, India", "lat": "13.02223470", "lng": "77.56718325", "type": "edu", "country": "India"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.09142.pdf"], "doi": []}, {"id": "b9566216ec1e5dcd02e3a222987f1934e44c773e", "title": "Neuron-level Selective Context Aggregation for Scene Segmentation", "addresses": [{"name": "Hebrew University of Jerusalem", "source_name": "The Hebrew University of Jerusalem", "street_adddress": "\u05d4\u05d0\u05d5\u05e0\u05d9\u05d1\u05e8\u05e1\u05d9\u05d8\u05d4 \u05d4\u05e2\u05d1\u05e8\u05d9\u05ea \u05d1\u05d9\u05e8\u05d5\u05e9\u05dc\u05d9\u05dd, Reagan Plaza, \u05e7\u05e8\u05d9\u05ea \u05de\u05e0\u05d7\u05dd \u05d1\u05d2\u05d9\u05df, \u05d4\u05e8 \u05d4\u05e6\u05d5\u05e4\u05d9\u05dd, \u05d9\u05e8\u05d5\u05e9\u05dc\u05d9\u05dd, \u05de\u05d7\u05d5\u05d6 \u05d9\u05e8\u05d5\u05e9\u05dc\u05d9\u05dd, NO, \u05d9\u05e9\u05e8\u05d0\u05dc", "lat": "31.79185550", "lng": "35.24472300", "type": "edu", "country": "Israel"}, {"name": "Shandong University", "source_name": "Shandong University", "street_adddress": "\u5c71\u4e1c\u5927\u5b66, \u6cf0\u5b89\u8857, \u9ccc\u5c71\u536b\u8857\u9053, \u5373\u58a8\u533a, \u9752\u5c9b\u5e02, \u5c71\u4e1c\u7701, 266200, \u4e2d\u56fd", "lat": "36.36934730", "lng": "120.67381800", "type": "edu", "country": "China"}, {"name": "Tel Aviv University", "source_name": "Tel Aviv University", "street_adddress": "\u05d0\u05d5\u05e0\u05d9\u05d1\u05e8\u05e1\u05d9\u05d8\u05ea \u05ea\u05dc \u05d0\u05d1\u05d9\u05d1, \u05db\u05d9\u05db\u05e8 \u05de\u05e0\u05d3\u05dc, \u05ea\u05dc \u05d0\u05d1\u05d9\u05d1 - \u05d9\u05e4\u05d5, \u05d0\u05e4\u05e7\u05d4, \u05ea\u05dc \u05d0\u05d1\u05d9\u05d1-\u05d9\u05e4\u05d5, \u05de\u05d7\u05d5\u05d6 \u05ea\u05dc \u05d0\u05d1\u05d9\u05d1, NO, \u05d9\u05e9\u05e8\u05d0\u05dc", "lat": "32.11198890", "lng": "34.80459702", "type": "edu", "country": "Israel"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1711.08278.pdf"], "doi": []}, {"id": "8c3cf0c579a28890e21428fcad7f09175e65e43d", "title": "Adding object detection skills to visual dialogue agents", "addresses": [{"name": "University of Amsterdam", "source_name": "University of Amsterdam", "street_adddress": "Institute for Logic, Language and Computation (ILLC), 107, Science Park, Oost-Watergraafsmeer, Amsterdam, Oost, Amsterdam, Noord-Holland, Nederland, 1098XG, Nederland", "lat": "52.35536550", "lng": "4.95016440", "type": "edu", "country": "Netherlands"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/8c3c/f0c579a28890e21428fcad7f09175e65e43d.pdf"], "doi": []}, {"id": "e559630c5710afb0d5eb8f95141e451393bbcbd9", "title": "Factors Influencing The Performance of Image Captioning Model: An Evaluation", "addresses": [{"name": "National University of Singapore", "source_name": "National University of Singapore", "street_adddress": "NUS, Former 1936 British Outpost, Nepal Hill, Clementi, Southwest, 117542, Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu", "country": "Singapore"}, {"name": "Hanoi University of Science and Technology", "source_name": "Hanoi University of Science and Technology", "street_adddress": "HUST, Tr\u1ea7n \u0110\u1ea1i Ngh\u0129a, Hai B\u00e0 Tr\u01b0ng, H\u00e0 N\u1ed9i, 10999, Vietnam", "lat": "21.00395200", "lng": "105.84360183", "type": "edu", "country": "Vietnam"}], "year": "2016", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3007136"]}, {"id": "e6d8ebfd88ee333deccce32b09ee41d271af6dc4", "title": "Grasp2Vec: Learning Object Representations from Self-Supervised Grasping", "addresses": [{"name": "UC Berkeley", "source_name": "UC Berkeley", "street_adddress": "Berkeley, CA, USA", "lat": "37.87189920", "lng": "-122.25853990", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.06964.pdf"], "doi": []}, {"id": "aea6dfb43df75b176ff209f5510a0f17256a4d0a", "title": "Learning 3 D Scene Synthesis from Annotated RGB-D Images", "addresses": [{"name": "Simon Fraser University", "source_name": "Simon Fraser University", "street_adddress": "SFU Burnaby, South Campus Road, Barnet, Burnaby, Metro Vancouver, British Columbia, V5A 4X6, Canada", "lat": "49.27674540", "lng": "-122.91777375", "type": "edu", "country": "Canada"}, {"name": "Zhejiang University", "source_name": "Zhejiang University", "street_adddress": "\u6d59\u6c5f\u5927\u5b66\u4e4b\u6c5f\u6821\u533a, \u4e4b\u6c5f\u8def, \u8f6c\u5858\u8857\u9053, \u897f\u6e56\u533a (Xihu), \u676d\u5dde\u5e02 Hangzhou, \u6d59\u6c5f\u7701, 310008, \u4e2d\u56fd", "lat": "30.19331415", "lng": "120.11930822", "type": "edu", "country": "China"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/aea6/dfb43df75b176ff209f5510a0f17256a4d0a.pdf"], "doi": []}, {"id": "b7407b2ea67b8c82246f013f4966c4cac1507e60", "title": "Object Detection via End-to-End Integration of Aspect Ratio and Context Aware Part-based Models and Fully Convolutional Networks", "addresses": [{"name": "Jilin University", "source_name": "Jilin University", "street_adddress": "\u5409\u6797\u5927\u5b66\u73e0\u6d77\u6821\u533a, \u4e39\u6842\u8def, \u5723\u5802\u6751, \u91d1\u6e7e\u533a, \u73e0\u6d77\u5e02, \u5e7f\u4e1c\u7701, \u4e2d\u56fd", "lat": "22.05356500", "lng": "113.39913285", "type": "edu", "country": "China"}, {"name": "North Carolina State University", "source_name": "North Carolina State University", "street_adddress": "North Carolina State University, Oval Drive, West Raleigh, Raleigh, Wake County, North Carolina, 27695, USA", "lat": "35.77184965", "lng": "-78.67408695", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/b740/7b2ea67b8c82246f013f4966c4cac1507e60.pdf"], "doi": []}, {"id": "079495c84b68623d9b1d4d48809cc24c1eee0a7e", "title": "Natural Language Object Retrieval", "addresses": [{"name": "University of California, Berkeley", "source_name": "University of California, Berkeley", "street_adddress": "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "lat": "37.86871260", "lng": "-122.25586815", "type": "edu", "country": "United States"}, {"name": "National University of Singapore", "source_name": "National University of Singapore", "street_adddress": "NUS, Former 1936 British Outpost, Nepal Hill, Clementi, Southwest, 117542, Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu", "country": "Singapore"}, {"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}, {"name": "University of Massachusetts", "source_name": "University of Massachusetts", "street_adddress": "University of Massachusetts, Hicks Way, Amherst, Hampshire, Massachusetts, 01003, USA", "lat": "42.38897850", "lng": "-72.52869870", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1511.04164.pdf"], "doi": []}, {"id": "e4b9c14951cea6259dd9d522586ba2c5bb1fbcce", "title": "Social Image Captioning: Exploring Visual Attention and User Attention", "addresses": [{"name": "China University of Petroleum (East China)", "source_name": "College of Information and Control Engineering, China University of Petroleum (East China), #66 Changjiang West Road, Qingdao Economic & Technological Development Zone, 266580 China", "street_adddress": "Jinan Rd, Dongying Qu, Dongying Shi, Shandong Sheng, China, 257000", "lat": "37.46230770", "lng": "118.50053220", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/e4b9/c14951cea6259dd9d522586ba2c5bb1fbcce.pdf"], "doi": []}, {"id": "cf98c333c8d7d5870c1ce5538bb0c3de3de16657", "title": "Panoptic Segmentation", "addresses": [{"name": "Heidelberg University", "source_name": "Institute of Psychology, Heidelberg University, Heidelberg, Germany", "street_adddress": "Hauptstra\u00dfe 47-51, 69117 Heidelberg, Germany", "lat": "49.41092660", "lng": "8.69795290", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1801.00868.pdf"], "doi": []}, {"id": "75cea964884a6f5c35e2954e56fc787ed8f9662c", "title": "Beyond Domain Adaptation: Unseen Domain Encapsulation via Universal Non-volume Preserving Models", "addresses": [{"name": "University of Science, Vietnam", "source_name": "University of Science, Vietnam", "street_adddress": "227 \u0110\u01b0\u1eddng Nguy\u1ec5n V\u0103n C\u1eeb, Ph\u01b0\u1eddng 4, Qu\u1eadn 5, H\u1ed3 Ch\u00ed Minh, Vietnam", "lat": "10.76291300", "lng": "106.68217170", "type": "edu", "country": "Vietnam"}, {"name": "Concordia University", "source_name": "Concordia University", "street_adddress": "Concordia University, 2811, Northeast Holman Street, Concordia, Portland, Multnomah County, Oregon, 97211, USA", "lat": "45.57022705", "lng": "-122.63709346", "type": "edu", "country": "United States"}, {"name": "University of Arkansas", "source_name": "University of Arkansas", "street_adddress": "Fayetteville, AR 72701, USA", "lat": "36.06783240", "lng": "-94.17365510", "type": "edu", "country": "United States"}, {"name": "University of Illinois", "source_name": "Advanced Digital Sciences Center (ADSC) of the University of Illinois, Singapore, Singapore", "street_adddress": "1 Create Way, 14-02 Create Tower, Singapore 138602", "lat": "1.30372570", "lng": "103.77377630", "type": "edu", "country": "Singapore"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.03407.pdf"], "doi": []}, {"id": "ad8fc03b492590a4282df52fe998d713995d0a0c", "title": "Exploring confusing scene classes for the places dataset: Insights and solutions", "addresses": [{"name": "University of Southern California", "source_name": "University of Southern California", "street_adddress": "University of Southern California, Watt Way, Saint James Park, LA, Los Angeles County, California, 90089, USA", "lat": "34.02241490", "lng": "-118.28634407", "type": "edu", "country": "United States"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8282094", "http://doi.org/10.1109/APSIPA.2017.8282094"]}, {"id": "943c372336ced4b28e15e02fe8db1f4b23bf6835", "title": "Advanced Deep-Learning Techniques for Salient and Category-Specific Object Detection: A Survey", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}, {"name": "University of Sydney", "source_name": "University of Sydney", "street_adddress": "USyd, Fisher Road, Camperdown, Sydney, NSW, 2006, Australia", "lat": "-33.88890695", "lng": "151.18943366", "type": "edu", "country": "Australia"}, {"name": "Northwestern Polytechnical University", "source_name": "Northwestern Polytechnical University", "street_adddress": "\u897f\u5317\u5de5\u4e1a\u5927\u5b66 \u53cb\u8c0a\u6821\u533a, 127\u53f7, \u53cb\u8c0a\u897f\u8def, \u957f\u5b89\u8def, \u7891\u6797\u533a (Beilin), \u897f\u5b89\u5e02, \u9655\u897f\u7701, 710072, \u4e2d\u56fd", "lat": "34.24691520", "lng": "108.91061982", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8253582", "http://doi.org/10.1109/MSP.2017.2749125"]}, {"id": "4923c6bc3ab501651763f6814a8384745f3d9a4d", "title": "Visual attribute transfer through deep image analogy", "addresses": [{"name": "Microsoft", "source_name": "Microsoft Corporation, Redmond, WA, USA", "street_adddress": "One Microsoft Way, Redmond, WA 98052, USA", "lat": "47.64233180", "lng": "-122.13693020", "type": "company", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.01088.pdf"], "doi": []}, {"id": "0013fae7390cbd34aade7959b4476512d8ab9aa3", "title": "Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions", "addresses": [{"name": "University of Modena and Reggio Emilia", "source_name": "University of Modena and Reggio Emilia 41125, Modena, Italy", "street_adddress": "Via Universit\u00e0, 4, 41121 Modena MO, Italy", "lat": "44.64510460", "lng": "10.92792680", "type": "edu", "country": "Italy"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.10652.pdf"], "doi": []}, {"id": "00ca28c1c8005ae8d06c7afd0284f67c67710c43", "title": "Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments", "addresses": [{"name": "Cornell University", "source_name": "Cornell University", "street_adddress": "Cornell University, Forest Home Drive, Forest Home, Tompkins County, New York, 14853, USA", "lat": "42.45055070", "lng": "-76.47835130", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.12354.pdf"], "doi": []}, {"id": "a88f86093e6f2d14761d4b8cbdcadfeff496c948", "title": "Adversarial Ranking for Language Generation", "addresses": [{"name": "University of Washington", "source_name": "University of Washington", "street_adddress": "University of Washington, Rainier Vista, Montlake, University District, Seattle, King County, Washington, 98195, USA", "lat": "47.65432380", "lng": "-122.30800894", "type": "edu", "country": "United States"}, {"name": "Microsoft", "source_name": "Microsoft Corporation, Redmond, WA, USA", "street_adddress": "One Microsoft Way, Redmond, WA 98052, USA", "lat": "47.64233180", "lng": "-122.13693020", "type": "company", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.11001.pdf"], "doi": []}, {"id": "30f33cffe390dfcc03d8df28593aebba6afafd59", "title": "Video Predictive Object Detector", "addresses": [{"name": "Queen's University", "source_name": "Queen's University, Belfast, UK", "street_adddress": "University Rd, Belfast BT7 1NN, UK", "lat": "54.58440870", "lng": "-5.93404930", "type": "edu", "country": "United Kingdom"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8615054"]}, {"id": "e69b1314cd65a115c98082a5863b92daa4dcf9f0", "title": "Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks", "addresses": [{"name": "Hong Kong Polytechnic University", "source_name": "Hong Kong Polytechnic University", "street_adddress": "hong kong, 11, \u80b2\u624d\u9053 Yuk Choi Road, \u5c16\u6c99\u5480 Tsim Sha Tsui, \u6cb9\u5c16\u65fa\u5340 Yau Tsim Mong District, \u4e5d\u9f8d Kowloon, HK, 00000, \u4e2d\u56fd", "lat": "22.30457200", "lng": "114.17976285", "type": "edu", "country": "China"}, {"name": "Chinese University of Hong Kong", "source_name": "Chinese University of Hong Kong", "street_adddress": "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "lat": "22.41626320", "lng": "114.21093180", "type": "edu", "country": "China"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7792699", "http://doi.org/10.1109/TMI.2016.2642839", "https://www.ncbi.nlm.nih.gov/pubmed/28026754", "https://www.wikidata.org/entity/Q39062626"]}, {"id": "fe8431a3b4313737183510d8f01003d48870d277", "title": "Superpixel Filtering for Mean Field Inference in CRFs Integrated with Convolutional Neural Networks", "addresses": [{"name": "University of Oxford", "source_name": "University of Oxford", "street_adddress": "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "lat": "51.75345380", "lng": "-1.25400997", "type": "edu", "country": "United Kingdom"}], "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/fe84/31a3b4313737183510d8f01003d48870d277.pdf"], "doi": []}, {"id": "99ef290d0eca8cfe8dc086bb1c4571e88eb876e4", "title": "Multi-label image classification with recurrently learning semantic dependencies", "addresses": [{"name": "Hefei University of Technology", "source_name": "Hefei University of Technology", "street_adddress": "\u5408\u80a5\u5de5\u4e1a\u5927\u5b66\uff08\u5c6f\u6eaa\u8def\u6821\u533a\uff09, 193\u53f7, \u5357\u4e00\u73af\u8def, \u822a\u8fd0\u5357\u6751, \u5305\u516c\u8857\u9053, \u5408\u80a5\u5e02\u533a, \u5408\u80a5\u5e02, \u5b89\u5fbd\u7701, 230009, \u4e2d\u56fd", "lat": "31.84691800", "lng": "117.29053367", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://doi.org/10.1007/s00371-018-01615-0"]}, {"id": "2e0f1c89c4e099b14c4d77bd406be9f7b78d6f6d", "title": "GLA: Global\u2013Local Attention for Image Description", "addresses": [{"name": "University of Texas at San Antonio", "source_name": "University of Texas at San Antonio", "street_adddress": "UTSA, Paseo Principal, San Antonio, Bexar County, Texas, 78249-1620, USA", "lat": "29.58333105", "lng": "-98.61944505", "type": "edu", "country": "United States"}, {"name": "Chinese Academy of Sciences", "source_name": "Chinese Academy of Sciences", "street_adddress": "\u4e2d\u56fd\u79d1\u5b66\u9662\u5fc3\u7406\u7814\u7a76\u6240, 16, \u6797\u8403\u8def, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100101, \u4e2d\u56fd", "lat": "40.00447950", "lng": "116.37023800", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8031355", "http://doi.org/10.1109/TMM.2017.2751140"]}, {"id": "5983b0c92f2a619157e2bedf15abb97ed1b0b98f", "title": "Computer Vision and Deep Learning for Automated Surveillance Technology", "addresses": [{"name": "Stanford University", "source_name": "Stanford University", "street_adddress": "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/5983/b0c92f2a619157e2bedf15abb97ed1b0b98f.pdf"], "doi": []}, {"id": "8d0fb60adc54c168587bce2cf5b1c46ba2ac36e3", "title": "Exploiting Saliency for Object Segmentation from Image Level Labels", "addresses": [{"name": "Max Planck Institute for Informatics", "source_name": "Max Planck Institute for Informatics", "street_adddress": "MPII, E1 4, Campus, Universit\u00e4t, Sankt Johann, Bezirk Mitte, Saarbr\u00fccken, Regionalverband Saarbr\u00fccken, Saarland, 66123, Deutschland", "lat": "49.25795660", "lng": "7.04577417", "type": "edu", "country": "Germany"}, {"name": "University of Amsterdam", "source_name": "University of Amsterdam", "street_adddress": "Institute for Logic, Language and Computation (ILLC), 107, Science Park, Oost-Watergraafsmeer, Amsterdam, Oost, Amsterdam, Noord-Holland, Nederland, 1098XG, Nederland", "lat": "52.35536550", "lng": "4.95016440", "type": "edu", "country": "Netherlands"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1701.08261.pdf"], "doi": []}, {"id": "55b9b1c1c5487f5f62b44340104a9c4cc2ed7c96", "title": "The Color of the Cat is Gray: 1 Million Full-Sentences Visual Question Answering (FSVQA).", "addresses": [{"name": "University of Tokyo", "source_name": "University of Tokyo", "street_adddress": "\u6771\u4eac\u5927\u5b66 \u67cf\u30ad\u30e3\u30f3\u30d1\u30b9, \u5b66\u878d\u5408\u306e\u9053, \u67cf\u5e02, \u5343\u8449\u770c, \u95a2\u6771\u5730\u65b9, 277-8583, \u65e5\u672c", "lat": "35.90204480", "lng": "139.93622009", "type": "edu", "country": "Japan"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1609.06657.pdf"], "doi": []}, {"id": "0d57ba12a6d958e178d83be4c84513f7e42b24e5", "title": "Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour.", "addresses": [{"name": "Facebook", "source_name": "Facebook", "street_adddress": "250 Bryant St, Mountain View, CA 94041, USA", "lat": "37.39367170", "lng": "-122.08072620", "type": "company", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1706.02677.pdf"], "doi": []}, {"id": "030646f4fc694ffea5d4f77203cbbc5d02aae797", "title": "Cognitive Deep Machine Can Train Itself", "addresses": [{"name": "E\u00f6tv\u00f6s Lor\u00e1nd University", "source_name": "Faculty of Informatics, E\u00f6tv\u00f6s Lor\u00e1nd University, P\u00e1zm\u00e1ny P\u00e9ter s\u00e9t\u00e1ny 1/C, Budapest H-1117, Hungary", "street_adddress": "Budapest, P\u00e1zm\u00e1ny P\u00e9ter stny. 1/C., 1117 Hungary", "lat": "47.47228960", "lng": "19.06235910", "type": "edu", "country": "Hungary"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1612.00745.pdf"], "doi": []}, {"id": "0744143542ffcb45b1ad83078c23efa9d3ec2be4", "title": "Multispectral Pedestrian Detection via Simultaneous Detection and Segmentation", "addresses": [{"name": "Zhejiang University", "source_name": "Zhejiang University", "street_adddress": "\u6d59\u6c5f\u5927\u5b66\u4e4b\u6c5f\u6821\u533a, \u4e4b\u6c5f\u8def, \u8f6c\u5858\u8857\u9053, \u897f\u6e56\u533a (Xihu), \u676d\u5dde\u5e02 Hangzhou, \u6d59\u6c5f\u7701, 310008, \u4e2d\u56fd", "lat": "30.19331415", "lng": "120.11930822", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.04818.pdf"], "doi": []}, {"id": "ee5b4fc5fafa7e883d751557b5c7863503cd92d2", "title": "Findings of the Second Shared Task on Multimodal Machine Translation and Multilingual Image Description", "addresses": [{"name": "University of Edinburgh", "source_name": "University of Edinburgh", "street_adddress": "New College, New College Courtyard, The Mound, Old Town, Edinburgh, City of Edinburgh, Scotland, EH1 2LX, UK", "lat": "55.94951105", "lng": "-3.19534913", "type": "edu", "country": "United Kingdom"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1710.07177.pdf"], "doi": []}, {"id": "3f15c35d4c5ed41de9f57e06849f750e43fe80b3", "title": "JointFlow : Temporal Flow Fields for Multi Person Pose Tracking", "addresses": [{"name": "University of Bonn", "source_name": "University of Bonn", "street_adddress": "Rheinische Friedrich-Wilhelms-Universit\u00e4t Bonn, Arkadenhof, Bonn-Zentrum, Stadtbezirk Bonn, Bonn, Regierungsbezirk K\u00f6ln, Nordrhein-Westfalen, 53113, Deutschland", "lat": "50.73381240", "lng": "7.10224650", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/3f15/c35d4c5ed41de9f57e06849f750e43fe80b3.pdf"], "doi": []}, {"id": "d0e20aa3d61b77d17f005a1d24d7cf47600836ef", "title": "Rethinking Atrous Convolution for Semantic Image Segmentation", "addresses": [{"name": "Google", "source_name": "Google, Inc.", "street_adddress": "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "lat": "37.42199990", "lng": "-122.08405750", "type": "company", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1706.05587.pdf"], "doi": []}, {"id": "4fa6a688f350831503d158f8f618c58d1e06bc5d", "title": "A Semi-supervised Framework for Image Captioning", "addresses": [{"name": "ETH Zurich", "source_name": "ETH Zurich", "street_adddress": "R\u00e4mistrasse 101, 8092 Z\u00fcrich, Switzerland", "lat": "47.37631300", "lng": "8.54766990", "type": "edu", "country": "Switzerland"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1611.05321.pdf"], "doi": []}, {"id": "7d8c2d29deb80ceed3c8568100376195ce0914cb", "title": "Identity-Aware Textual-Visual Matching with Latent Co-attention", "addresses": [{"name": "Chinese University of Hong Kong", "source_name": "Chinese University of Hong Kong", "street_adddress": "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "lat": "22.41626320", "lng": "114.21093180", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.01988.pdf"], "doi": []}, {"id": "3f607dd67b456e3dfb136c70a3dae369945a6076", "title": "Improved Selective Refinement Network for Face Detection", "addresses": [{"name": "Chinese Academy of Sciences", "source_name": "Chinese Academy of Sciences", "street_adddress": "\u4e2d\u56fd\u79d1\u5b66\u9662\u5fc3\u7406\u7814\u7a76\u6240, 16, \u6797\u8403\u8def, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100101, \u4e2d\u56fd", "lat": "40.00447950", "lng": "116.37023800", "type": "edu", "country": "China"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.06651.pdf"], "doi": []}, {"id": "357df3ee0f0c30d5c8abc5a1bdf70122322d6fbd", "title": "O BJECT DETECTORS EMERGE IN D EEP S CENE CNN S", "addresses": [{"name": "MIT", "source_name": "Massachusetts Institute", "street_adddress": "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/08c7/a85c443935468450a162ddeccd2b945660e3.pdf"], "doi": []}, {"id": "ef12de45bd47e03451cde586697601cd7e36c3b9", "title": "Aligning Text and Document Illustrations: Towards Visually Explainable Digital Humanities", "addresses": [{"name": "University of of Modena and Reggio Emilia", "source_name": "University of of Modena and Reggio Emilia", "street_adddress": "Via Universit\u00e0, 4, 41121 Modena MO, Italy", "lat": "44.64510460", "lng": "10.92792680", "type": "edu", "country": "Italy"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8545064", "http://doi.ieeecomputersociety.org/10.1109/ICPR.2018.8545064", "http://doi.org/10.1109/ICPR.2018.8545064"]}, {"id": "6cc46899b415ebef4a70068b2cbd8a50e955aeb6", "title": "Where to put the Image in an Image Caption Generator", "addresses": [{"name": "University of Malta", "source_name": "University of Malta", "street_adddress": "University of Malta, Ring Road, Japanese Garden, L-Imsida, Malta, MSD 9027, Malta", "lat": "35.90232260", "lng": "14.48341890", "type": "edu", "country": "Malta"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1703.09137.pdf"], "doi": []}, {"id": "3d732ba534081326eb9de70f2e370a31940c2990", "title": "Semantic image segmentation using fully convolutional neural networks with multi-scale images and multi-scale dilated convolutions", "addresses": [{"name": "Gachon University", "source_name": "Gachon University, Gyeonggi-do, South Korea", "street_adddress": "1342 Seongnam-daero, Bokjeong-dong, Sujeong-gu, Seongnam-si, Gyeonggi-do, South Korea", "lat": "37.45074520", "lng": "127.12884740", "type": "edu", "country": "South Korea"}], "year": "2018", "pdf": [], "doi": ["http://doi.org/10.1007/s11042-018-5653-x"]}, {"id": "5ffa8cfea2f5bea0ec7cecfdf76f9478ca87df89", "title": "Context-Aware Captions from Context-Agnostic Supervision", "addresses": [{"name": "Virginia Tech", "source_name": "Virginia Tech", "street_adddress": "Blacksburg, VA 24061, USA", "lat": "37.22838430", "lng": "-80.42341670", "type": "edu", "country": "United States"}, {"name": "Georgia Institute of Technology", "source_name": "Georgia Institute of Technology", "street_adddress": "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu", "country": "United States"}, {"name": "Google", "source_name": "Google, Inc.", "street_adddress": "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "lat": "37.42199990", "lng": "-122.08405750", "type": "company", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1701.02870.pdf"], "doi": []}, {"id": "b9146b314812231d09587e3a9f622dda65d3cc40", "title": "A survey on social image understanding", "addresses": [{"name": "Nanjing Normal University Nanjing", "source_name": "Honors College, Nanjing Normal University Nanjing, Jiangsu, 210023, China", "street_adddress": "122 Ninghai Rd, Gulou Qu, Nanjing Shi, Jiangsu Sheng, China, 210097", "lat": "32.05494300", "lng": "118.76494700", "type": "edu", "country": "China"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8256394", "http://doi.org/10.1109/BESC.2017.8256394"]}, {"id": "9d0c3adbee8098d47c7c0704e0841fa7daf8d161", "title": "The price of debiasing automatic metrics in natural language evalaution", "addresses": [{"name": "Stanford University", "source_name": "Stanford University", "street_adddress": "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.02202.pdf"], "doi": []}, {"id": "6e97a99b2879634ecae962ddb8af7c1a0a653a82", "title": "Towards Context-aware Interaction Recognition", "addresses": [{"name": "University of Adelaide", "source_name": "University of Adelaide", "street_adddress": "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu", "country": "Australia"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.06246.pdf"], "doi": []}, {"id": "4cc2dc6e6b1f4575e86217a13b591f605a12b825", "title": "Consistent Optimization for Single-Shot Object Detection", "addresses": [{"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.06563.pdf"], "doi": []}, {"id": "9ac253caa50f7d94eead17ac12499226c0f05e87", "title": "Analysing object detectors from the perspective of co-occurring object categories", "addresses": [{"name": "Nokia Bell Labs, Budapest, Hungary", "source_name": "Nokia Bell Labs, Budapest, Hungary", "street_adddress": "Budapest, Hungary", "lat": "47.49791200", "lng": "19.04023500", "type": "company", "country": "Hungary"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8639888"]}, {"id": "102e7bd7660357e1814c821c7f697f2eccececa4", "title": "Predicting Motivations of Actions by Leveraging Text", "addresses": [{"name": "MIT", "source_name": "Massachusetts Institute", "street_adddress": "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu", "country": "United States"}, {"name": "University of Maryland", "source_name": "University of Maryland", "street_adddress": "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1406.5472.pdf"], "doi": []}, {"id": "c2f1aa6395941438501653ea262df63c812e8f71", "title": "Non-parametric human segmentation using support vector machine", "addresses": [{"name": "Yonsei University", "source_name": "Yonsei University", "street_adddress": "\uc5f0\uc138\ub300, \uc5f0\uc138\ub85c, \uc2e0\ucd0c\ub3d9, \ucc3d\ucc9c\ub3d9, \uc11c\ub300\ubb38\uad6c, \uc11c\uc6b8\ud2b9\ubcc4\uc2dc, 03789, \ub300\ud55c\ubbfc\uad6d", "lat": "37.56004060", "lng": "126.93692480", "type": "edu", "country": "South Korea"}], "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7514714", "http://doi.org/10.1109/ICCE.2016.7430551"]}, {"id": "819d1dcea397e6e671acf74adccdef5750550873", "title": "Representations for Visually Guided Actions", "addresses": [{"name": "University of California at Berkeley", "source_name": "International Computer Science Institute, University of California at Berkeley, Berkeley, USA", "street_adddress": "1947 Center St, Berkeley, CA 94704, USA", "lat": "37.87015430", "lng": "-122.27123120", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/819d/1dcea397e6e671acf74adccdef5750550873.pdf"], "doi": []}, {"id": "c1de9803bd0072f017a97c0503308a7b9b4f211b", "title": "Analysis of Spatial, Temporal, and Content Characteristics of Videos in the YFCC100M Dataset", "addresses": [{"name": "Yonsei University", "source_name": "Yonsei University", "street_adddress": "\uc5f0\uc138\ub300, \uc5f0\uc138\ub85c, \uc2e0\ucd0c\ub3d9, \ucc3d\ucc9c\ub3d9, \uc11c\ub300\ubb38\uad6c, \uc11c\uc6b8\ud2b9\ubcc4\uc2dc, 03789, \ub300\ud55c\ubbfc\uad6d", "lat": "37.56004060", "lng": "126.93692480", "type": "edu", "country": "South Korea"}], "year": "2016", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=2983559"]}, {"id": "2298a1e437b4f8f2f2f016f1a98c027bf2f7f5bb", "title": "Top-Down Neural Attention by Excitation Backprop", "addresses": [{"name": "Boston University", "source_name": "Boston University", "street_adddress": "BU, Bay State Road, Fenway, Boston, Suffolk County, Massachusetts, 02215, USA", "lat": "42.35042530", "lng": "-71.10056114", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1608.00507.pdf"], "doi": []}, {"id": "afa073e5ec712423e300f21bcb2c3f17a69fa9d1", "title": "Style Transfer at 100+ FPS Via Sub-Pixel Super-Resolution", "addresses": [{"name": "South China University of Technology", "source_name": "South China University of Technology", "street_adddress": "\u534e\u5357\u7406\u5de5\u5927\u5b66, \u5927\u5b66\u57ce\u4e2d\u73af\u4e1c\u8def, \u5e7f\u5dde\u5927\u5b66\u57ce, \u65b0\u9020, \u756a\u79ba\u533a (Panyu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510006, \u4e2d\u56fd", "lat": "23.05020420", "lng": "113.39880323", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8551538", "http://doi.ieeecomputersociety.org/10.1109/ICMEW.2018.8551538", "http://doi.org/10.1109/ICMEW.2018.8551538"]}, {"id": "19317c6aa7f88c79abe03b146aa5d340a11fde3f", "title": "Object Proposal Generation With Fully Convolutional Networks", "addresses": [{"name": "National University of Singapore", "source_name": "National University of Singapore", "street_adddress": "NUS, Former 1936 British Outpost, Nepal Hill, Clementi, Southwest, 117542, Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu", "country": "Singapore"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7484700", "http://doi.org/10.1109/TCSVT.2016.2576759"]}, {"id": "6a75ef6b36489cb59c61f21f3cd09c50ad5b2995", "title": "MVTec D2S: Densely Segmented Supermarket Dataset", "addresses": [{"name": "Technical University of Munich", "source_name": "Computer Aided Medical Procedures, Technical University of Munich, Garching, Germany", "street_adddress": "Boltzmannstra\u00dfe 3, 85748 Garching bei M\u00fcnchen, Germany", "lat": "48.26301100", "lng": "11.66685700", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.08292.pdf"], "doi": []}, {"id": "02d6fb270c82c390476faffc6015b3116ddbb60c", "title": "Image Captioning with Sentiment Terms via Weakly-Supervised Sentiment Dataset", "addresses": [{"name": "University of Tokyo", "source_name": "University of Tokyo", "street_adddress": "\u6771\u4eac\u5927\u5b66 \u67cf\u30ad\u30e3\u30f3\u30d1\u30b9, \u5b66\u878d\u5408\u306e\u9053, \u67cf\u5e02, \u5343\u8449\u770c, \u95a2\u6771\u5730\u65b9, 277-8583, \u65e5\u672c", "lat": "35.90204480", "lng": "139.93622009", "type": "edu", "country": "Japan"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/bd4a/bb49151220b389d9df1f19fecc3d92e0bff4.pdf"], "doi": []}, {"id": "11d256be1eb3da7789c0c9672f467079917baada", "title": "Action Classification via Concepts and Attributes", "addresses": [{"name": "York University", "source_name": "York University", "street_adddress": "York University, Keele Campus, Campus Walk, North York, Toronto, Ontario, M3J 2S5, Canada", "lat": "43.77439110", "lng": "-79.50481085", "type": "edu", "country": "Canada"}, {"name": "Weizmann Institute of Science", "source_name": "Weizmann Institute of Science", "street_adddress": "\u05de\u05db\u05d5\u05df \u05d5\u05d9\u05e6\u05de\u05df \u05dc\u05de\u05d3\u05e2, \u05e9\u05d3\u05e8\u05ea \u05de\u05e8\u05db\u05d5\u05e1 \u05d6\u05d9\u05d5, \u05de\u05e2\u05d5\u05e0\u05d5\u05ea \u05e9\u05d9\u05d9\u05df, \u05d0\u05d7\u05d5\u05d6\u05d5\u05ea \u05d4\u05e0\u05e9\u05d9\u05d0, \u05e8\u05d7\u05d5\u05d1\u05d5\u05ea, \u05de\u05d7\u05d5\u05d6 \u05d4\u05de\u05e8\u05db\u05d6, NO, \u05d9\u05e9\u05e8\u05d0\u05dc", "lat": "31.90784990", "lng": "34.81334092", "type": "edu", "country": "Israel"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1605.07824.pdf"], "doi": []}, {"id": "549d55a06c5402696e063ce36b411f341a64f8a9", "title": "Learning Deep Structure-Preserving Image-Text Embeddings", "addresses": [{"name": "University of Illinois, Urbana-Champaign", "source_name": "University of Illinois, Urbana-Champaign", "street_adddress": "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu", "country": "United States"}, {"name": "Georgia Institute of Technology", "source_name": "Georgia Institute of Technology", "street_adddress": "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1511.06078.pdf"], "doi": []}, {"id": "3f5b20c35f55417823f0201862d85af1f31e9348", "title": "Salience Biased Loss for Object Detection in Aerial Images", "addresses": [{"name": "University of Missouri-Columbia", "source_name": "University of Missouri-Columbia, USA", "street_adddress": "Columbia, MO 65211, USA", "lat": "38.94038080", "lng": "-92.32773750", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.08103.pdf"], "doi": []}, {"id": "cbe6739ecdb23d61f2ff74481c6b538ef953eb10", "title": "Learning to Learn: Model Regression Networks for Easy Small Sample Learning", "addresses": [{"name": "Robotics Institute", "source_name": "Robotics Institute", "street_adddress": "Institute for Field Robotics, \u0e1b\u0e23\u0e30\u0e0a\u0e32\u0e2d\u0e38\u0e17\u0e34\u0e28, \u0e01\u0e23\u0e38\u0e07\u0e40\u0e17\u0e1e\u0e21\u0e2b\u0e32\u0e19\u0e04\u0e23, \u0e40\u0e02\u0e15\u0e23\u0e32\u0e29\u0e0e\u0e23\u0e4c\u0e1a\u0e39\u0e23\u0e13\u0e30, \u0e01\u0e23\u0e38\u0e07\u0e40\u0e17\u0e1e\u0e21\u0e2b\u0e32\u0e19\u0e04\u0e23, 10140, \u0e1b\u0e23\u0e30\u0e40\u0e17\u0e28\u0e44\u0e17\u0e22", "lat": "13.65450525", "lng": "100.49423171", "type": "edu", "country": "Thailand"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/cbe6/739ecdb23d61f2ff74481c6b538ef953eb10.pdf"], "doi": []}, {"id": "a4e1a95c32e9477aa1b09073a1fd3ca129aacadc", "title": "Driver Identification System Using Convolutional Neural Network with Background Removal-based Infrared Data Augmentation", "addresses": [{"name": "Sogang University", "source_name": "Sogang University, Seoul, Republic of Korea", "street_adddress": "35 Baekbeom-ro, Sinsu-dong, Mapo-gu, Seoul, South Korea", "lat": "37.55094420", "lng": "126.94100230", "type": "edu", "country": "South Korea"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8500364", "http://doi.org/10.1109/IVS.2018.8500364"]}, {"id": "3e4d8bd8cb917db9bad1ed4382ccb266ab5fa411", "title": "Toward Efficient Simultaneous Detection and Segmentation", "addresses": [{"name": "Beijing Information Science and Technology University", "source_name": "Beijing Information Science and Technology University, Beijing, China", "street_adddress": "China, Beijing, Haidian, \u6e05\u6cb3\u56db\u62d4\u5b50", "lat": "40.04332040", "lng": "116.34181090", "type": "edu", "country": "China"}, {"name": "Beijing Institute of Technology", "source_name": "Beijing Institute of Technology University", "street_adddress": "\u5317\u4eac\u7406\u5de5\u5927\u5b66, 5, \u4e2d\u5173\u6751\u5357\u5927\u8857, \u4e2d\u5173\u6751, \u7a3b\u9999\u56ed\u5357\u793e\u533a, \u6d77\u6dc0\u533a, \u5317\u4eac\u5e02, 100872, \u4e2d\u56fd", "lat": "39.95866520", "lng": "116.30971281", "type": "edu", "country": "China"}, {"name": "Peking University", "source_name": "Peking University", "street_adddress": "\u5317\u4eac\u5927\u5b66, 5\u53f7, \u9890\u548c\u56ed\u8def, \u7a3b\u9999\u56ed\u5357\u793e\u533a, \u6d77\u6dc0\u533a, \u5317\u4eac\u5e02, 100871, \u4e2d\u56fd", "lat": "39.99223790", "lng": "116.30393816", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8499154", "http://doi.ieeecomputersociety.org/10.1109/BigMM.2018.8499154", "http://doi.org/10.1109/BigMM.2018.8499154"]}, {"id": "4f0b8f730273e9f11b2bfad2415485414b96299f", "title": "BDD100K: A Diverse Driving Video Database with Scalable Annotation Tooling", "addresses": [{"name": "UC Berkeley", "source_name": "UC Berkeley", "street_adddress": "Berkeley, CA, USA", "lat": "37.87189920", "lng": "-122.25853990", "type": "edu", "country": "United States"}, {"name": "Georgia Institute of Technology", "source_name": "Georgia Institute of Technology", "street_adddress": "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu", "country": "United States"}, {"name": "Peking University", "source_name": "Peking University", "street_adddress": "\u5317\u4eac\u5927\u5b66, 5\u53f7, \u9890\u548c\u56ed\u8def, \u7a3b\u9999\u56ed\u5357\u793e\u533a, \u6d77\u6dc0\u533a, \u5317\u4eac\u5e02, 100871, \u4e2d\u56fd", "lat": "39.99223790", "lng": "116.30393816", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.04687.pdf"], "doi": []}, {"id": "4f9beb035a3d196f653e8528303fdf9ded998e22", "title": "Can You See the (Linguistic) Difference? Exploring Mass/Count Distinction in Vision", "addresses": [{"name": "University of Trento", "source_name": "University of Trento", "street_adddress": "University of Trento, Via Giuseppe Verdi, Piedicastello, Trento, Territorio Val d'Adige, TN, TAA, 38122, Italia", "lat": "46.06588360", "lng": "11.11598940", "type": "edu", "country": "Italy"}, {"name": "University of Padova", "source_name": "University of Padova", "street_adddress": "Via Giovanni Gradenigo, 6, 35131 Padova PD, Italy", "lat": "45.40811720", "lng": "11.89437860", "type": "edu", "country": "Italy"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/4f9b/eb035a3d196f653e8528303fdf9ded998e22.pdf"], "doi": []}, {"id": "87e1ae939f3632f26a9878fe32674e338cb18094", "title": "C4Synth: Cross-Caption Cycle-Consistent Text-to-Image Synthesis", "addresses": [{"name": "IIT Hyderabad, India", "source_name": "IIT Hyderabad, Kandi, Telangana, 502285, India", "street_adddress": "IITH Main Road, Near NH-65, Sangareddy, Kandi, Telangana 502285, India", "lat": "17.59470330", "lng": "78.12310540", "type": "edu", "country": "India"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.10238.pdf"], "doi": []}, {"id": "7277fdf51bb3fc38f254a5546c53caa4169653c9", "title": "Domain Adaptation for Neural Networks by Parameter Augmentation", "addresses": [{"name": "University of Tokyo", "source_name": "University of Tokyo", "street_adddress": "\u6771\u4eac\u5927\u5b66 \u67cf\u30ad\u30e3\u30f3\u30d1\u30b9, \u5b66\u878d\u5408\u306e\u9053, \u67cf\u5e02, \u5343\u8449\u770c, \u95a2\u6771\u5730\u65b9, 277-8583, \u65e5\u672c", "lat": "35.90204480", "lng": "139.93622009", "type": "edu", "country": "Japan"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1607.00410.pdf"], "doi": []}, {"id": "32812f35efab1fc5bdbcc17d67f27bba31c720c6", "title": "Dropout during inference as a model for neurological degeneration in an image captioning network", "addresses": [{"name": "University of Toronto", "source_name": "University of Toronto", "street_adddress": "University of Toronto, St. George Street, Bloor Street Culture Corridor, Old Toronto, Toronto, Ontario, M5S 1A5, Canada", "lat": "43.66333345", "lng": "-79.39769975", "type": "edu", "country": "Canada"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.03747.pdf"], "doi": []}, {"id": "9534a04de5e99a44df76ea30140f66a62e83fdaa", "title": "Iteratively Trained Interactive Segmentation", "addresses": [{"name": "RWTH Aachen University", "source_name": "RWTH Aachen University", "street_adddress": "RWTH Aachen, Mies-van-der-Rohe-Stra\u00dfe, K\u00f6nigsh\u00fcgel, Aachen-Mitte, Aachen, St\u00e4dteregion Aachen, Regierungsbezirk K\u00f6ln, Nordrhein-Westfalen, 52074, Deutschland", "lat": "50.77917030", "lng": "6.06728733", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.04398.pdf"], "doi": []}, {"id": "3349fab3a5e2b7c5194289bdc839f87f556ea3ef", "title": "Social Image Tags as a Source of Word Embeddings: A Task-oriented Evaluation", "addresses": [{"name": "Waseda University", "source_name": "Waseda University", "street_adddress": "\u65e9\u7a32\u7530\u5927\u5b66 \u5317\u4e5d\u5dde\u30ad\u30e3\u30f3\u30d1\u30b9, 2-2, \u6709\u6bdb\u5f15\u91ce\u7dda, \u516b\u5e61\u897f\u533a, \u5317\u4e5d\u5dde\u5e02, \u798f\u5ca1\u770c, \u4e5d\u5dde\u5730\u65b9, 808-0135, \u65e5\u672c", "lat": "33.88987280", "lng": "130.70856205", "type": "edu", "country": "Japan"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/3349/fab3a5e2b7c5194289bdc839f87f556ea3ef.pdf"], "doi": []}, {"id": "eb7e0dfc61f3f9993a39316ccaaa263059b3a108", "title": "Spatially Adaptive Computation Time for Residual Networks", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}, {"name": "Google", "source_name": "Google, Inc.", "street_adddress": "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "lat": "37.42199990", "lng": "-122.08405750", "type": "company", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1612.02297.pdf"], "doi": []}, {"id": "16beefb2f8d0d61e536bf20766e485499906c2e0", "title": "Image Surveillance Assistant", "addresses": [{"name": "Naval Research Laboratory", "source_name": "Naval Research Laboratory", "street_adddress": "Naval Research Laboratory Post Office, 4555, Overlook Avenue Southwest, Washington, D.C., 20375, USA", "lat": "38.82313810", "lng": "-77.01789020", "type": "mil", "country": "United States"}], "year": "2016", "pdf": ["http://cs.umd.edu/~maynord/Image_Surveillance_Assistant.pdf", "https://www.nrl.navy.mil/itd/aic/sites/www.nrl.navy.mil.itd.aic/files/pdfs/(Maynord+%20WACV-16%20WS)%20Intelligent%20Surveillance%20Assistant.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7470119", "http://doi.ieeecomputersociety.org/10.1109/WACVW.2016.7470119", "http://doi.org/10.1109/WACVW.2016.7470119"]}, {"id": "0bbb40e5b9e546a3f4e7340b2980059065c99203", "title": "Learning Object Detectors from Scratch with Gated Recurrent Feature Pyramids", "addresses": [{"name": "Beckman Institute", "source_name": "Beckman Institute", "street_adddress": "Beckman Institute, The Presidents' Walk, Urbana, Champaign County, Illinois, 61801-2341, USA", "lat": "40.11571585", "lng": "-88.22750772", "type": "edu", "country": "United States"}, {"name": "Fudan University", "source_name": "Fudan University", "street_adddress": "\u590d\u65e6\u5927\u5b66, 220, \u90af\u90f8\u8def, \u4e94\u89d2\u573a\u8857\u9053, \u6768\u6d66\u533a, \u4e0a\u6d77\u5e02, 200433, \u4e2d\u56fd", "lat": "31.30104395", "lng": "121.50045497", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1712.00886.pdf"], "doi": []}, {"id": "edafa697ba68874d608015b521c43d04e3584992", "title": "Gated Recurrent Capsules for Visual Word Embeddings", "addresses": [{"name": "EURECOM", "source_name": "EURECOM", "street_adddress": "Campus SophiaTech, 450 Route des Chappes, 06410 Biot, France", "lat": "43.61438600", "lng": "7.07112500", "type": "edu", "country": "France"}], "year": "2019", "pdf": ["https://pdfs.semanticscholar.org/edaf/a697ba68874d608015b521c43d04e3584992.pdf"], "doi": []}, {"id": "6e09a291d61f0e26ce3522a1b0fce952fb811090", "title": "Generative Attention Model with Adversarial Self-learning for Visual Question Answering", "addresses": [{"name": "National University of Singapore", "source_name": "National University of Singapore", "street_adddress": "NUS, Former 1936 British Outpost, Nepal Hill, Clementi, Southwest, 117542, Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu", "country": "Singapore"}], "year": "2017", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3126695"]}, {"id": "46253ab8721ced8c9b94234f3a2401efde1e3f2a", "title": "Language Models for Image Captioning: The Quirks and What Works", "addresses": [{"name": "Microsoft", "source_name": "Microsoft Corporation, Redmond, WA, USA", "street_adddress": "One Microsoft Way, Redmond, WA 98052, USA", "lat": "47.64233180", "lng": "-122.13693020", "type": "company", "country": "United States"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1505.01809.pdf"], "doi": []}, {"id": "402324c77b7b4040810480d6947c7db92d491308", "title": "Socratic Learning: Augmenting Generative Models to Incorporate Latent Subsets in Training Data", "addresses": [{"name": "Stanford University", "source_name": "Stanford University", "street_adddress": "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1610.08123.pdf"], "doi": []}, {"id": "64e2ea4ca45cbf1a6ef35f3448c5799354e2f603", "title": "Visual and Semantic Knowledge Transfer for Large Scale Semi-Supervised Object Detection", "addresses": [{"name": "University of Sheffield", "source_name": "The University of Sheffield", "street_adddress": "University of Sheffield, Portobello, Port Mahon, Saint George's, Sheffield, Yorkshire and the Humber, England, S1 4DP, UK", "lat": "53.38152480", "lng": "-1.48068143", "type": "edu", "country": "United Kingdom"}, {"name": "National Institutes of Health (NIH) Clinical Center, Bethesda, MD", "source_name": "National Institutes of Health (NIH) Clinical Center, Bethesda, MD", "street_adddress": "10 Center Dr, Bethesda, MD 20814, USA", "lat": "39.00252720", "lng": "-77.10437890", "type": "edu", "country": "United States"}, {"name": "\u00c9cole Centrale de Lyon", "source_name": "Laboratoire LIRIS", "street_adddress": "40 Avenue Guy de Collongue, 69130 \u00c9cully, France", "lat": "45.78359660", "lng": "4.76789480", "type": "edu", "country": "France"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8103045"]}, {"id": "14c2321851fb5ae580a19726dd2753a525d6ad76", "title": "Grounding of Textual Phrases in Images by Reconstruction", "addresses": [{"name": "Max Planck Institute for Informatics", "source_name": "Max Planck Institute for Informatics", "street_adddress": "MPII, E1 4, Campus, Universit\u00e4t, Sankt Johann, Bezirk Mitte, Saarbr\u00fccken, Regionalverband Saarbr\u00fccken, Saarland, 66123, Deutschland", "lat": "49.25795660", "lng": "7.04577417", "type": "edu", "country": "Germany"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1511.03745.pdf"], "doi": []}, {"id": "8176e3aea16595b3fe6afdb6c745c9eca98ece06", "title": "The Helping Hand: An Assistive Manipulation Framework Using Augmented Reality and Tongue-Drive Interfaces", "addresses": [{"name": "Georgia Institute of Technology", "source_name": "Georgia Institute of Technology", "street_adddress": "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu", "country": "United States"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8512668", "http://doi.org/10.1109/EMBC.2018.8512668", "https://www.ncbi.nlm.nih.gov/pubmed/30440831"]}, {"id": "2bc70a13426c79c192c5e57f8a0041d8ecf628a8", "title": "Image Labeling with Markov Random Fields and Conditional Random Fields", "addresses": [{"name": "Robotics Institute", "source_name": "Robotics Institute", "street_adddress": "Institute for Field Robotics, \u0e1b\u0e23\u0e30\u0e0a\u0e32\u0e2d\u0e38\u0e17\u0e34\u0e28, \u0e01\u0e23\u0e38\u0e07\u0e40\u0e17\u0e1e\u0e21\u0e2b\u0e32\u0e19\u0e04\u0e23, \u0e40\u0e02\u0e15\u0e23\u0e32\u0e29\u0e0e\u0e23\u0e4c\u0e1a\u0e39\u0e23\u0e13\u0e30, \u0e01\u0e23\u0e38\u0e07\u0e40\u0e17\u0e1e\u0e21\u0e2b\u0e32\u0e19\u0e04\u0e23, 10140, \u0e1b\u0e23\u0e30\u0e40\u0e17\u0e28\u0e44\u0e17\u0e22", "lat": "13.65450525", "lng": "100.49423171", "type": "edu", "country": "Thailand"}, {"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.11323.pdf"], "doi": []}, {"id": "af55a25cdd3a2c138e755d5206b35457c1f5760b", "title": "DistInit: Learning Video Representations without a Single Labeled Video", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.09244.pdf"], "doi": []}, {"id": "9a7784eea6bfa62bf2834ee0b87a3cdda46006f2", "title": "Digital Comics Image Indexing Based on Deep Learning", "addresses": [{"name": "University of La Rochelle", "source_name": "Laboratoire MIA, University of La Rochelle, La Rochelle, France", "street_adddress": "23 Avenue Albert Einstein, 17000 La Rochelle, France", "lat": "46.14764610", "lng": "-1.15494150", "type": "edu", "country": "France"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/9a77/84eea6bfa62bf2834ee0b87a3cdda46006f2.pdf"], "doi": []}, {"id": "719969807953d7ea8bda0397b1aadbaa6e205718", "title": "Automatic Dataset Augmentation", "addresses": [{"name": "Harbin Institute of Technology", "source_name": "Harbin Institute of Technology", "street_adddress": "\u54c8\u5c14\u6ee8\u5de5\u4e1a\u5927\u5b66, \u53f8\u4ee4\u8857, \u5357\u5c97\u533a, \u54c8\u5c14\u6ee8\u5e02 / Harbin, \u9ed1\u9f99\u6c5f\u7701, 150000, \u4e2d\u56fd", "lat": "45.74139210", "lng": "126.62552755", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.08201.pdf"], "doi": []}, {"id": "8de065f412a7d739dff40044212c8506b5c52bf7", "title": "Multi-Person Pose Estimation for PoseTrack with Enhanced Part Affinity Fields", "addresses": [{"name": "Beijing, China", "source_name": "Beijing, China", "street_adddress": "Beijing, China", "lat": "39.90419990", "lng": "116.40739630", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/8de0/65f412a7d739dff40044212c8506b5c52bf7.pdf"], "doi": []}, {"id": "80ef252a17d343ac7b12485c117d6df4a409dee5", "title": "Image Caption with Endogenous\u2013Exogenous Attention", "addresses": [{"name": "Sun Yat-Sen University", "source_name": "Sun Yat-Sen University", "street_adddress": "\u4e2d\u5927, \u65b0\u6e2f\u897f\u8def, \u9f99\u8239\u6ed8, \u5eb7\u4e50, \u6d77\u73e0\u533a (Haizhu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510105, \u4e2d\u56fd", "lat": "23.09461185", "lng": "113.28788994", "type": "edu", "country": "China"}], "year": "2019", "pdf": [], "doi": ["http://doi.org/10.1007/s11063-019-09979-7"]}, {"id": "bd2a3ad4f28757791c9335033f39ac31cb84b8c7", "title": "ScaleNet: Guiding Object Proposal Generation in Supermarkets and Beyond", "addresses": [{"name": "Johns Hopkins University", "source_name": "Johns Hopkins University", "street_adddress": "Baltimore, MD 21218, USA", "lat": "39.32990130", "lng": "-76.62051770", "type": "edu", "country": "United States"}, {"name": "Shanghai University", "source_name": "Shanghai University", "street_adddress": "\u4e0a\u6d77\u5927\u5b66, \u9526\u79cb\u8def, \u5927\u573a\u9547, \u5b9d\u5c71\u533a (Baoshan), \u4e0a\u6d77\u5e02, 201906, \u4e2d\u56fd", "lat": "31.32235655", "lng": "121.38400941", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.06752.pdf"], "doi": []}, {"id": "8a1f46d56ef6dfa34412986a802b5affe2512000", "title": "Aided Action Recognition Using Single Images", "addresses": [{"name": "Lehigh University", "source_name": "Lehigh University", "street_adddress": "Lehigh University, Library Drive, Sayre Park, Bethlehem, Northampton County, Pennsylvania, 18015, USA", "lat": "40.60680280", "lng": "-75.37824880", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/8a1f/46d56ef6dfa34412986a802b5affe2512000.pdf"], "doi": []}, {"id": "6d3d61ef9b5ff6d41badbc3d40ea23acbbc9c3fe", "title": "Learning to Evaluate Image Captioning", "addresses": [{"name": "Cornell University", "source_name": "Cornell University", "street_adddress": "Cornell University, Forest Home Drive, Forest Home, Tompkins County, New York, 14853, USA", "lat": "42.45055070", "lng": "-76.47835130", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.06422.pdf"], "doi": []}, {"id": "2df1688afdb470a9d9eee95e41fc34ebd0c9036b", "title": "Deep Multimodal Learning: An Effective Method for Video Classification", "addresses": [{"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.12563.pdf"], "doi": []}, {"id": "ed605dc1e69dccabf47044499e7ec26e30b72b58", "title": "Pre-gen Metrics: Predicting Caption Quality Metrics Without Generating Captions", "addresses": [{"name": "University of Malta", "source_name": "University of Malta", "street_adddress": "University of Malta, Ring Road, Japanese Garden, L-Imsida, Malta, MSD 9027, Malta", "lat": "35.90232260", "lng": "14.48341890", "type": "edu", "country": "Malta"}], "year": "2018", "pdf": [], "doi": ["http://doi.org/10.1007/978-3-030-11018-5_10"]}, {"id": "c0d0ef94dd3c53c3130b5b8ce38d981929b7adb2", "title": "Weakly- and Semi-supervised Panoptic Segmentation", "addresses": [{"name": "University of Oxford", "source_name": "University of Oxford", "street_adddress": "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "lat": "51.75345380", "lng": "-1.25400997", "type": "edu", "country": "United Kingdom"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.03575.pdf"], "doi": []}, {"id": "31b05f65405534a696a847dd19c621b7b8588263", "title": "UMDFaces: An annotated face dataset for training deep networks", "addresses": [{"name": "University of Maryland", "source_name": "University of Maryland", "street_adddress": "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu", "country": "United States"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8272731"]}, {"id": "43eee49e372e5299608a79f8491fcf40998028df", "title": "Complex event processing for content-based text, image, and video retrieval", "addresses": [{"name": "Army Research Laboratory, Computational and Information Sciences Directorate", "source_name": "Army Research Laboratory, Computational and Information Sciences Directorate", "street_adddress": "2800 Powder Mill Rd, Adelphi, MD 20783, USA", "lat": "39.02985870", "lng": "-76.96380270", "type": "mil", "country": "United States"}, {"name": "Army Research Laboratory, Sensors and Electron Devices Directorate", "source_name": "Army Research Laboratory, Sensors and Electron Devices Directorate", "street_adddress": "2800 Powder Mill Rd, Adelphi, MD 20783, USA", "lat": "39.02985870", "lng": "-76.96380270", "type": "mil", "country": "United States"}, {"name": "Atos Turkey, Ankara, Turkey", "source_name": "Atos Turkey, Ankara, Turkey", "street_adddress": "No: 21, \u00dcniversiteler Mh., Teknokent Silikon Bloklar, 06800 \u00c7ankaya/Ankara, Turkey", "lat": "39.89961620", "lng": "32.77396810", "type": "edu", "country": "Turkey"}, {"name": "Defence Research and Development Canada, Toronto, Ontario", "source_name": "Defence Research and Development Canada, Toronto, Ontario", "street_adddress": "1133 Sheppard Ave W, North York, ON M3K 2C9, Canada", "lat": "43.75107650", "lng": "-79.46945700", "type": "mil", "country": "Canada"}, {"name": "Defence Research and Development Canada, Valcartier, Quebec", "source_name": "Defence Research and Development Canada, Valcartier, Quebec", "street_adddress": "400 Cumberland St, Ottawa, ON K1N 1J8, Canada", "lat": "45.42826030", "lng": "-75.68804370", "type": "mil", "country": "Canada"}, {"name": "TNO, The Hague, Netherlands", "source_name": "TNO, The Hague, Netherlands", "street_adddress": "Anna van Buerenplein 1, 2595 DA Den Haag, Netherlands", "lat": "52.08227700", "lng": "4.32580700", "type": "edu", "country": "Netherlands"}, {"name": "UK Defence Science and Technology Laboratory, Porton, Salisbury, UK", "source_name": "UK Defence Science and Technology Laboratory, Porton, Salisbury, UK", "street_adddress": "Porton Down, Salisbury SP4 0JQ, UK", "lat": "51.13122970", "lng": "-1.70368420", "type": "mil", "country": "United Kingdom"}, {"name": "United States Air Force Research Laboratory, Dayton, OH", "source_name": "United States Air Force Research Laboratory, Dayton, OH", "street_adddress": "1864 4th St, Wright-Patterson AFB, OH 45433, USA", "lat": "39.79084110", "lng": "-84.09897580", "type": "mil", "country": "United States"}], "year": "2016", "pdf": ["http://www.dtic.mil/dtic/tr/fulltext/u2/1011094.pdf", "https://apps.dtic.mil/dtic/tr/fulltext/u2/1011094.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7496546"]}, {"id": "f43012db4836cf671a2a095413ba5ec6725e4a41", "title": "Deep TripletQuantization", "addresses": [{"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}, {"name": "Microsoft Research Asia", "source_name": "Microsoft Research Asia", "street_adddress": "1 Memorial Dr, Cambridge, MA 02142, USA", "lat": "42.36142560", "lng": "-71.08120920", "type": "company", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/f430/12db4836cf671a2a095413ba5ec6725e4a41.pdf"], "doi": []}, {"id": "ebe7eda4fd10caa326d57b93e8a1e2a13e09a403", "title": "TSCSet: A Crowdsourced Time-Sync Comment Dataset for Exploration of User Experience Improvement", "addresses": [{"name": "Rutgers University", "source_name": "Rutgers University", "street_adddress": "Rutgers Cook Campus - North, Biel Road, New Brunswick, Middlesex County, New Jersey, 08901, USA", "lat": "40.47913175", "lng": "-74.43168868", "type": "edu", "country": "United States"}, {"name": "Tongji University", "source_name": "Tongji University", "street_adddress": "\u540c\u6d4e\u5927\u5b66, 1239, \u56db\u5e73\u8def, \u6c5f\u6e7e, \u8679\u53e3\u533a, \u4e0a\u6d77\u5e02, 200092, \u4e2d\u56fd", "lat": "31.28473925", "lng": "121.49694909", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3172966"]}, {"id": "5ba8bb7d204e7a5a29a043792546577500e2e5c1", "title": "Background Appearance Modeling with Applications to Visual Object Detection in an Open-Pit Mine", "addresses": [{"name": "Queensland University of Technology", "source_name": "Queensland University of Technology", "street_adddress": "Queensland University of Technology, Macgregor Lane, Merthyr, South Brisbane, Brisbane, QLD, 4000, Australia", "lat": "-27.47715625", "lng": "153.02841004", "type": "edu", "country": "Australia"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/5ba8/bb7d204e7a5a29a043792546577500e2e5c1.pdf"], "doi": []}, {"id": "48320a4be9cc741fdb28ad72f359c449e41309cc", "title": "Manga109 dataset and creation of metadata", "addresses": [{"name": "University of Tokyo", "source_name": "University of Tokyo", "street_adddress": "\u6771\u4eac\u5927\u5b66 \u67cf\u30ad\u30e3\u30f3\u30d1\u30b9, \u5b66\u878d\u5408\u306e\u9053, \u67cf\u5e02, \u5343\u8449\u770c, \u95a2\u6771\u5730\u65b9, 277-8583, \u65e5\u672c", "lat": "35.90204480", "lng": "139.93622009", "type": "edu", "country": "Japan"}], "year": "2016", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3011551"]}, {"id": "6701efa7f715b3c296843b8ff5414a6610711cf9", "title": "Semi-automatic image and video annotation system for generating ground truth information", "addresses": [{"name": "Korea Electronics Technology Institute", "source_name": "Korea Electronics Technology Institute", "street_adddress": "South Korea, Gyeonggi-do, Seongnam-si, Bundang-gu, \uc0c8\ub098\ub9ac\ub85c 25 (\uc57c\ud0d1\ub3d9) KETI \uc804\uc790\ubd80\ud488\uc5f0\uad6c\uc6d0", "lat": "37.40391700", "lng": "127.15978600", "type": "edu", "country": "South Korea"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8343233", "http://doi.ieeecomputersociety.org/10.1109/ICOIN.2018.8343233", "http://doi.org/10.1109/ICOIN.2018.8343233"]}, {"id": "1334d274bca9c94fed724ecfac7e36d3789aea38", "title": "ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detector", "addresses": [{"name": "Georgia Institute of Technology", "source_name": "Georgia Institute of Technology", "street_adddress": "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu", "country": "United States"}, {"name": "Intel Corporation, Hillsboro, OR, USA", "source_name": "Intel Corporation, Hillsboro, OR, USA", "street_adddress": "6397 NE Evergreen Pkwy, Hillsboro, OR 97124, USA", "lat": "45.55236000", "lng": "-122.91429880", "type": "company", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.05810.pdf"], "doi": []}, {"id": "632fa986bed53862d83918c2b71ab953fd70d6cc", "title": "What Face and Body Shapes Can Tell About Height", "addresses": [{"name": "EPFL", "source_name": "EPFL", "street_adddress": "Route Cantonale, 1015 Lausanne, Switzerland", "lat": "46.51905570", "lng": "6.56675760", "type": "edu", "country": "Switzerland"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.10355.pdf"], "doi": []}, {"id": "2bf41bf420c8d86dd1bffbacd28c70fa8b12b6dd", "title": "Counting the uncountable: deep semantic density estimation from Space", "addresses": [{"name": "ETH Zurich", "source_name": "ETH Zurich", "street_adddress": "R\u00e4mistrasse 101, 8092 Z\u00fcrich, Switzerland", "lat": "47.37631300", "lng": "8.54766990", "type": "edu", "country": "Switzerland"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.07091.pdf"], "doi": []}, {"id": "e4845fb1e624965d4f036d7fd32e8dcdd2408148", "title": "YOLOv3: An Incremental Improvement", "addresses": [{"name": "University of Washington", "source_name": "University of Washington", "street_adddress": "University of Washington, Rainier Vista, Montlake, University District, Seattle, King County, Washington, 98195, USA", "lat": "47.65432380", "lng": "-122.30800894", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.02767.pdf"], "doi": []}, {"id": "663617c728b18e333acb5279e9b1095eeda9287e", "title": "The 2018 DAVIS Challenge on Video Object Segmentation-CVPR 2018 Workshops", "addresses": [{"name": "KTH Royal Institute of Technology, Stockholm", "source_name": "KTH   Royal Institute of Technology, Stockholm", "street_adddress": "KTH, Teknikringen, L\u00e4rkstaden, Norra Djurg\u00e5rden, \u00d6stermalms stadsdelsomr\u00e5de, Sthlm, Stockholm, Stockholms l\u00e4n, Svealand, 114 28, Sverige", "lat": "59.34986645", "lng": "18.07063213", "type": "edu", "country": "Sweden"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/bd1c/72de32b9dafc2c8b392ed26a9977af62fe58.pdf"], "doi": []}, {"id": "fb0bbbc159dad0113f5d01ac736945feeced1247", "title": "Appearance and Gait-Based Progressive Person Re-Identification for Surveillance Systems", "addresses": [{"name": "Beijing University of Posts and Telecommunications", "source_name": "Beijing University of Posts and Telecommunications", "street_adddress": "\u5317\u4eac\u90ae\u7535\u5927\u5b66, \u897f\u571f\u57ce\u8def, \u6d77\u6dc0\u533a, \u5317\u4eac\u5e02, 100082, \u4e2d\u56fd", "lat": "39.96014880", "lng": "116.35193921", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8499460", "http://doi.org/10.1109/BigMM.2018.8499460"]}, {"id": "15147ca5866dc5fbcfa0d91259798599004d051d", "title": "CO-FILTERING HUMAN INTERACTION AND OBJECT SEGMENTATION A Degree Thesis Submitted to the Faculty of the Escola Te\u0300cnica d'Enginyeria de Telecomunicacio\u0301 de Barcelona", "addresses": [{"name": "Universitat Polit\u00e8cnica de Catalunya", "source_name": "Universitat Polit\u00e8cnica de Catalunya", "street_adddress": "Campus Nord, Carrer de Jordi Girona, 1, 3, 08034 Barcelona, Spain", "lat": "41.38800400", "lng": "2.11328040", "type": "edu", "country": "Spain"}], "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/1514/7ca5866dc5fbcfa0d91259798599004d051d.pdf"], "doi": []}, {"id": "6d880f543e583cf1ba4333be7f3845de4dcbda64", "title": "Recursive Visual Attention in Visual Dialog", "addresses": [{"name": "Renmin University of China", "source_name": "Beijing Key Laboratory of Big Data Management and Analysis Methods, Renmin University of China, Beijing, 100872, China", "street_adddress": "59 Zhongguancun St, Haidian Qu, China, 100872", "lat": "39.96960620", "lng": "116.31881450", "type": "edu", "country": "China"}, {"name": "Nanyang Technological University", "source_name": "Nanyang Technological University", "street_adddress": "NTU, Faculty Avenue, Jurong West, Southwest, 637460, Singapore", "lat": "1.34841040", "lng": "103.68297965", "type": "edu", "country": "Singapore"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.02664.pdf"], "doi": []}, {"id": "cba8b9949e71ff485a4ecba33128e2f206651cac", "title": "An RGBD segmentation model for robot vision learned from synthetic data", "addresses": [{"name": "Georgia Institute of Technology", "source_name": "Georgia Institute of Technology", "street_adddress": "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/cba8/b9949e71ff485a4ecba33128e2f206651cac.pdf"], "doi": []}, {"id": "b93cd1e6f1aee81f4f94452c0091d11ee0cb8af3", "title": "Real-world Mapping of Gaze Fixations Using Instance Segmentation for Road Construction Safety Applications", "addresses": [{"name": "North Carolina State University", "source_name": "North Carolina State University", "street_adddress": "North Carolina State University, Oval Drive, West Raleigh, Raleigh, Wake County, North Carolina, 27695, USA", "lat": "35.77184965", "lng": "-78.67408695", "type": "edu", "country": "United States"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.11078.pdf"], "doi": []}, {"id": "4c33746fc5688da61059daa93978ac887f04cce8", "title": "Trainable performance upper bounds for image and video captioning", "addresses": [{"name": "New York University", "source_name": "New York University", "street_adddress": "NYU, West 4th Street, NoHo Historic District, NoHo, Manhattan, Manhattan Community Board 2, New York County, NYC, New York, 10012, USA", "lat": "40.72925325", "lng": "-73.99625394", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/e97f/10c2a4d7edac33597692e6dc243bd86adf10.pdf"], "doi": []}, {"id": "c682ff7a573082c5b69880c4bf84cdd464b70ae5", "title": "Dial2Desc: End-to-end Dialogue Description Generation", "addresses": [{"name": "Zhejiang University", "source_name": "Zhejiang University", "street_adddress": "\u6d59\u6c5f\u5927\u5b66\u4e4b\u6c5f\u6821\u533a, \u4e4b\u6c5f\u8def, \u8f6c\u5858\u8857\u9053, \u897f\u6e56\u533a (Xihu), \u676d\u5dde\u5e02 Hangzhou, \u6d59\u6c5f\u7701, 310008, \u4e2d\u56fd", "lat": "30.19331415", "lng": "120.11930822", "type": "edu", "country": "China"}, {"name": "University of Southern California", "source_name": "University of Southern California", "street_adddress": "University of Southern California, Watt Way, Saint James Park, LA, Los Angeles County, California, 90089, USA", "lat": "34.02241490", "lng": "-118.28634407", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.00185.pdf"], "doi": []}, {"id": "3899b49ca98a134fb9d33feab458f2092da32096", "title": "Faster Bounding Box Annotation for Object Detection in Indoor Scenes", "addresses": [{"name": "Sandvik Mining and Construction Oyj, Tampere, Finland", "source_name": "Sandvik Mining and Construction Oyj, Tampere, Finland", "street_adddress": "Pihtisulunkatu 9, 33330 Tampere, Finland", "lat": "61.50907030", "lng": "23.57149070", "type": "company", "country": "Finland"}, {"name": "Tampere University of Technology", "source_name": "Tampere University of Technology", "street_adddress": "TTY, 10, Korkeakoulunkatu, Finninm\u00e4ki, Hervanta, Tampere, Tampereen seutukunta, Pirkanmaa, L\u00e4nsi- ja Sis\u00e4-Suomen aluehallintovirasto, L\u00e4nsi-Suomi, Manner-Suomi, 33720, Suomi", "lat": "61.44964205", "lng": "23.85877462", "type": "edu", "country": "Finland"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8611732"]}, {"id": "2dda7f46bbb8684a3a497dd40aabd4d759a62386", "title": "YouCookII Dataset", "addresses": [{"name": "Robotics Institute", "source_name": "Robotics Institute", "street_adddress": "Institute for Field Robotics, \u0e1b\u0e23\u0e30\u0e0a\u0e32\u0e2d\u0e38\u0e17\u0e34\u0e28, \u0e01\u0e23\u0e38\u0e07\u0e40\u0e17\u0e1e\u0e21\u0e2b\u0e32\u0e19\u0e04\u0e23, \u0e40\u0e02\u0e15\u0e23\u0e32\u0e29\u0e0e\u0e23\u0e4c\u0e1a\u0e39\u0e23\u0e13\u0e30, \u0e01\u0e23\u0e38\u0e07\u0e40\u0e17\u0e1e\u0e21\u0e2b\u0e32\u0e19\u0e04\u0e23, 10140, \u0e1b\u0e23\u0e30\u0e40\u0e17\u0e28\u0e44\u0e17\u0e22", "lat": "13.65450525", "lng": "100.49423171", "type": "edu", "country": "Thailand"}, {"name": "University of Michigan", "source_name": "University of Michigan", "street_adddress": "University of Michigan, 500, Hayward Street, Ann Arbor, Washtenaw County, Michigan, 48109, USA", "lat": "42.29421420", "lng": "-83.71003894", "type": "edu", "country": "United States"}, {"name": "University of Rochester", "source_name": "University of Rochester", "street_adddress": "Memorial Art Gallery, 500, University Avenue, East End, Rochester, Monroe County, New York, 14607, USA", "lat": "43.15769690", "lng": "-77.58829158", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/2dda/7f46bbb8684a3a497dd40aabd4d759a62386.pdf"], "doi": []}, {"id": "93b689145277f7594e4bc0af2ffec5d3a31cc1fa", "title": "Leveraging Convolutional Pose Machines for Fast and Accurate Head Pose Estimation", "addresses": [{"name": "IDIAP Research Institute", "source_name": "IDIAP Research Institute", "street_adddress": "Idiap Research Institute, Parking Centre du parc, Martigny, Valais/Wallis, 1920, Schweiz/Suisse/Svizzera/Svizra", "lat": "46.10923700", "lng": "7.08453549", "type": "edu", "country": "Switzerland"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8594223"]}, {"id": "14198efb1ea9d1c621dcac44e9c5aad349c0d69f", "title": "Learning to Segment Human by Watching YouTube", "addresses": [{"name": "Adobe Research, San Jose, CA", "source_name": "Adobe Research, San Jose, CA 95110, USA", "street_adddress": "345 Park Ave, San Jose, CA 95110, USA", "lat": "37.33093070", "lng": "-121.89404850", "type": "company", "country": "United States"}, {"name": "National University of Singapore", "source_name": "National University of Singapore", "street_adddress": "NUS, Former 1936 British Outpost, Nepal Hill, Clementi, Southwest, 117542, Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu", "country": "Singapore"}, {"name": "SnapChat Inc., Venice, CA", "source_name": "SnapChat Inc., Venice, CA", "street_adddress": "2772 Donald Douglas Loop N, Santa Monica, CA 90405, USA", "lat": "34.01629660", "lng": "-118.45349590", "type": "company", "country": "United States"}, {"name": "Sun Yat-Sen University", "source_name": "Sun Yat-Sen University", "street_adddress": "\u4e2d\u5927, \u65b0\u6e2f\u897f\u8def, \u9f99\u8239\u6ed8, \u5eb7\u4e50, \u6d77\u73e0\u533a (Haizhu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510105, \u4e2d\u56fd", "lat": "23.09461185", "lng": "113.28788994", "type": "edu", "country": "China"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7534869"]}, {"id": "72976d066d38d3d378d75dcf1467b0a295acad6b", "title": "iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection", "addresses": [{"name": "Virginia Tech", "source_name": "Virginia Tech", "street_adddress": "Blacksburg, VA 24061, USA", "lat": "37.22838430", "lng": "-80.42341670", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.10437.pdf"], "doi": []}, {"id": "7fda1edac608bc67e55ac3d7c9dc5a542d8f8aee", "title": "Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding", "addresses": [{"name": "Max Planck Institute for Informatics", "source_name": "Max Planck Institute for Informatics", "street_adddress": "MPII, E1 4, Campus, Universit\u00e4t, Sankt Johann, Bezirk Mitte, Saarbr\u00fccken, Regionalverband Saarbr\u00fccken, Saarland, 66123, Deutschland", "lat": "49.25795660", "lng": "7.04577417", "type": "edu", "country": "Germany"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1606.01847.pdf"], "doi": []}, {"id": "54830a1cf8606a5183561357b4004088718e4141", "title": "Deep Watershed Detector for Music Object Recognition", "addresses": [{"name": "ZHAW Datalab", "source_name": "ZHAW Datalab", "street_adddress": "Gertrudstrasse 15, 8400 Winterthur, Switzerland", "lat": "47.49991300", "lng": "8.72052200", "type": "edu", "country": "Switzerland"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.10548.pdf"], "doi": []}, {"id": "e772c6ea8a30ec21c3ede6c8abfd540621174fc2", "title": "Semi- and weakly-supervised human pose estimation", "addresses": [{"name": "Toyota Technological Institute", "source_name": "Toyota Technological Institute", "street_adddress": "6045 S Kenwood Ave, Chicago, IL 60637, USA", "lat": "41.78469820", "lng": "-87.59258480", "type": "edu", "country": "United States"}, {"name": "Nara Institute of Science and Technology, Japan", "source_name": "Nara Institute of Science and Technology, Japan", "street_adddress": "8916\u756a\u5730\u2212\uff15 Takayamacho, Ikoma, Nara Prefecture 630-0192, Japan", "lat": "34.73211210", "lng": "135.73285850", "type": "edu", "country": "Japan"}], "year": "2018", "pdf": ["https://www.toyota-ti.ac.jp/Lab/Denshi/iim/ukita/MyPapers/CVIU2018_Pose_preprint.pdf"], "doi": ["http://doi.org/10.1016/j.cviu.2018.02.003"]}, {"id": "94d177db3f198a3571576e562b4d3d9e816eb3cf", "title": "Dynamic Object Scanning: Object-Based Elastic Timeline for Quickly Browsing First-Person Videos", "addresses": [{"name": "University of Tokyo", "source_name": "University of Tokyo", "street_adddress": "\u6771\u4eac\u5927\u5b66 \u67cf\u30ad\u30e3\u30f3\u30d1\u30b9, \u5b66\u878d\u5408\u306e\u9053, \u67cf\u5e02, \u5343\u8449\u770c, \u95a2\u6771\u5730\u65b9, 277-8583, \u65e5\u672c", "lat": "35.90204480", "lng": "139.93622009", "type": "edu", "country": "Japan"}, {"name": "Waseda University", "source_name": "Waseda University", "street_adddress": "\u65e9\u7a32\u7530\u5927\u5b66 \u5317\u4e5d\u5dde\u30ad\u30e3\u30f3\u30d1\u30b9, 2-2, \u6709\u6bdb\u5f15\u91ce\u7dda, \u516b\u5e61\u897f\u533a, \u5317\u4e5d\u5dde\u5e02, \u798f\u5ca1\u770c, \u4e5d\u5dde\u5730\u65b9, 808-0135, \u65e5\u672c", "lat": "33.88987280", "lng": "130.70856205", "type": "edu", "country": "Japan"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3186501"]}, {"id": "4a9831e5fec549edee454709048a51997ef60fb7", "title": "Did the Model Understand the Question?", "addresses": [{"name": "University of Chicago", "source_name": "THE UNIVERSITY OF CHICAGO", "street_adddress": "University of Chicago, South Ellis Avenue, Woodlawn, Chicago, Cook County, Illinois, 60637, USA", "lat": "41.78468745", "lng": "-87.60074933", "type": "edu", "country": "United States"}, {"name": "Google", "source_name": "Google, Inc.", "street_adddress": "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "lat": "37.42199990", "lng": "-122.08405750", "type": "company", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.05492.pdf"], "doi": []}, {"id": "6f71862aa00d61fc8fd7f205de35ee8af458ec0c", "title": "Semi-supervised Learning of Instance-level Recognition from Video", "addresses": [{"name": "Imperial College London", "source_name": "Imperial College London", "street_adddress": "Imperial College London, Exhibition Road, Brompton, Royal Borough of Kensington and Chelsea, London, Greater London, England, SW7 2AZ, UK", "lat": "51.49887085", "lng": "-0.17560797", "type": "edu", "country": "United Kingdom"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/6f71/862aa00d61fc8fd7f205de35ee8af458ec0c.pdf"], "doi": []}, {"id": "c41e483fee61e5040eeb49859a481352f8e3f8ac", "title": "TOWARDS BETTER UNDERSTANDING OF DEEP LEARNING WITH VISUALIZATION by HAIPENG ZENG", "addresses": [{"name": "Hong Kong University of Science and Technology", "source_name": "Hong Kong University of Science and Technology", "street_adddress": "\u9999\u6e2f\u79d1\u6280\u5927\u5b78 Hong Kong University of Science and Technology, \u5927\u5b78\u9053 University Road, \u5927\u57d4\u4ed4 Tai Po Tsai, \u5927\u57d4\u4ed4\u6751 Tai Po Tsai Village, \u65b0\u754c New Territories, HK, DD253 1209, \u4e2d\u56fd", "lat": "22.33863040", "lng": "114.26203370", "type": "edu", "country": "China"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/c41e/483fee61e5040eeb49859a481352f8e3f8ac.pdf"], "doi": []}, {"id": "101d1cff1aa5590a1f79bc485cbfec094a995f74", "title": "Persuasive Faces: Generating Faces in Advertisements (Supplementary Material)", "addresses": [{"name": "University of Pittsburgh", "source_name": "University of Pittsburgh", "street_adddress": "University of Pittsburgh, Sutherland Drive, West Oakland, PGH, Allegheny County, Pennsylvania, 15240, USA", "lat": "40.44415295", "lng": "-79.96243993", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/101d/1cff1aa5590a1f79bc485cbfec094a995f74.pdf"], "doi": []}, {"id": "9a6268d2bc1221ea154097feadea0c58f234d02f", "title": "Co-Attending Free-Form Regions and Detections With Multi-Modal Multiplicative Feature Embedding for Visual Question Answering", "addresses": [{"name": "Chinese University of Hong Kong", "source_name": "Chinese University of Hong Kong", "street_adddress": "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "lat": "22.41626320", "lng": "114.21093180", "type": "edu", "country": "China"}, {"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}, {"name": "East China Normal University", "source_name": "East China Normal University", "street_adddress": "\u534e\u4e1c\u5e08\u8303\u5927\u5b66, 3663, \u4e2d\u5c71\u5317\u8def, \u66f9\u5bb6\u6e21, \u666e\u9640\u533a, \u666e\u9640\u533a (Putuo), \u4e0a\u6d77\u5e02, 200062, \u4e2d\u56fd", "lat": "31.22849230", "lng": "121.40211389", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.06794.pdf"], "doi": []}, {"id": "44674b020e9ce46b16ffb72952a7cacb40d01657", "title": "Depth-aware neural style transfer", "addresses": [{"name": "Cardiff University", "source_name": "Cardiff University", "street_adddress": "Cardiff University, Park Place, Castle, Cardiff, Wales, CF, UK", "lat": "51.48799610", "lng": "-3.17969747", "type": "edu", "country": "United Kingdom"}, {"name": "NanKai University", "source_name": "College of Information Technical Science, NanKai University, CITS, TianJin, China", "street_adddress": "China, Tianjin, Nankai, Lequn N Rd, \u5357\u5f00\u5927\u5b66\u7efc\u5408\u5b9e\u9a8c\u697cA\u533a604", "lat": "39.10335500", "lng": "117.16492700", "type": "edu", "country": "China"}], "year": "2017", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3092924"]}, {"id": "bce963c494ccce1c66757e69993f578c37564f6d", "title": "Can Adversarial Networks Hallucinate Occluded People With a Plausible Aspect?", "addresses": [{"name": "University of Modena and Reggio Emilia", "source_name": "University of Modena and Reggio Emilia 41125, Modena, Italy", "street_adddress": "Via Universit\u00e0, 4, 41121 Modena MO, Italy", "lat": "44.64510460", "lng": "10.92792680", "type": "edu", "country": "Italy"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.08097.pdf"], "doi": []}, {"id": "8dcc95debd07ebab1721c53fa50d846fef265022", "title": "MicroExpNet: An Extremely Small and Fast Model For Expression Recognition From Frontal Face Images", "addresses": [{"name": "Middle East Technical University", "source_name": "Middle East Technical University", "street_adddress": "ODT\u00dc, 1, 1591.sk(315.sk), \u00c7i\u011fdem Mahallesi, Ankara, \u00c7ankaya, Ankara, \u0130\u00e7 Anadolu B\u00f6lgesi, 06800, T\u00fcrkiye", "lat": "39.87549675", "lng": "32.78553506", "type": "edu", "country": "Turkey"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1711.07011.pdf"], "doi": []}, {"id": "3ff40f0760bd8d3c46d72147b0f5b0d4aee2a24f", "title": "AI Challenger : A Large-scale Dataset for Going Deeper in Image Understanding", "addresses": [{"name": "Peking University", "source_name": "Peking University", "street_adddress": "\u5317\u4eac\u5927\u5b66, 5\u53f7, \u9890\u548c\u56ed\u8def, \u7a3b\u9999\u56ed\u5357\u793e\u533a, \u6d77\u6dc0\u533a, \u5317\u4eac\u5e02, 100871, \u4e2d\u56fd", "lat": "39.99223790", "lng": "116.30393816", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1711.06475.pdf"], "doi": []}, {"id": "e7d6fc6daf70a30993b57efff9a259bd418c5c91", "title": "Infrared and Visible Image Fusion with ResNet and zero-phase component analysis", "addresses": [{"name": "University of Strathclyde", "source_name": "Centre for excellence in Signal and Image Processing, University of Strathclyde, Glasgow, UK", "street_adddress": "16 Richmond St, Glasgow G1 1XQ, UK", "lat": "55.86212200", "lng": "-4.24228510", "type": "edu", "country": "United Kingdom"}, {"name": "Jiangnan University", "source_name": "Jiangnan University", "street_adddress": "\u6c5f\u5357\u5927\u5b66\u7ad9, \u8821\u6e56\u5927\u9053, \u6ee8\u6e56\u533a, \u5357\u573a\u6751, \u6ee8\u6e56\u533a (Binhu), \u65e0\u9521\u5e02 / Wuxi, \u6c5f\u82cf\u7701, 214121, \u4e2d\u56fd", "lat": "31.48542550", "lng": "120.27395810", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.07119.pdf"], "doi": []}, {"id": "74875368649f52f74bfc4355689b85a724c3db47", "title": "Object detection by labeling superpixels", "addresses": [{"name": "National Laboratory of Pattern Recognition, Chinese Academy of Sciences", "source_name": "National Laboratory of Pattern Recognition, Institute of Automation of Chinese, Academy of Sciences, Beijing, China", "street_adddress": "China, Beijing, Haidian, \u4e2d\u5173\u6751\u4e1c\u8def95\u53f7", "lat": "39.97920300", "lng": "116.33287000", "type": "edu", "country": "China"}], "year": "2015", "pdf": ["http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/3B_072.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/3B_072_ext.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7299146", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2015.7299146", "http://doi.org/10.1109/CVPR.2015.7299146"]}, {"id": "01cb4071a0a43aeef63e5d568ad5afe1fb8b2411", "title": "Domain Separation Networks", "addresses": [{"name": "Imperial College London", "source_name": "Imperial College London", "street_adddress": "Imperial College London, Exhibition Road, Brompton, Royal Borough of Kensington and Chelsea, London, Greater London, England, SW7 2AZ, UK", "lat": "51.49887085", "lng": "-0.17560797", "type": "edu", "country": "United Kingdom"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/01cb/4071a0a43aeef63e5d568ad5afe1fb8b2411.pdf"], "doi": []}, {"id": "54b5aab87dbe38803935789c4d730bd203d198a1", "title": "3D Human Pose Estimation in RGBD Images for Robotic Task Learning", "addresses": [{"name": "University of Freiburg", "source_name": "Social Robotics Lab, University of Freiburg, Germany", "street_adddress": "Fahnenbergplatz, 79085 Freiburg im Breisgau, Germany", "lat": "47.99354410", "lng": "7.84594960", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8462833"]}, {"id": "09a4f1b7afd8d5f6854b23f0aa9e80b9a0fa6d20", "title": "Seeing Beyond Appearance - Mapping Real Images into Geometrical Domains for Unsupervised CAD-based Recognition", "addresses": [{"name": "University of Passau", "source_name": "Chair of Complex & Intelligent Systems, University of Passau, Passau, Germany", "street_adddress": "Innstra\u00dfe 41, 94032 Passau, Germany", "lat": "48.56704660", "lng": "13.45178350", "type": "edu", "country": "Germany"}, {"name": "Technical University of Munich", "source_name": "Computer Aided Medical Procedures, Technical University of Munich, Garching, Germany", "street_adddress": "Boltzmannstra\u00dfe 3, 85748 Garching bei M\u00fcnchen, Germany", "lat": "48.26301100", "lng": "11.66685700", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.04158.pdf"], "doi": []}, {"id": "f9a14264ca328cfbd817c7458eee5b18592e5d54", "title": "Feature Fusion for Weakly Supervised Object Localization", "addresses": [{"name": "Xi'an Jiaotong University", "source_name": "Xi'an Jiaotong University", "street_adddress": "\u897f\u5b89\u4ea4\u901a\u5927\u5b66\u5174\u5e86\u6821\u533a, \u6587\u6cbb\u8def, \u4e50\u5c45\u573a, \u7891\u6797\u533a (Beilin), \u897f\u5b89\u5e02, \u9655\u897f\u7701, 710048, \u4e2d\u56fd", "lat": "34.24749490", "lng": "108.97898751", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8623227"]}, {"id": "ab0715642330502d5efca948e4753651cb004d84", "title": "Soft-NMS \u2014 Improving Object Detection with One Line of Code", "addresses": [{"name": "University of Maryland", "source_name": "University of Maryland", "street_adddress": "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.04503.pdf"], "doi": []}, {"id": "86c158ef6caaf247d5d14e07c5edded0147df8b7", "title": "Spatial Memory for Context Reasoning in Object Detection", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.04224.pdf"], "doi": []}, {"id": "adc55a30b17060d68b5092dfaba52243e39c68f5", "title": "Meaningful maps with object-oriented semantic mapping", "addresses": [{"name": "Queensland University of Technology (QUT)", "source_name": "Queensland University of Technology (QUT)", "street_adddress": "2 George St, Brisbane City QLD 4000, Australia", "lat": "-27.47735700", "lng": "153.02841500", "type": "edu", "country": "Australia"}, {"name": "University of Adelaide", "source_name": "University of Adelaide", "street_adddress": "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu", "country": "Australia"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8206392"]}, {"id": "3d5575e9ba02128d94c20330f4525fc816411ec2", "title": "Learning Video Object Segmentation from Static Images", "addresses": [{"name": "Disney Research", "source_name": "Disney Research", "street_adddress": "521 Circle 7 Dr, Glendale, CA 91201, USA", "lat": "34.15797420", "lng": "-118.28947290", "type": "company", "country": "United States"}, {"name": "ETH Zurich", "source_name": "ETH Zurich", "street_adddress": "R\u00e4mistrasse 101, 8092 Z\u00fcrich, Switzerland", "lat": "47.37631300", "lng": "8.54766990", "type": "edu", "country": "Switzerland"}, {"name": "Max Planck Institute for Informatics", "source_name": "Max Planck Institute for Informatics", "street_adddress": "MPII, E1 4, Campus, Universit\u00e4t, Sankt Johann, Bezirk Mitte, Saarbr\u00fccken, Regionalverband Saarbr\u00fccken, Saarland, 66123, Deutschland", "lat": "49.25795660", "lng": "7.04577417", "type": "edu", "country": "Germany"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1612.02646.pdf"], "doi": []}, {"id": "089513ca240c6d672c79a46fa94a92cde28bd567", "title": "RNN Fisher Vectors for Action Recognition and Image Annotation", "addresses": [{"name": "Tel Aviv University", "source_name": "Tel Aviv University", "street_adddress": "\u05d0\u05d5\u05e0\u05d9\u05d1\u05e8\u05e1\u05d9\u05d8\u05ea \u05ea\u05dc \u05d0\u05d1\u05d9\u05d1, \u05db\u05d9\u05db\u05e8 \u05de\u05e0\u05d3\u05dc, \u05ea\u05dc \u05d0\u05d1\u05d9\u05d1 - \u05d9\u05e4\u05d5, \u05d0\u05e4\u05e7\u05d4, \u05ea\u05dc \u05d0\u05d1\u05d9\u05d1-\u05d9\u05e4\u05d5, \u05de\u05d7\u05d5\u05d6 \u05ea\u05dc \u05d0\u05d1\u05d9\u05d1, NO, \u05d9\u05e9\u05e8\u05d0\u05dc", "lat": "32.11198890", "lng": "34.80459702", "type": "edu", "country": "Israel"}, {"name": "IBM Research, Haifa, Israel", "source_name": "IBM Research - Haifa, Israel", "street_adddress": "\u05e7\u05de\u05e4\u05d5\u05e1 \u05d0\u05d5\u05e0\u05d9\u05d1\u05e8\u05e1\u05d9\u05d8\u05d4 \u05d7\u05d9\u05e4\u05d4, \u05d7\u05d9\u05e4\u05d4, Israel", "lat": "32.76526220", "lng": "35.01576130", "type": "company", "country": "Israel"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1512.03958.pdf"], "doi": []}, {"id": "8f1fcd6c3007f48eafeddf5f517c1197b2aab9cc", "title": "DPRed: Making Typical Activation and Weight Values Matter In Deep Learning Computing.", "addresses": [{"name": "University of Toronto", "source_name": "University of Toronto", "street_adddress": "University of Toronto, St. George Street, Bloor Street Culture Corridor, Old Toronto, Toronto, Ontario, M5S 1A5, Canada", "lat": "43.66333345", "lng": "-79.39769975", "type": "edu", "country": "Canada"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.06732.pdf"], "doi": []}, {"id": "c0d5fa2e57646f2cc7dbb9633261af7d20f8a51e", "title": "Joint Global and Co-Attentive Representation Learning for Image-Sentence Retrieval", "addresses": [{"name": "Chinese Academy of Sciences & University of Chinese Academy of Sciences", "source_name": "Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China", "street_adddress": "China, Beijing, Haidian, Zhongguancun South 1st Alley, \u4e2d\u5173\u6751\u5357\u4e00\u6761", "lat": "39.98177000", "lng": "116.33008600", "type": "edu", "country": "China"}, {"name": "Chinese Academy of Sciences", "source_name": "Chinese Academy of Sciences", "street_adddress": "\u4e2d\u56fd\u79d1\u5b66\u9662\u5fc3\u7406\u7814\u7a76\u6240, 16, \u6797\u8403\u8def, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100101, \u4e2d\u56fd", "lat": "40.00447950", "lng": "116.37023800", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3240535"]}, {"id": "7ec16949adf6ea78054f6c6512f332a86960b91f", "title": "Computer Vision \u2013 ECCV 2016", "addresses": [{"name": "Czech Technical University", "source_name": "Czech Technical University", "street_adddress": "\u010cesk\u00e9 vysok\u00e9 u\u010den\u00ed technick\u00e9 v Praze, Resslova, Nov\u00e9 M\u011bsto, Praha, okres Hlavn\u00ed m\u011bsto Praha, Hlavn\u00ed m\u011bsto Praha, Praha, 11121, \u010cesko", "lat": "50.07642960", "lng": "14.41802312", "type": "edu", "country": "Czech Republic"}, {"name": "RWTH Aachen, Aachen, Germany", "source_name": "RWTH Aachen, Aachen, Germany", "street_adddress": "Templergraben 55, 52062 Aachen, Germany", "lat": "50.78007780", "lng": "6.06568690", "type": "edu", "country": "Germany"}, {"name": "University of Amsterdam", "source_name": "University of Amsterdam", "street_adddress": "Institute for Logic, Language and Computation (ILLC), 107, Science Park, Oost-Watergraafsmeer, Amsterdam, Oost, Amsterdam, Noord-Holland, Nederland, 1098XG, Nederland", "lat": "52.35536550", "lng": "4.95016440", "type": "edu", "country": "Netherlands"}, {"name": "University of Trento", "source_name": "University of Trento", "street_adddress": "University of Trento, Via Giuseppe Verdi, Piedicastello, Trento, Territorio Val d'Adige, TN, TAA, 38122, Italia", "lat": "46.06588360", "lng": "11.11598940", "type": "edu", "country": "Italy"}], "year": "2016", "pdf": [], "doi": ["http://doi.org/10.1007/978-3-319-46475-6"]}, {"id": "277bfd1bc89044b4a523ef23f48bd053d5560657", "title": "Large-Scale Object Discovery and Detector Adaptation from Unlabeled Video", "addresses": [{"name": "RWTH Aachen University", "source_name": "RWTH Aachen University", "street_adddress": "RWTH Aachen, Mies-van-der-Rohe-Stra\u00dfe, K\u00f6nigsh\u00fcgel, Aachen-Mitte, Aachen, St\u00e4dteregion Aachen, Regierungsbezirk K\u00f6ln, Nordrhein-Westfalen, 52074, Deutschland", "lat": "50.77917030", "lng": "6.06728733", "type": "edu", "country": "Germany"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1712.08832.pdf"], "doi": []}, {"id": "3e6d2e963f9a1b417871327f648d16f2c66a4068", "title": "Fully Convolutional Neural Networks with Full-Scale-Features for Semantic Segmentation", "addresses": [{"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/3e6d/2e963f9a1b417871327f648d16f2c66a4068.pdf"], "doi": []}, {"id": "cda6d9b0cc1509ec61a43e24e9b7a14b18642aca", "title": "Convolutional Neural Networks combined with Runge-Kutta Methods", "addresses": [{"name": "Northeastern University", "source_name": "Northeastern University", "street_adddress": "Snell Library, 360, Huntington Avenue, Roxbury Crossing, Fenway, Boston, Suffolk County, Massachusetts, 02115, USA", "lat": "42.33836680", "lng": "-71.08793524", "type": "edu", "country": "United States"}, {"name": "University of British Columbia", "source_name": "University of British Columbia", "street_adddress": "University of British Columbia, Eagles Drive, Hawthorn Place, University Endowment Lands, Metro Vancouver, British Columbia, V6T, Canada", "lat": "49.25839375", "lng": "-123.24658161", "type": "edu", "country": "Canada"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.08831.pdf"], "doi": []}, {"id": "9a8662189388dd84ce1ec6e90d103959a4132a95", "title": "Analysis and Optimization of Loss Functions for Multiclass, Top-k, and Multilabel Classification", "addresses": [{"name": "Saarbr\u00fccken, Saarland, Germany", "source_name": "Saarbr\u00fccken, Saarland, Germany", "street_adddress": "Saarbr\u00fccken, Germany", "lat": "49.24015720", "lng": "6.99693270", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8036272"]}, {"id": "33bcc97b605f00145098d095be2841a1fa6b9a95", "title": "Order-Embeddings of Images and Language", "addresses": [{"name": "University of Toronto", "source_name": "University of Toronto", "street_adddress": "University of Toronto, St. George Street, Bloor Street Culture Corridor, Old Toronto, Toronto, Ontario, M5S 1A5, Canada", "lat": "43.66333345", "lng": "-79.39769975", "type": "edu", "country": "Canada"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1511.06361.pdf"], "doi": []}, {"id": "126e5a90e12aee34d33e6d301ab9533acf03c199", "title": "Multi-style Generative Network for Real-Time Transfer", "addresses": [{"name": "Rutgers University", "source_name": "Rutgers University", "street_adddress": "Rutgers Cook Campus - North, Biel Road, New Brunswick, Middlesex County, New Jersey, 08901, USA", "lat": "40.47913175", "lng": "-74.43168868", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.06953.pdf"], "doi": []}, {"id": "9c1f5547d98f5390e2389ce40668da83a9830487", "title": "Non-parametric Structured Output Networks", "addresses": [{"name": "Disney Research", "source_name": "Disney Research", "street_adddress": "521 Circle 7 Dr, Glendale, CA 91201, USA", "lat": "34.15797420", "lng": "-118.28947290", "type": "company", "country": "United States"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/9c1f/5547d98f5390e2389ce40668da83a9830487.pdf"], "doi": []}, {"id": "032bde9da87439c781a6c81ba7933985ed95d88e", "title": "What's the point: Semantic segmentation with point supervision", "addresses": [{"name": "Stanford University", "source_name": "Stanford University", "street_adddress": "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu", "country": "United States"}, {"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}, {"name": "University of Edinburgh", "source_name": "University of Edinburgh", "street_adddress": "New College, New College Courtyard, The Mound, Old Town, Edinburgh, City of Edinburgh, Scotland, EH1 2LX, UK", "lat": "55.94951105", "lng": "-3.19534913", "type": "edu", "country": "United Kingdom"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1506.02106.pdf"], "doi": []}, {"id": "414315d44a489d09c6e1933033ffba6396974ee1", "title": "Video Visual Relation Detection", "addresses": [{"name": "Columbia University", "source_name": "Columbia University", "street_adddress": "Columbia University Medical Center, 630, West 168th Street, Washington Heights, Manhattan, Manhattan Community Board 12, New York County, NYC, New York, 10031, USA", "lat": "40.84198360", "lng": "-73.94368971", "type": "edu", "country": "United States"}], "year": "2017", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3123380"]}, {"id": "d182c6d9ac4777b5ad73afdd64b7b68d76037212", "title": "Aligned Image-Word Representations Improve Inductive Transfer Across Vision-Language Tasks", "addresses": [{"name": "University of Illinois, Urbana-Champaign", "source_name": "University of Illinois, Urbana-Champaign", "street_adddress": "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu", "country": "United States"}, {"name": "Google", "source_name": "Google, Inc.", "street_adddress": "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "lat": "37.42199990", "lng": "-122.08405750", "type": "company", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.00260.pdf"], "doi": []}, {"id": "7f33a5fcc5db4625c66972f0e6f06540b64d4f1e", "title": "Image Surveillance Assistant Architecture : Status and Planned Extensions", "addresses": [{"name": "University of Maryland", "source_name": "University of Maryland", "street_adddress": "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu", "country": "United States"}, {"name": "Naval Research Laboratory", "source_name": "Naval Research Laboratory", "street_adddress": "Naval Research Laboratory Post Office, 4555, Overlook Avenue Southwest, Washington, D.C., 20375, USA", "lat": "38.82313810", "lng": "-77.01789020", "type": "mil", "country": "United States"}, {"name": "Fayetteville State University", "source_name": "Fayetteville State University", "street_adddress": "1200 Murchison Rd, Fayetteville, NC 28301, USA", "lat": "35.07422060", "lng": "-78.89248960", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/7f33/a5fcc5db4625c66972f0e6f06540b64d4f1e.pdf"], "doi": []}, {"id": "c0e4b6a993a35ded0d17a5e751bd135b795244ae", "title": "Large-Scale Training of Shadow Detectors with Noisily-Annotated Shadow Examples", "addresses": [{"name": "Stony Brook University", "source_name": "Stony Brook University", "street_adddress": "Stony Brook University, 100, Nicolls Road, Stony Brook, Suffolk County, New York, 11794, USA", "lat": "40.91531960", "lng": "-73.12706260", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["http://www3.cs.stonybrook.edu/~cvl/content/papers/2016/LSS_ECCV16.pdf", "http://www3.cs.stonybrook.edu/~minhhoai/papers/LSS_ECCV16.pdf"], "doi": ["https://doi.org/10.1007/978-3-319-46466-4_49"]}, {"id": "237c0c0749aaab0f73ec0641bef2453714da3099", "title": "An Efficient Hierarchical Convolutional Neural Network for Traffic Object Detection", "addresses": [{"name": "Shanghai Jiao Tong University", "source_name": "Shanghai Jiao Tong University", "street_adddress": "\u4e0a\u6d77\u4ea4\u901a\u5927\u5b66\uff08\u5f90\u6c47\u6821\u533a\uff09, \u6dee\u6d77\u897f\u8def, \u756a\u79ba\u5c0f\u533a, \u5e73\u9634\u6865, \u5f90\u6c47\u533a, \u4e0a\u6d77\u5e02, 200052, \u4e2d\u56fd", "lat": "31.20081505", "lng": "121.42840681", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8500640"]}, {"id": "87697847062e7eefec99a8c3aec888e3eef5e5b9", "title": "Unsupervised Learning of Spoken Language with Visual Context", "addresses": [{"name": "MIT", "source_name": "Massachusetts Institute", "street_adddress": "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/8769/7847062e7eefec99a8c3aec888e3eef5e5b9.pdf"], "doi": []}, {"id": "15908912ce3943fc5ec281c1cbf062722cb114d7", "title": "Dynamic Graph Modules for Modeling Higher-Order Interactions in Activity Recognition", "addresses": [{"name": "University of Rochester", "source_name": "University of Rochester", "street_adddress": "Memorial Art Gallery, 500, University Avenue, East End, Rochester, Monroe County, New York, 14607, USA", "lat": "43.15769690", "lng": "-77.58829158", "type": "edu", "country": "United States"}, {"name": "University of Michigan", "source_name": "University of Michigan", "street_adddress": "University of Michigan, 500, Hayward Street, Ann Arbor, Washtenaw County, Michigan, 48109, USA", "lat": "42.29421420", "lng": "-83.71003894", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.05637.pdf"], "doi": []}, {"id": "60542b1a857024c79db8b5b03db6e79f74ec8f9f", "title": "Learning to Detect Human-Object Interactions", "addresses": [{"name": "University of Michigan", "source_name": "University of Michigan", "street_adddress": "University of Michigan, 500, Hayward Street, Ann Arbor, Washtenaw County, Michigan, 48109, USA", "lat": "42.29421420", "lng": "-83.71003894", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1702.05448.pdf"], "doi": []}, {"id": "41d9719922c81d14f2a39392285c5789f5ea4282", "title": "Head and Body Orientation Estimation Using Convolutional Random Projection Forests", "addresses": [{"name": "Seoul National University", "source_name": "Seoul National University", "street_adddress": "\uc11c\uc6b8\ub300\ud559\uad50, \uc11c\ud638\ub3d9\ub85c, \uc11c\ub454\ub3d9, \uad8c\uc120\uad6c, \uc218\uc6d0\uc2dc, \uacbd\uae30, 16614, \ub300\ud55c\ubbfc\uad6d", "lat": "37.26728000", "lng": "126.98411510", "type": "edu", "country": "South Korea"}], "year": "2019", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8219761"]}, {"id": "6459cf454b87fded65a223a30341e5304519a6aa", "title": "Integrated Object Detection and Tracking with Tracklet-Conditioned Detection", "addresses": [{"name": "Microsoft Research Asia", "source_name": "Microsoft Research Asia", "street_adddress": "1 Memorial Dr, Cambridge, MA 02142, USA", "lat": "42.36142560", "lng": "-71.08120920", "type": "company", "country": "United States"}, {"name": "Beijing Institute of Technology", "source_name": "Beijing Institute of Technology University", "street_adddress": "\u5317\u4eac\u7406\u5de5\u5927\u5b66, 5, \u4e2d\u5173\u6751\u5357\u5927\u8857, \u4e2d\u5173\u6751, \u7a3b\u9999\u56ed\u5357\u793e\u533a, \u6d77\u6dc0\u533a, \u5317\u4eac\u5e02, 100872, \u4e2d\u56fd", "lat": "39.95866520", "lng": "116.30971281", "type": "edu", "country": "China"}, {"name": "University of Science and Technology of China", "source_name": "University of Science and Technology of China", "street_adddress": "\u4e2d\u56fd\u79d1\u5b66\u6280\u672f\u5927\u5b66 \u4e1c\u6821\u533a, 96\u53f7, \u91d1\u5be8\u8def, \u6c5f\u6dee\u5316\u80a5\u5382\u5c0f\u533a, \u829c\u6e56\u8def\u8857\u9053, \u5408\u80a5\u5e02\u533a, \u5408\u80a5\u5e02, \u5b89\u5fbd\u7701, 230026, \u4e2d\u56fd", "lat": "31.83907195", "lng": "117.26420748", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.11167.pdf"], "doi": []}, {"id": "7f836c047bc86d52e3a28098b53311cb2186acaa", "title": "Deep Compositional Question Answering with Neural Module Networks", "addresses": [{"name": "University of California, Berkeley", "source_name": "University of California, Berkeley", "street_adddress": "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "lat": "37.86871260", "lng": "-122.25586815", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/7f83/6c047bc86d52e3a28098b53311cb2186acaa.pdf"], "doi": []}, {"id": "5f5068645a5cebf923093542302c1fa21e387cee", "title": "ChipGAN: A Generative Adversarial Network for Chinese Ink Wash Painting Style Transfer", "addresses": [{"name": "Peking University", "source_name": "Peking University", "street_adddress": "\u5317\u4eac\u5927\u5b66, 5\u53f7, \u9890\u548c\u56ed\u8def, \u7a3b\u9999\u56ed\u5357\u793e\u533a, \u6d77\u6dc0\u533a, \u5317\u4eac\u5e02, 100871, \u4e2d\u56fd", "lat": "39.99223790", "lng": "116.30393816", "type": "edu", "country": "China"}, {"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3240655"]}, {"id": "84ed65bda3de8a17526a0ad06ae3777fbbbeef20", "title": "Adapting Object Detectors from Images to Weakly Labeled Videos", "addresses": [{"name": "University of Manitoba", "source_name": "University of Manitoba", "street_adddress": "University of Manitoba, Gillson Street, Normand Park, Saint Vital, Winnipeg, Manitoba, R3T 2N2, Canada", "lat": "49.80915360", "lng": "-97.13304179", "type": "edu", "country": "Canada"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/84ed/65bda3de8a17526a0ad06ae3777fbbbeef20.pdf"], "doi": []}, {"id": "f85be6a31b74d6da6f490635d314306d77d0b6c7", "title": "Answerer in Questioner's Mind: Information Theoretic Approach to Goal-Oriented Visual Dialog", "addresses": [{"name": "Seoul National University", "source_name": "Seoul National University", "street_adddress": "\uc11c\uc6b8\ub300\ud559\uad50, \uc11c\ud638\ub3d9\ub85c, \uc11c\ub454\ub3d9, \uad8c\uc120\uad6c, \uc218\uc6d0\uc2dc, \uacbd\uae30, 16614, \ub300\ud55c\ubbfc\uad6d", "lat": "37.26728000", "lng": "126.98411510", "type": "edu", "country": "South Korea"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.03881.pdf"], "doi": []}, {"id": "bf8e413869e96afa15ef3ff884cc7739eafa8308", "title": "Deep conditional neural network for image segmentation", "addresses": [{"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}, {"name": "Hong Kong Polytechnic University", "source_name": "Hong Kong Polytechnic University", "street_adddress": "hong kong, 11, \u80b2\u624d\u9053 Yuk Choi Road, \u5c16\u6c99\u5480 Tsim Sha Tsui, \u6cb9\u5c16\u65fa\u5340 Yau Tsim Mong District, \u4e5d\u9f8d Kowloon, HK, 00000, \u4e2d\u56fd", "lat": "22.30457200", "lng": "114.17976285", "type": "edu", "country": "China"}], "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7552924", "http://doi.ieeecomputersociety.org/10.1109/ICME.2016.7552924", "http://doi.org/10.1109/ICME.2016.7552924"]}, {"id": "7dcaf1ef07a593a987f3b529c2ad1e977c0c7196", "title": "Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input", "addresses": [{"name": "MIT", "source_name": "Massachusetts Institute", "street_adddress": "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.01452.pdf"], "doi": []}, {"id": "1bfc74bad04b407d1792a70d73a3f5dc0be0506d", "title": "Cross-Dataset Adaptation for Visual Question Answering", "addresses": [{"name": "U. of Southern California", "source_name": "U. of Southern California", "street_adddress": "Los Angeles, CA 90007, USA", "lat": "34.02235190", "lng": "-118.28511700", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.03726.pdf"], "doi": []}, {"id": "516d57bbd02a6938a99b45691a3d7864c2fdc70a", "title": "DART: Domain-Adversarial Residual-Transfer Networks for Unsupervised Cross-Domain Image Classification", "addresses": [{"name": "Chinese University of Hong Kong", "source_name": "Chinese University of Hong Kong", "street_adddress": "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "lat": "22.41626320", "lng": "114.21093180", "type": "edu", "country": "China"}, {"name": "University of Electronic Science and Technology of China", "source_name": "University of Electronic Science and Technology of China", "street_adddress": "2 Jianshe North Rd 2nd Section, Jianshe Road, Chenghua Qu, Chengdu Shi, Sichuan Sheng, China, 610054", "lat": "30.67272100", "lng": "104.09880600", "type": "edu", "country": "China"}, {"name": "Google", "source_name": "Google, Inc.", "street_adddress": "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "lat": "37.42199990", "lng": "-122.08405750", "type": "company", "country": "United States"}, {"name": "Singapore Management University", "source_name": "Singapore Management University", "street_adddress": "Singapore Management University, Fort Canning Tunnel, Clarke Quay, City Hall, Singapore, Central, 178895, Singapore", "lat": "1.29500195", "lng": "103.84909214", "type": "edu", "country": "Singapore"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.11478.pdf"], "doi": []}, {"id": "d0a934ef5b4edf7ebdc2276048534e4c9acf5a76", "title": "Person Retrieval in Surveillance Video using Height, Color and Gender", "addresses": [{"name": "L. D. College of Engineering, India", "source_name": "L. D. College of Engineering, India", "street_adddress": "120, Circular Road, University Area, Ahmedabad, Gujarat 380015, India", "lat": "23.03380000", "lng": "72.54658400", "type": "edu", "country": "India"}, {"name": "Ahmedabad University", "source_name": "Ahmedabad University", "street_adddress": "School of Science and Technology, University Road, Gurukul, Gulbai tekra, Ahmedabad, Ahmedabad District, Gujarat, 380001, India", "lat": "23.03787430", "lng": "72.55180046", "type": "edu", "country": "India"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8639145"]}, {"id": "ce9287a47f00d06ef75fe3ace9adbd7691b6e844", "title": "Large-Scale Visual Relationship Understanding", "addresses": [{"name": "Rutgers University", "source_name": "Rutgers University", "street_adddress": "Rutgers Cook Campus - North, Biel Road, New Brunswick, Middlesex County, New Jersey, 08901, USA", "lat": "40.47913175", "lng": "-74.43168868", "type": "edu", "country": "United States"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1804.10660.pdf"], "doi": []}, {"id": "c7132da9421bfa06fbc859d6c3d6e621bd7bf472", "title": "Multimodal Deep Embedding via Hierarchical Grounded Compositional Semantics", "addresses": [{"name": "Zhejiang University", "source_name": "Zhejiang University", "street_adddress": "\u6d59\u6c5f\u5927\u5b66\u4e4b\u6c5f\u6821\u533a, \u4e4b\u6c5f\u8def, \u8f6c\u5858\u8857\u9053, \u897f\u6e56\u533a (Xihu), \u676d\u5dde\u5e02 Hangzhou, \u6d59\u6c5f\u7701, 310008, \u4e2d\u56fd", "lat": "30.19331415", "lng": "120.11930822", "type": "edu", "country": "China"}, {"name": "Binghamton University", "source_name": "Binghamton University", "street_adddress": "Binghamton University Downtown Center, Washington Street, Downtown, Binghamton, Broome County, New York, 13901, USA", "lat": "42.09580770", "lng": "-75.91455689", "type": "edu", "country": "United States"}, {"name": "Microsoft Research Asia", "source_name": "Microsoft Research Asia", "street_adddress": "1 Memorial Dr, Cambridge, MA 02142, USA", "lat": "42.36142560", "lng": "-71.08120920", "type": "company", "country": "United States"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7562283"]}, {"id": "c8b592fcf2ed2f75799b94c428d2ccdf1e82c5f7", "title": "RUC-Tencent at ImageCLEF 2015: Concept Detection, Localization and Sentence Generation", "addresses": [{"name": "Renmin University of China", "source_name": "Beijing Key Laboratory of Big Data Management and Analysis Methods, Renmin University of China, Beijing, 100872, China", "street_adddress": "59 Zhongguancun St, Haidian Qu, China, 100872", "lat": "39.96960620", "lng": "116.31881450", "type": "edu", "country": "China"}, {"name": "Tencent", "source_name": "Tencent", "street_adddress": "Ke Ji Zhong Yi Lu, Nanshan Qu, Shenzhen Shi, Guangdong Sheng, China, 518057", "lat": "22.54471540", "lng": "113.93571640", "type": "company", "country": "United States"}], "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/c8b5/92fcf2ed2f75799b94c428d2ccdf1e82c5f7.pdf"], "doi": []}, {"id": "ea8c1ac5a1594d6441d10914e0ccc4bd3e9eadfa", "title": "Anchor Box Optimization for Object Detection", "addresses": [{"name": "University of Illinois, Urbana-Champaign", "source_name": "University of Illinois, Urbana-Champaign", "street_adddress": "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu", "country": "United States"}, {"name": "Microsoft", "source_name": "Microsoft Corporation, Redmond, WA, USA", "street_adddress": "One Microsoft Way, Redmond, WA 98052, USA", "lat": "47.64233180", "lng": "-122.13693020", "type": "company", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.00469.pdf"], "doi": []}, {"id": "d4a7259340ece685b9dacb390eea10c6684a05b3", "title": "Object Detection based on Region Decomposition and Assembly", "addresses": [{"name": "Incheon National University", "source_name": "Incheon National University, Incheon, South Korea", "street_adddress": "119 Academy-ro, Songdo 1(il)-dong, Yeonsu-gu, Incheon, South Korea", "lat": "37.37505480", "lng": "126.63289980", "type": "edu", "country": "South Korea"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.08225.pdf"], "doi": []}, {"id": "c733e4a14b51623120da9b4571b4409bc99ab0cd", "title": "Mainstream: Dynamic Stem-Sharing for Multi-Tenant Video Processing", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/2d64/9992d78efd47b22c9a4dcb52386a951b54ea.pdf"], "doi": []}, {"id": "4328ec9d98eff5d7eb70997f76d81b27849f3220", "title": "Scalable, High-Quality Object Detection", "addresses": [{"name": "Google", "source_name": "Google, Inc.", "street_adddress": "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "lat": "37.42199990", "lng": "-122.08405750", "type": "company", "country": "United States"}, {"name": "University of Michigan", "source_name": "University of Michigan", "street_adddress": "University of Michigan, 500, Hayward Street, Ann Arbor, Washtenaw County, Michigan, 48109, USA", "lat": "42.29421420", "lng": "-83.71003894", "type": "edu", "country": "United States"}], "year": "2014", "pdf": ["https://arxiv.org/pdf/1412.1441.pdf"], "doi": []}, {"id": "e304e516fd4e1499b616f120795600eb688fa93e", "title": "People and Vehicles in Danger - A Fire and Flood Detection System in Social Media", "addresses": [{"name": "CERTH-ITI, Thessaloniki, Greece", "source_name": "CERTH-ITI, Thessaloniki, Greece", "street_adddress": "Thermi 570 01, Greece", "lat": "40.56676110", "lng": "22.99801470", "type": "edu", "country": "Greece"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8448732", "http://doi.org/10.1109/IVMSPW.2018.8448732"]}, {"id": "438d4c181362386590eb703c3b65934a6acbbbdc", "title": "A Multi-Oriented Scene Text Detector with Position-Sensitive Segmentation", "addresses": [{"name": "University of Chinese Academy of Sciences", "source_name": "University of Chinese Academy of Sciences", "street_adddress": "University of Chinese Academy of Sciences, UCAS, Yuquanlu, \u7389\u6cc9\u8def, \u7530\u6751, \u6d77\u6dc0\u533a, 100049, \u4e2d\u56fd", "lat": "39.90828040", "lng": "116.24585270", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3206043"]}, {"id": "29b1a44d1e1ffa05c2bf7f4be931c5045f427718", "title": "ON GENERIC OBJECT RECOGNITION TECHNIQUES : CHALLENGES AND OPPORTUNITIES Prof", "addresses": [{"name": "Nirma University", "source_name": "Student, Computer Engineering, Institute of Technology, Nirma University, Ahmedabad - 382 481, Gujarat, India", "street_adddress": "Sarkhej-Gandhinagar Highway, Gota, Ahmedabad, Gujarat 382481, India", "lat": "23.12838620", "lng": "72.54485080", "type": "edu", "country": "India"}], "year": "", "pdf": ["https://pdfs.semanticscholar.org/29b1/a44d1e1ffa05c2bf7f4be931c5045f427718.pdf"], "doi": []}, {"id": "0005a23c0db792ac9d0f5d408c39240ffe4c1d57", "title": "Understanding Fake Faces", "addresses": [{"name": "Waseda University", "source_name": "Waseda University", "street_adddress": "\u65e9\u7a32\u7530\u5927\u5b66 \u5317\u4e5d\u5dde\u30ad\u30e3\u30f3\u30d1\u30b9, 2-2, \u6709\u6bdb\u5f15\u91ce\u7dda, \u516b\u5e61\u897f\u533a, \u5317\u4e5d\u5dde\u5e02, \u798f\u5ca1\u770c, \u4e5d\u5dde\u5730\u65b9, 808-0135, \u65e5\u672c", "lat": "33.88987280", "lng": "130.70856205", "type": "edu", "country": "Japan"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.08391.pdf"], "doi": []}, {"id": "f660ea723b62f69b9f4c439724a6b73357e1d3c3", "title": "Survey on the attention based RNN model and its applications in computer vision", "addresses": [{"name": "Delft University of Technology", "source_name": "Delft University of Technology", "street_adddress": "TU Delft, Mekelweg, TU-wijk, Delft, Zuid-Holland, Nederland, 2628, Nederland", "lat": "51.99882735", "lng": "4.37396037", "type": "edu", "country": "Netherlands"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1601.06823.pdf"], "doi": []}, {"id": "057d5f66a873ec80f8ae2603f937b671030035e6", "title": "Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images", "addresses": [{"name": "University of Washington", "source_name": "University of Washington", "street_adddress": "University of Washington, Rainier Vista, Montlake, University District, Seattle, King County, Washington, 98195, USA", "lat": "47.65432380", "lng": "-122.30800894", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1511.04048.pdf"], "doi": []}, {"id": "05fa7085663bbbd1057c0d240158091930c59c6a", "title": "MovieQA: Understanding Stories in Movies through Question-Answering", "addresses": [{"name": "Karlsruhe Institute of Technology", "source_name": "Karlsruhe Institute of Technology", "street_adddress": "KIT, Leopoldshafener Allee, Linkenheim, Linkenheim-Hochstetten, Landkreis Karlsruhe, Regierungsbezirk Karlsruhe, Baden-W\u00fcrttemberg, 76351, Deutschland", "lat": "49.10184375", "lng": "8.43312560", "type": "edu", "country": "Germany"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1512.02902.pdf"], "doi": []}, {"id": "2fe87224a5b8db29f72936c1cae17389e1c553ad", "title": "ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation", "addresses": [{"name": "University of Washington", "source_name": "University of Washington", "street_adddress": "University of Washington, Rainier Vista, Montlake, University District, Seattle, King County, Washington, 98195, USA", "lat": "47.65432380", "lng": "-122.30800894", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.06815.pdf"], "doi": []}, {"id": "bb9e418469d018be7f5ac2c4b2435ccac50088a3", "title": "Deep Learning\u2013Based Multimedia Analytics: A Review", "addresses": [{"name": "University of Ottawa", "source_name": "University of Ottawa", "street_adddress": "University of Ottawa, 1, Stewart Street, Byward Market, Lowertown, Rideau-Vanier, Ottawa, Ontario, K1N 6N5, Canada", "lat": "45.42580475", "lng": "-75.68740118", "type": "edu", "country": "Canada"}], "year": "2019", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3279952"]}, {"id": "4634bf44a0c994e2bed89686225f8cef601a0224", "title": "NLM at ImageCLEF 2018 Visual Question Answering in the Medical Domain", "addresses": [{"name": "Lister Hill National Center for Biomedical Communications", "source_name": "Lister Hill National Center for Biomedical Communications, U.S. National Library of Medicine, Bethesda, MD, USA", "street_adddress": "8600 Rockville Pike, Bethesda, MD 20894, USA", "lat": "38.99595080", "lng": "-77.09883230", "type": "gov", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/4634/bf44a0c994e2bed89686225f8cef601a0224.pdf"], "doi": []}, {"id": "59f357015054bab43fb8cbfd3f3dbf17b1d1f881", "title": "Unsupervised Multi-Object Detection for Video Surveillance Using Memory-Based Recurrent Attention Networks", "addresses": [{"name": "National University of Defense Technology, China", "source_name": "National University of Defence Technology, Changsha 410000, China", "street_adddress": "\u56fd\u9632\u79d1\u5b66\u6280\u672f\u5927\u5b66, \u4e09\u4e00\u5927\u9053, \u5f00\u798f\u533a, \u5f00\u798f\u533a (Kaifu), \u957f\u6c99\u5e02 / Changsha, \u6e56\u5357\u7701, 410073, \u4e2d\u56fd", "lat": "28.22902090", "lng": "112.99483204", "type": "mil", "country": "China"}, {"name": "University College London", "source_name": "University College London", "street_adddress": "UCL Institute of Education, 20, Bedford Way, Holborn, Bloomsbury, London Borough of Camden, London, Greater London, England, WC1H 0AL, UK", "lat": "51.52316070", "lng": "-0.12820370", "type": "edu", "country": "United Kingdom"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/59f3/57015054bab43fb8cbfd3f3dbf17b1d1f881.pdf"], "doi": []}, {"id": "1687d0120e937d5efe2022cbeab19b38edba0608", "title": "A 2 A : Attention to Attention Reasoning for Movie Question Answering", "addresses": [{"name": "National Tsing Hua University", "source_name": "National Tsing Hua University", "street_adddress": "\u570b\u7acb\u6e05\u83ef\u5927\u5b78, 101, \u514b\u606d\u6a4b, \u5149\u660e\u91cc, \u8d64\u571f\u5d0e, \u6771\u5340, \u65b0\u7af9\u5e02, 30013, \u81fa\u7063", "lat": "24.79254840", "lng": "120.99511830", "type": "edu", "country": "Taiwan"}, {"name": "Institute of Information Science", "source_name": "Institute of Information Science", "street_adddress": "\u8cc7\u8a0a\u79d1\u5b78\u7814\u7a76\u6240, \u6578\u7406\u5927\u9053, \u4e2d\u7814\u91cc, \u5357\u6e2f\u5b50, \u5357\u6e2f\u5340, \u81fa\u5317\u5e02, 11574, \u81fa\u7063", "lat": "25.04107280", "lng": "121.61475620", "type": "edu", "country": "Taiwan"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/1687/d0120e937d5efe2022cbeab19b38edba0608.pdf"], "doi": []}, {"id": "dbf777403156adda2d551a973379edd3e2bc5aaa", "title": "Interpretable Explanations of Black Boxes by Meaningful Perturbation", "addresses": [{"name": "University of Oxford", "source_name": "University of Oxford", "street_adddress": "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "lat": "51.75345380", "lng": "-1.25400997", "type": "edu", "country": "United Kingdom"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.03296.pdf"], "doi": []}, {"id": "4d925db7c9e3cca2e8fed644f750d218a48cd081", "title": "Automatic Concept Discovery from Parallel Text and Visual Corpora", "addresses": [{"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1509.07225.pdf"], "doi": []}, {"id": "d2b2cb1d5cc1aa30cf5be7bcb0494198934caabb", "title": "A Restricted Visual Turing Test for Deep Scene and Event Understanding", "addresses": [{"name": "UCLA", "source_name": "University of California, Los Angeles", "street_adddress": "Los Angeles, CA 90095, USA", "lat": "34.06892100", "lng": "-118.44518110", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1512.01715.pdf"], "doi": []}, {"id": "07ca470ed3be3a476b6fc1917bbbf4182846d1db", "title": "Transforming sensor data to the image domain for deep learning \u2014 An application to footstep detection", "addresses": [{"name": "University of Fribourg", "source_name": "University of Fribourg", "street_adddress": "Avenue de l'Europe 20, 1700 Fribourg, Switzerland", "lat": "46.80635700", "lng": "7.15200600", "type": "edu", "country": "Switzerland"}, {"name": "TU Kaiserslautern, Germany", "source_name": "TU Kaiserslautern, Germany", "street_adddress": "Erwin-Schr\u00f6dinger-Stra\u00dfe 52, 67663 Kaiserslautern, Germany", "lat": "49.42538910", "lng": "7.75531960", "type": "edu", "country": "Germany"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1701.01077.pdf"], "doi": []}, {"id": "9dde6ed569684356c46217fa53224272b668bae8", "title": "Are You Talking to Me? Reasoned Visual Dialog Generation Through Adversarial Learning", "addresses": [{"name": "University of Adelaide", "source_name": "University of Adelaide", "street_adddress": "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu", "country": "Australia"}, {"name": "Northwestern Polytechnical University", "source_name": "Northwestern Polytechnical University", "street_adddress": "\u897f\u5317\u5de5\u4e1a\u5927\u5b66 \u53cb\u8c0a\u6821\u533a, 127\u53f7, \u53cb\u8c0a\u897f\u8def, \u957f\u5b89\u8def, \u7891\u6797\u533a (Beilin), \u897f\u5b89\u5e02, \u9655\u897f\u7701, 710072, \u4e2d\u56fd", "lat": "34.24691520", "lng": "108.91061982", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.07613.pdf"], "doi": []}, {"id": "eff328e0ecfb9a7a2d6664ee38aa32a61c7b9f42", "title": "Visual Question Reasoning on General Dependency Tree", "addresses": [{"name": "Sun Yat-Sen University", "source_name": "Sun Yat-Sen University", "street_adddress": "\u4e2d\u5927, \u65b0\u6e2f\u897f\u8def, \u9f99\u8239\u6ed8, \u5eb7\u4e50, \u6d77\u73e0\u533a (Haizhu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510105, \u4e2d\u56fd", "lat": "23.09461185", "lng": "113.28788994", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.00105.pdf"], "doi": []}, {"id": "6115445ca062b8f865f0b447c059813088b9dd49", "title": "A Dataset and Exploration of Models for Understanding Video Data through Fill-in-the-Blank Question-Answering", "addresses": [{"name": "Polytechnique Montreal", "source_name": "Polytechnique Montr\u00b4eal", "street_adddress": "2900 Boulevard Edouard-Montpetit, Montr\u00e9al, QC H3T 1J4, Canada", "lat": "45.50438400", "lng": "-73.61288290", "type": "edu", "country": "Canada"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1611.07810.pdf"], "doi": []}, {"id": "c8e1c1a82b76d7bfd69c04ab6ab057bb946e262f", "title": "Towards Deep Cellular Phenotyping in Placental Histology", "addresses": [{"name": "University of Oxford", "source_name": "University of Oxford", "street_adddress": "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "lat": "51.75345380", "lng": "-1.25400997", "type": "edu", "country": "United Kingdom"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.03270.pdf"], "doi": []}, {"id": "1be7ecc7100bb5fdbcff7f5f6191a9b57165fa2c", "title": "Deep Learning for Classification of Colorectal Polyps on Whole-slide Images", "addresses": [{"name": "Dartmouth College", "source_name": "Dartmouth College", "street_adddress": "Dartmouth College, Tuck Mall, Hanover, Grafton County, New Hampshire, 03755, USA", "lat": "43.70479270", "lng": "-72.29259090", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.01550.pdf"], "doi": []}, {"id": "290941887c37547462285152ff82796ad71dd757", "title": "Snuba: Automating Weak Supervision to Label Training Data", "addresses": [{"name": "Stanford University", "source_name": "Stanford University", "street_adddress": "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/df8d/c49f33ac02e2f87aac8343869b2affaf4808.pdf"], "doi": []}, {"id": "71de9b3b8f482863d544da0f26ac2876b4fc210a", "title": "Who Are Raising Their Hands ? Hand-Raiser Seeking Based on Object Detection and Pose Estimation", "addresses": [{"name": "Shanghai Jiao Tong University", "source_name": "Shanghai Jiao Tong University", "street_adddress": "\u4e0a\u6d77\u4ea4\u901a\u5927\u5b66\uff08\u5f90\u6c47\u6821\u533a\uff09, \u6dee\u6d77\u897f\u8def, \u756a\u79ba\u5c0f\u533a, \u5e73\u9634\u6865, \u5f90\u6c47\u533a, \u4e0a\u6d77\u5e02, 200052, \u4e2d\u56fd", "lat": "31.20081505", "lng": "121.42840681", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/71de/9b3b8f482863d544da0f26ac2876b4fc210a.pdf"], "doi": []}, {"id": "cb3e91a4c800c60c3f734dd77a64ced7d81e570e", "title": "Grounded Objects and Interactions for Video Captioning", "addresses": [{"name": "Georgia Institute of Technology", "source_name": "Georgia Institute of Technology", "street_adddress": "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1711.06354.pdf"], "doi": []}, {"id": "4e83df2bf849eb6af24bf919ddc7bb25c7249c39", "title": "Fusion that matters: convolutional fusion networks for visual recognition", "addresses": [{"name": "Leiden University", "source_name": "Leiden University, Leiden, The Netherlands", "street_adddress": "Rapenburg 70, 2311 EZ Leiden, Netherlands", "lat": "52.15714850", "lng": "4.48520900", "type": "edu", "country": "Netherlands"}], "year": "2018", "pdf": [], "doi": ["http://doi.org/10.1007/s11042-018-5691-4"]}, {"id": "0e36ada8cb9c91f07c9dcaf196d036564e117536", "title": "Much Ado About Time: Exhaustive Annotation of Temporal Data", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}, {"name": "INRIA", "source_name": "INRIA Grenoble Rhone-Alpes, Grenoble, France", "street_adddress": "655 Avenue de l'Europe, 38330 Montbonnot-Saint-Martin, France", "lat": "45.21788600", "lng": "5.80736900", "type": "edu", "country": "France"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1607.07429.pdf"], "doi": []}, {"id": "d68a6bf394f8f6440426a84d8494e83d08aa1535", "title": "Automatic Portrait Segmentation for Image Stylization", "addresses": [{"name": "Chinese University of Hong Kong", "source_name": "Chinese University of Hong Kong", "street_adddress": "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "lat": "22.41626320", "lng": "114.21093180", "type": "edu", "country": "China"}], "year": "2016", "pdf": ["http://xiaoyongshen.me/webpage_portrait/papers/portrait_eg16.pdf"], "doi": ["https://doi.org/10.1111/cgf.12814"]}, {"id": "db640eddc51258cf6b11e442745d9a4bd5d6995b", "title": "Simple Baselines for Human Pose Estimation and Tracking", "addresses": [{"name": "Microsoft Research Asia", "source_name": "Microsoft Research Asia", "street_adddress": "1 Memorial Dr, Cambridge, MA 02142, USA", "lat": "42.36142560", "lng": "-71.08120920", "type": "company", "country": "United States"}, {"name": "University of Electronic Science and Technology of China", "source_name": "University of Electronic Science and Technology of China", "street_adddress": "2 Jianshe North Rd 2nd Section, Jianshe Road, Chenghua Qu, Chengdu Shi, Sichuan Sheng, China, 610054", "lat": "30.67272100", "lng": "104.09880600", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.06208.pdf"], "doi": []}, {"id": "e1f041594fa37d407c80b28a13680a9ddc081c49", "title": "Euphrates: Algorithm-SoC Co-Design for Low-Power Mobile Continuous Vision", "addresses": [{"name": "University of Rochester", "source_name": "University of Rochester", "street_adddress": "Memorial Art Gallery, 500, University Avenue, East End, Rochester, Monroe County, New York, 14607, USA", "lat": "43.15769690", "lng": "-77.58829158", "type": "edu", "country": "United States"}, {"name": "Georgia Institute of Technology", "source_name": "Georgia Institute of Technology", "street_adddress": "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.11232.pdf"], "doi": []}, {"id": "bb1dc1e9e9c20d99b55f37b9e635457af86a065f", "title": "Neural Ctrl-F: Segmentation-Free Query-by-String Word Spotting in Handwritten Manuscript Collections", "addresses": [{"name": "Uppsala University", "source_name": "Uppsala University, Uppsala, Sweden", "street_adddress": "Uppsala, 752 36 Uppsala, Sweden", "lat": "59.85090050", "lng": "17.63000930", "type": "edu", "country": "Sweden"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.07645.pdf"], "doi": []}, {"id": "7902309d3c5ab2e1e3a1f08503dc39108e1639dc", "title": "Look into Person: Joint Body Parsing & Pose Estimation Network and A New Benchmark", "addresses": [{"name": "Adobe", "source_name": "Adobe2", "street_adddress": "345 Park Ave, San Jose, CA 95110, USA", "lat": "37.33077030", "lng": "-121.89409510", "type": "company", "country": "United States"}, {"name": "Sun Yat-Sen University", "source_name": "Sun Yat-Sen University", "street_adddress": "\u4e2d\u5927, \u65b0\u6e2f\u897f\u8def, \u9f99\u8239\u6ed8, \u5eb7\u4e50, \u6d77\u73e0\u533a (Haizhu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510105, \u4e2d\u56fd", "lat": "23.09461185", "lng": "113.28788994", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.01984.pdf"], "doi": []}, {"id": "211fe99400bde5116efea3b42719d00a34931dcd", "title": "Multimodal Differential Network for Visual Question Generation", "addresses": [{"name": "Indian Institute of Technology Delhi", "source_name": "IIIT-Delhi, India", "street_adddress": "IIIT-Delhi, Mathura Road, Friends Colony, South East Delhi, Delhi, 110020, India", "lat": "28.54632595", "lng": "77.27325504", "type": "edu", "country": "India"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.03986.pdf"], "doi": []}, {"id": "50ab5859994c76dd69f2ef6c770888408d9ae5d0", "title": "Intention Oriented Image Captions with Guiding Objects", "addresses": [{"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.07662.pdf"], "doi": []}, {"id": "fbe3ba628fa8435bf1ad4ed153c93109624b8dff", "title": "Understanding the Message of Images with Knowledge Base Traversals", "addresses": [{"name": "University of Mannheim", "source_name": "University of Mannheim, Mannheim, Germany", "street_adddress": "68131 Mannheim, Germany", "lat": "49.48371060", "lng": "8.46223330", "type": "edu", "country": "Germany"}], "year": "2016", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=2970414"]}, {"id": "857fb344977e5181bf5a99593ceba09a158d412c", "title": "VCI 2 R at the NTCIR-13 Lifelog-2 Lifelog Semantic Access Task", "addresses": [{"name": "A*STAR", "source_name": "I2R, A*STAR, Singapore", "street_adddress": "1 Fusionopolis Way, #21-01 Connexis, Singapore 138632", "lat": "1.29889260", "lng": "103.78731070", "type": "edu", "country": "Singapore"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/857f/b344977e5181bf5a99593ceba09a158d412c.pdf"], "doi": []}, {"id": "a799babbbd56a047feee85d09e57e2c240c5f50c", "title": "Image describing based on bidirectional LSTM and improved sequence sampling", "addresses": [{"name": "Chongqing University", "source_name": "Chongqing University", "street_adddress": "\u91cd\u5e86\u5de5\u5546\u5927\u5b66, 19, \u7fe0\u6797\u8def, \u91cd\u5e86\u5e02, \u91cd\u5e86\u5e02\u4e2d\u5fc3, \u5357\u5cb8\u533a (Nan'an), \u91cd\u5e86\u5e02, 400067, \u4e2d\u56fd", "lat": "29.50841740", "lng": "106.57858552", "type": "edu", "country": "China"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8078733"]}, {"id": "d4ea0438b6c0479a7d7611130a0dc242a22f93eb", "title": "Pose2Instance: Harnessing Keypoints for Person Instance Segmentation", "addresses": [{"name": "UC San Diego", "source_name": "UC San Diego", "street_adddress": "9500 Gilman Dr, La Jolla, CA 92093, USA", "lat": "32.88006040", "lng": "-117.23401350", "type": "edu", "country": "United States"}, {"name": "Google", "source_name": "Google, Inc.", "street_adddress": "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "lat": "37.42199990", "lng": "-122.08405750", "type": "company", "country": "United States"}, {"name": "Cornell University", "source_name": "Cornell University", "street_adddress": "Cornell University, Forest Home Drive, Forest Home, Tompkins County, New York, 14853, USA", "lat": "42.45055070", "lng": "-76.47835130", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.01152.pdf"], "doi": []}, {"id": "66652367a369d18e1845dd14220dc94a9748c9fd", "title": "Learning Spatial Regularization with Image-Level Supervisions for Multi-label Image Classification", "addresses": [{"name": "Chinese University of Hong Kong", "source_name": "Chinese University of Hong Kong", "street_adddress": "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "lat": "22.41626320", "lng": "114.21093180", "type": "edu", "country": "China"}, {"name": "University of Science and Technology of China", "source_name": "University of Science and Technology of China", "street_adddress": "\u4e2d\u56fd\u79d1\u5b66\u6280\u672f\u5927\u5b66 \u4e1c\u6821\u533a, 96\u53f7, \u91d1\u5be8\u8def, \u6c5f\u6dee\u5316\u80a5\u5382\u5c0f\u533a, \u829c\u6e56\u8def\u8857\u9053, \u5408\u80a5\u5e02\u533a, \u5408\u80a5\u5e02, \u5b89\u5fbd\u7701, 230026, \u4e2d\u56fd", "lat": "31.83907195", "lng": "117.26420748", "type": "edu", "country": "China"}, {"name": "University of Sydney", "source_name": "University of Sydney", "street_adddress": "USyd, Fisher Road, Camperdown, Sydney, NSW, 2006, Australia", "lat": "-33.88890695", "lng": "151.18943366", "type": "edu", "country": "Australia"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1702.05891.pdf"], "doi": []}, {"id": "6f44303f9664a4ceabd0f4bc74cb3886aad5012f", "title": "An Integral Pose Regression System for the ECCV2018 PoseTrack Challenge", "addresses": [{"name": "Microsoft", "source_name": "Microsoft Corporation, Redmond, WA, USA", "street_adddress": "One Microsoft Way, Redmond, WA 98052, USA", "lat": "47.64233180", "lng": "-122.13693020", "type": "company", "country": "United States"}, {"name": "Zhejiang University", "source_name": "Zhejiang University", "street_adddress": "\u6d59\u6c5f\u5927\u5b66\u4e4b\u6c5f\u6821\u533a, \u4e4b\u6c5f\u8def, \u8f6c\u5858\u8857\u9053, \u897f\u6e56\u533a (Xihu), \u676d\u5dde\u5e02 Hangzhou, \u6d59\u6c5f\u7701, 310008, \u4e2d\u56fd", "lat": "30.19331415", "lng": "120.11930822", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.06079.pdf"], "doi": []}, {"id": "d2796a0d1ba7ed9287a9db6f4714585b8508871f", "title": "Human Centred Object Co-Segmentation", "addresses": [{"name": "Cornell University", "source_name": "Cornell University", "street_adddress": "Cornell University, Forest Home Drive, Forest Home, Tompkins County, New York, 14853, USA", "lat": "42.45055070", "lng": "-76.47835130", "type": "edu", "country": "United States"}, {"name": "Stanford University", "source_name": "Stanford University", "street_adddress": "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1606.03774.pdf"], "doi": []}, {"id": "68d96226fb71daad7d1a4ccbda267062244d9bc0", "title": "Aligning Books and Movies: Towards Story-Like Visual Explanations by Watching Movies and Reading Books", "addresses": [{"name": "University of Toronto", "source_name": "University of Toronto", "street_adddress": "University of Toronto, St. George Street, Bloor Street Culture Corridor, Old Toronto, Toronto, Ontario, M5S 1A5, Canada", "lat": "43.66333345", "lng": "-79.39769975", "type": "edu", "country": "Canada"}, {"name": "MIT", "source_name": "Massachusetts Institute", "street_adddress": "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1506.06724.pdf"], "doi": []}, {"id": "f9e3bef2ffec5bd1e62003a3f1d8f735265b4d2f", "title": "ReDMark: Framework for Residual Diffusion Watermarking on Deep Networks", "addresses": [{"name": "University of Michigan", "source_name": "University of Michigan", "street_adddress": "University of Michigan, 500, Hayward Street, Ann Arbor, Washtenaw County, Michigan, 48109, USA", "lat": "42.29421420", "lng": "-83.71003894", "type": "edu", "country": "United States"}, {"name": "University of Queensland", "source_name": "University of Queensland", "street_adddress": "University of Queensland, University Drive, Hill End, St Lucia, Brisbane, QLD, 4072, Australia", "lat": "-27.49741805", "lng": "153.01316956", "type": "edu", "country": "Australia"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.07248.pdf"], "doi": []}, {"id": "5a546cd0e8622b32cfdfd0358041f7d7ab00b5d4", "title": "SuperNeurons: FFT-based Gradient Sparsification in the Distributed Training of Deep Neural Networks", "addresses": [{"name": "Brown University", "source_name": "Brown University", "street_adddress": "Brown University, Waterman Street, College Hill, Providence, Bristol, Rhode Island, 02912, USA", "lat": "41.82686820", "lng": "-71.40123146", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.08596.pdf"], "doi": []}, {"id": "e0ffda149d1d81fff507953377e08cf4f718d8ae", "title": "Image Captioning with both Object and Scene Information", "addresses": [{"name": "Chinese Academy of Sciences", "source_name": "Chinese Academy of Sciences", "street_adddress": "\u4e2d\u56fd\u79d1\u5b66\u9662\u5fc3\u7406\u7814\u7a76\u6240, 16, \u6797\u8403\u8def, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100101, \u4e2d\u56fd", "lat": "40.00447950", "lng": "116.37023800", "type": "edu", "country": "China"}], "year": "2016", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=2984069"]}, {"id": "ee53c9480132fc0d09b1192226cb2c460462fd6d", "title": "Channel Pruning for Accelerating Very Deep Neural Networks", "addresses": [{"name": "Xi\u2019an Jiaotong University", "source_name": "Institute of Information and System Sciences, Faculty of Mathematics and Statistics, Xi\u2019an Jiaotong University, Xi\u2019an, China", "street_adddress": "28 Xianning W Rd, JiaoDa ShangYe JieQu, Beilin Qu, Xian Shi, Shaanxi Sheng, China", "lat": "34.25080300", "lng": "108.98369300", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.06168.pdf"], "doi": []}, {"id": "2453dd38cde21f3248b55d281405f11d58168fa9", "title": "Multi-scale Patch Aggregation (MPA) for Simultaneous Detection and Segmentation", "addresses": [{"name": "Chinese University of Hong Kong", "source_name": "Chinese University of Hong Kong", "street_adddress": "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "lat": "22.41626320", "lng": "114.21093180", "type": "edu", "country": "China"}], "year": "2016", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2016/papers/Liu_Multi-Scale_Patch_Aggregation_CVPR_2016_paper.pdf", "http://www.cse.cuhk.edu.hk/~leojia/papers/mpa_cvpr16.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Liu_Multi-Scale_Patch_Aggregation_CVPR_2016_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780711", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.342", "http://doi.org/10.1109/CVPR.2016.342"]}, {"id": "0abd1a332717f540f1e3297a9eedd9633ad9c3a9", "title": "From UI Design Image to GUI Skeleton: A Neural Machine Translator to Bootstrap Mobile GUI Implementation", "addresses": [{"name": "Australian National University", "source_name": "Australian National University", "street_adddress": "Canberra ACT 0200, Australia", "lat": "-35.27769990", "lng": "149.11852700", "type": "edu", "country": "Australia"}, {"name": "Nanyang Technological University", "source_name": "Nanyang Technological University", "street_adddress": "NTU, Faculty Avenue, Jurong West, Southwest, 637460, Singapore", "lat": "1.34841040", "lng": "103.68297965", "type": "edu", "country": "Singapore"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3180240"]}, {"id": "51a03fe7cbcf5c650b5dbdba0bf14be8a45cbaee", "title": "Deep Triplet Quantization", "addresses": [{"name": "Microsoft Research Asia", "source_name": "Microsoft Research Asia", "street_adddress": "1 Memorial Dr, Cambridge, MA 02142, USA", "lat": "42.36142560", "lng": "-71.08120920", "type": "company", "country": "United States"}, {"name": "Tsinghua University & Beijing National Research Center for Information Science and Technology", "source_name": "Tsinghua University & Beijing National Research Center for Information Science and Technology, Beijing, China", "street_adddress": "30 Shuangqing Rd, Haidian Qu, Beijing Shi, China", "lat": "39.99966740", "lng": "116.32644390", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3240516"]}, {"id": "85a65932f30b05532e259a99bd6a179af20ab267", "title": "HashNet: Deep Learning to Hash by Continuation", "addresses": [{"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}, {"name": "University of Illinois at Chicago", "source_name": "University of Illinois at Chicago", "street_adddress": "University of Illinois at Chicago, West Taylor Street, Greektown, Chicago, Cook County, Illinois, 60607, USA", "lat": "41.86898915", "lng": "-87.64856256", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1702.00758.pdf"], "doi": []}, {"id": "1ed5c62eec52380c285daf2ffa7576d96e4ac150", "title": "Modeling Image Virality with Pairwise Spatial Transformer Networks", "addresses": [{"name": "MIT", "source_name": "Massachusetts Institute", "street_adddress": "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu", "country": "United States"}, {"name": "Indian Institute of Technology Delhi", "source_name": "IIIT-Delhi, India", "street_adddress": "IIIT-Delhi, Mathura Road, Friends Colony, South East Delhi, Delhi, 110020, India", "lat": "28.54632595", "lng": "77.27325504", "type": "edu", "country": "India"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1709.07914.pdf"], "doi": []}, {"id": "6f1c84d5a137ad14e5de9a8728fced8044d05b79", "title": "SketchyScene: Richly-Annotated Scene Sketches", "addresses": [{"name": "University of Maryland", "source_name": "University of Maryland", "street_adddress": "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu", "country": "United States"}, {"name": "Queen Mary University of London", "source_name": "Queen Mary University of London", "street_adddress": "Queen Mary (University of London), Mile End Road, Globe Town, Mile End, London Borough of Tower Hamlets, London, Greater London, England, E1 4NS, UK", "lat": "51.52472720", "lng": "-0.03931035", "type": "edu", "country": "United Kingdom"}, {"name": "Sun Yat-Sen University", "source_name": "Sun Yat-Sen University", "street_adddress": "\u4e2d\u5927, \u65b0\u6e2f\u897f\u8def, \u9f99\u8239\u6ed8, \u5eb7\u4e50, \u6d77\u73e0\u533a (Haizhu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510105, \u4e2d\u56fd", "lat": "23.09461185", "lng": "113.28788994", "type": "edu", "country": "China"}, {"name": "Shandong University", "source_name": "Shandong University", "street_adddress": "\u5c71\u4e1c\u5927\u5b66, \u6cf0\u5b89\u8857, \u9ccc\u5c71\u536b\u8857\u9053, \u5373\u58a8\u533a, \u9752\u5c9b\u5e02, \u5c71\u4e1c\u7701, 266200, \u4e2d\u56fd", "lat": "36.36934730", "lng": "120.67381800", "type": "edu", "country": "China"}, {"name": "Simon Fraser University", "source_name": "Simon Fraser University", "street_adddress": "SFU Burnaby, South Campus Road, Barnet, Burnaby, Metro Vancouver, British Columbia, V5A 4X6, Canada", "lat": "49.27674540", "lng": "-122.91777375", "type": "edu", "country": "Canada"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.02473.pdf"], "doi": []}, {"id": "e8cda2c754670850ec722799640c6cb42dfb8199", "title": "4D Generic Video Object Proposals", "addresses": [{"name": "RWTH Aachen University", "source_name": "RWTH Aachen University", "street_adddress": "RWTH Aachen, Mies-van-der-Rohe-Stra\u00dfe, K\u00f6nigsh\u00fcgel, Aachen-Mitte, Aachen, St\u00e4dteregion Aachen, Regierungsbezirk K\u00f6ln, Nordrhein-Westfalen, 52074, Deutschland", "lat": "50.77917030", "lng": "6.06728733", "type": "edu", "country": "Germany"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.09260.pdf"], "doi": []}, {"id": "5abc8b9ac261f320cae1ce6676a3f05038b93436", "title": "Mixed Supervised Object Detection with Robust Objectness Transfer", "addresses": [{"name": "National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China", "source_name": "National Laboratory of Pattern Recognition (NLPR) of Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China", "street_adddress": "China, Beijing, Haidian, \u4e2d\u5173\u6751\u4e1c\u8def95\u53f7", "lat": "39.97920300", "lng": "116.33287000", "type": "edu", "country": "China"}, {"name": "University of Dundee", "source_name": "University of Dundee", "street_adddress": "University of Dundee, Park Wynd, Law, Dundee, Dundee City, Scotland, DD1 4HN, UK", "lat": "56.45796755", "lng": "-2.98214831", "type": "edu", "country": "United Kingdom"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8304628"]}, {"id": "645f09f4bc2e6a13663564ee9032ca16e35fc52d", "title": "Interactive Demonstration of Probabilistic Predicates", "addresses": [{"name": "Microsoft", "source_name": "Microsoft Corporation, Redmond, WA, USA", "street_adddress": "One Microsoft Way, Redmond, WA 98052, USA", "lat": "47.64233180", "lng": "-122.13693020", "type": "company", "country": "United States"}, {"name": "University of Washington", "source_name": "University of Washington", "street_adddress": "University of Washington, Rainier Vista, Montlake, University District, Seattle, King County, Washington, 98195, USA", "lat": "47.65432380", "lng": "-122.30800894", "type": "edu", "country": "United States"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3193542"]}, {"id": "397085122a5cade71ef6c19f657c609f0a4f7473", "title": "Using Segmentation to Predict the Absence of Occluded Parts", "addresses": [{"name": "UC Irvine", "source_name": "UC Irvine", "street_adddress": "Irvine, CA 92697, USA", "lat": "33.64049520", "lng": "-117.84429620", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/db11/4901d09a07ab66bffa6986bc81303e133ae1.pdf"], "doi": []}, {"id": "60ac4be07ab4b20e1b9d0879e9553f05ec581867", "title": "LabelBank: Revisiting Global Perspectives for Semantic Segmentation", "addresses": [{"name": "University of Southern California", "source_name": "University of Southern California", "street_adddress": "University of Southern California, Watt Way, Saint James Park, LA, Los Angeles County, California, 90089, USA", "lat": "34.02241490", "lng": "-118.28634407", "type": "edu", "country": "United States"}, {"name": "Simon Fraser University", "source_name": "Simon Fraser University", "street_adddress": "SFU Burnaby, South Campus Road, Barnet, Burnaby, Metro Vancouver, British Columbia, V5A 4X6, Canada", "lat": "49.27674540", "lng": "-122.91777375", "type": "edu", "country": "Canada"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.09891.pdf"], "doi": []}, {"id": "0c2cb193274217855000c98a02488885571b55bc", "title": "TrackNet: Simultaneous Object Detection and Tracking and Its Application in Traffic Video Analysis", "addresses": [{"name": "New York University", "source_name": "New York University", "street_adddress": "NYU, West 4th Street, NoHo Historic District, NoHo, Manhattan, Manhattan Community Board 2, New York County, NYC, New York, 10012, USA", "lat": "40.72925325", "lng": "-73.99625394", "type": "edu", "country": "United States"}, {"name": "Chongqing University of Technology", "source_name": "Chongqing University of Technology, China", "street_adddress": "69 Hongguang Ave, Banan Qu, Chongqing Shi, China", "lat": "29.45832600", "lng": "106.52994700", "type": "edu", "country": "China"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1902.01466.pdf"], "doi": []}, {"id": "a98b63516c7d45eadf8cf4045ea114918eb3b636", "title": "Selective Refinement Network for High Performance Face Detection", "addresses": [{"name": "Chinese Academy of Sciences", "source_name": "Chinese Academy of Sciences", "street_adddress": "\u4e2d\u56fd\u79d1\u5b66\u9662\u5fc3\u7406\u7814\u7a76\u6240, 16, \u6797\u8403\u8def, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100101, \u4e2d\u56fd", "lat": "40.00447950", "lng": "116.37023800", "type": "edu", "country": "China"}, {"name": "University of Chinese Academy of Sciences", "source_name": "University of Chinese Academy of Sciences", "street_adddress": "University of Chinese Academy of Sciences, UCAS, Yuquanlu, \u7389\u6cc9\u8def, \u7530\u6751, \u6d77\u6dc0\u533a, 100049, \u4e2d\u56fd", "lat": "39.90828040", "lng": "116.24585270", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.02693.pdf"], "doi": []}, {"id": "6a9c3011b5092daa1d0cacda23f20ca4ae74b902", "title": "Fast and Accurate Person Re-Identification with RMNet.", "addresses": [{"name": "Intel", "source_name": "Intel Corp., 4600 S. Dobson Road, Chandler, AZ 85248", "street_adddress": "4500 S Dobson Rd, Chandler, AZ 85248, USA", "lat": "33.24160080", "lng": "-111.88390830", "type": "company", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.02465.pdf"], "doi": []}, {"id": "3361905a9ff903142e50d5b608f4775f1c5bac1a", "title": "Pathologist-level classification of histologic patterns on resected lung adenocarcinoma slides with deep neural networks", "addresses": [{"name": "Dartmouth College", "source_name": "Dartmouth College", "street_adddress": "Dartmouth College, Tuck Mall, Hanover, Grafton County, New Hampshire, 03755, USA", "lat": "43.70479270", "lng": "-72.29259090", "type": "edu", "country": "United States"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.11489.pdf"], "doi": []}, {"id": "02a5b7a41ffa8518eb3b7cae9914a2bd2bbc886b", "title": "Fast Online Object Tracking and Segmentation: A Unifying Approach", "addresses": [{"name": "University of Oxford", "source_name": "University of Oxford", "street_adddress": "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "lat": "51.75345380", "lng": "-1.25400997", "type": "edu", "country": "United Kingdom"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.05050.pdf"], "doi": []}, {"id": "7e163ae363b62b708566f348da87750284860822", "title": "Weakly-Supervised Spatial Context Networks", "addresses": [{"name": "University of Maryland", "source_name": "University of Maryland", "street_adddress": "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu", "country": "United States"}, {"name": "University of British Columbia", "source_name": "University of British Columbia", "street_adddress": "University of British Columbia, Eagles Drive, Hawthorn Place, University Endowment Lands, Metro Vancouver, British Columbia, V6T, Canada", "lat": "49.25839375", "lng": "-123.24658161", "type": "edu", "country": "Canada"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.02998.pdf"], "doi": []}, {"id": "e4d4346bd415c6fa9187c16a9b7f5c69f48f1ec4", "title": "Towards High Performance Video Object Detection for Mobiles", "addresses": [{"name": "Microsoft Research Asia", "source_name": "Microsoft Research Asia", "street_adddress": "1 Memorial Dr, Cambridge, MA 02142, USA", "lat": "42.36142560", "lng": "-71.08120920", "type": "company", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.05830.pdf"], "doi": []}, {"id": "0ec03a13063e5811ec9461cf7af04f4f3110ccaa", "title": "Visual Question Answering with Question Representation Update (QRU)", "addresses": [{"name": "Chinese University of Hong Kong", "source_name": "Chinese University of Hong Kong", "street_adddress": "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "lat": "22.41626320", "lng": "114.21093180", "type": "edu", "country": "China"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/2695/46925f0fd457b31c13c2870343b0aed761dc.pdf"], "doi": []}, {"id": "0f1c436aa7b1194e8660f7352315497c38ade853", "title": "GANtruth - an unpaired image-to-image translation method for driving scenarios", "addresses": [{"name": "KTH Royal Institute of Technology, Stockholm", "source_name": "KTH   Royal Institute of Technology, Stockholm", "street_adddress": "KTH, Teknikringen, L\u00e4rkstaden, Norra Djurg\u00e5rden, \u00d6stermalms stadsdelsomr\u00e5de, Sthlm, Stockholm, Stockholms l\u00e4n, Svealand, 114 28, Sverige", "lat": "59.34986645", "lng": "18.07063213", "type": "edu", "country": "Sweden"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.01710.pdf"], "doi": []}, {"id": "be22647956f1bc8cf6f936ae3c85f5637492b6b8", "title": "Ambiguity Helps: Classification with Disagreements in Crowdsourced Annotations", "addresses": [{"name": "Harvard University", "source_name": "Harvard University", "street_adddress": "Harvard University, Soldiers Field Road, Allston, Boston, Suffolk County, Massachusetts, 02163, USA", "lat": "42.36782045", "lng": "-71.12666653", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2016/supplemental/Sharmanska_Ambiguity_Helps_Classification_2016_CVPR_supplemental.pdf", "http://sro.sussex.ac.uk/60510/1/Sharmanska_Ambiguity_Helps_Classification_CVPR_2016_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780610", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.241", "http://doi.org/10.1109/CVPR.2016.241"]}, {"id": "fa5ab04ebf64de3bd57bd0729ce9ca3440258acc", "title": "Unprecedented Usage of Pre-trained CNNs on Beauty Product", "addresses": [{"name": "University of Malaya, Kuala Lumpur", "source_name": "University of Malaya", "street_adddress": "UM, Lingkaran Wawasan, Bukit Pantai, Bangsar, KL, 50603, Malaysia", "lat": "3.12267405", "lng": "101.65356103", "type": "edu", "country": "Malaysia"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3266433"]}, {"id": "9c2e5e2ba7c5b3a555c6c72f518e3631aab23c19", "title": "RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation", "addresses": [{"name": "University of Adelaide", "source_name": "University of Adelaide", "street_adddress": "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu", "country": "Australia"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1611.06612.pdf"], "doi": []}, {"id": "1daaeae28270b06962eb6fcf812a368892b5dff4", "title": "Modeling Visual Context Is Key to Augmenting Object Detection Datasets", "addresses": [{"name": "INRIA", "source_name": "INRIA Grenoble Rhone-Alpes, Grenoble, France", "street_adddress": "655 Avenue de l'Europe, 38330 Montbonnot-Saint-Martin, France", "lat": "45.21788600", "lng": "5.80736900", "type": "edu", "country": "France"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.07428.pdf"], "doi": []}, {"id": "3fb4bf38d34f7f7e5b3df36de2413d34da3e174a", "title": "Persuasive Faces: Generating Faces in Advertisements", "addresses": [{"name": "University of Pittsburgh", "source_name": "University of Pittsburgh", "street_adddress": "University of Pittsburgh, Sutherland Drive, West Oakland, PGH, Allegheny County, Pennsylvania, 15240, USA", "lat": "40.44415295", "lng": "-79.96243993", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.09882.pdf"], "doi": []}, {"id": "41aa209e9d294d370357434f310d49b2b0baebeb", "title": "Beyond caption to narrative: Video captioning with multiple sentences", "addresses": [{"name": "University of Tokyo", "source_name": "University of Tokyo", "street_adddress": "\u6771\u4eac\u5927\u5b66 \u67cf\u30ad\u30e3\u30f3\u30d1\u30b9, \u5b66\u878d\u5408\u306e\u9053, \u67cf\u5e02, \u5343\u8449\u770c, \u95a2\u6771\u5730\u65b9, 277-8583, \u65e5\u672c", "lat": "35.90204480", "lng": "139.93622009", "type": "edu", "country": "Japan"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1605.05440.pdf"], "doi": []}, {"id": "21c99706bb26e9012bfb4d8d48009a3d45af59b2", "title": "Neural Module Networks", "addresses": [{"name": "University of California, Berkeley", "source_name": "University of California, Berkeley", "street_adddress": "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "lat": "37.86871260", "lng": "-122.25586815", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1511.02799.pdf"], "doi": []}, {"id": "97ccbe3440e5a574b37753ff49165c7ee97a6eb4", "title": "Efficient Coarse-to-Fine Non-Local Module for the Detection of Small Objects.", "addresses": [{"name": "Weizmann Institute of Science", "source_name": "Weizmann Institute of Science", "street_adddress": "\u05de\u05db\u05d5\u05df \u05d5\u05d9\u05e6\u05de\u05df \u05dc\u05de\u05d3\u05e2, \u05e9\u05d3\u05e8\u05ea \u05de\u05e8\u05db\u05d5\u05e1 \u05d6\u05d9\u05d5, \u05de\u05e2\u05d5\u05e0\u05d5\u05ea \u05e9\u05d9\u05d9\u05df, \u05d0\u05d7\u05d5\u05d6\u05d5\u05ea \u05d4\u05e0\u05e9\u05d9\u05d0, \u05e8\u05d7\u05d5\u05d1\u05d5\u05ea, \u05de\u05d7\u05d5\u05d6 \u05d4\u05de\u05e8\u05db\u05d6, NO, \u05d9\u05e9\u05e8\u05d0\u05dc", "lat": "31.90784990", "lng": "34.81334092", "type": "edu", "country": "Israel"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.12152.pdf"], "doi": []}, {"id": "2a4bf8d096ea9b6a84ebb6cecf98589a76806777", "title": "Evaluation of Segmentation Quality via Adaptive Composition of Reference Segmentations", "addresses": [{"name": "Hong Kong Polytechnic University", "source_name": "Hong Kong Polytechnic University", "street_adddress": "hong kong, 11, \u80b2\u624d\u9053 Yuk Choi Road, \u5c16\u6c99\u5480 Tsim Sha Tsui, \u6cb9\u5c16\u65fa\u5340 Yau Tsim Mong District, \u4e5d\u9f8d Kowloon, HK, 00000, \u4e2d\u56fd", "lat": "22.30457200", "lng": "114.17976285", "type": "edu", "country": "China"}, {"name": "Southwest Jiaotong University", "source_name": "Southwest Jiaotong University", "street_adddress": "\u897f\u5357\u4ea4\u901a\u5927\u5b66 - Xinan Jiaotong University, \u4e8c\u73af\u9ad8\u67b6\u8def, \u6c81\u56ed\u5c0f\u533a, \u91d1\u725b\u533a, \u91d1\u725b\u533a (Jinniu), \u6210\u90fd\u5e02 / Chengdu, \u56db\u5ddd\u7701, 610084, \u4e2d\u56fd", "lat": "30.69784700", "lng": "104.05208110", "type": "edu", "country": "China"}, {"name": "Xi\u2019an Jiaotong University", "source_name": "Institute of Information and System Sciences, Faculty of Mathematics and Statistics, Xi\u2019an Jiaotong University, Xi\u2019an, China", "street_adddress": "28 Xianning W Rd, JiaoDa ShangYe JieQu, Beilin Qu, Xian Shi, Shaanxi Sheng, China", "lat": "34.25080300", "lng": "108.98369300", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["http://faculty.ucmerced.edu/mhyang/papers/pami16_segmentation_evaluation.pdf", "http://faculty.ucmerced.edu/mhyang/papers/pami17_segmentation_evaluation.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7723880", "http://doi.ieeecomputersociety.org/10.1109/TPAMI.2016.2622703", "http://doi.org/10.1109/TPAMI.2016.2622703", "https://www.ncbi.nlm.nih.gov/pubmed/27810800"]}, {"id": "7c4fdcda302b93c0a275420ddd6e249c565173ff", "title": "VISIR: Visual and Semantic Image Label Refinement", "addresses": [{"name": "Max Planck Institute for Informatics", "source_name": "Max Planck Institute for Informatics", "street_adddress": "MPII, E1 4, Campus, Universit\u00e4t, Sankt Johann, Bezirk Mitte, Saarbr\u00fccken, Regionalverband Saarbr\u00fccken, Saarland, 66123, Deutschland", "lat": "49.25795660", "lng": "7.04577417", "type": "edu", "country": "Germany"}, {"name": "University of Warwick", "source_name": "University of Warwick", "street_adddress": "University of Warwick, University Road, Kirby Corner, Cannon Park, Coventry, West Midlands Combined Authority, West Midlands, England, CV4 7AL, UK", "lat": "52.37931310", "lng": "-1.56042520", "type": "edu", "country": "United Kingdom"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3159693"]}, {"id": "a34de6e26cf34257d6c2fdc9a1801aea46c00b08", "title": "Complex Object Classification: A Multi-Modal Multi-Instance Multi-Label Deep Network with Optimal Transport", "addresses": [{"name": "Nanjing University", "source_name": "Nanjing University", "street_adddress": "NJU, \u4e09\u6c5f\u8def, \u9f13\u697c\u533a, \u5357\u4eac\u5e02, \u6c5f\u82cf\u7701, 210093, \u4e2d\u56fd", "lat": "32.05659570", "lng": "118.77408833", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3220012"]}, {"id": "b181ae8ed315ceb8f03332ba02ef0849adbe5b4c", "title": "Multi-modal Capsule Routing for Actor and Action Video Segmentation Conditioned on Natural Language Queries", "addresses": [{"name": "University of Central Florida", "source_name": "University of Central Florida", "street_adddress": "University of Central Florida, Libra Drive, University Park, Orange County, Florida, 32816, USA", "lat": "28.59899755", "lng": "-81.19712501", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.00303.pdf"], "doi": []}, {"id": "a213405441c68a0ce415a4a842bdd6ac62c1667b", "title": "Enhancement of SSD by concatenating feature maps for object detection.", "addresses": [{"name": "Seoul National University", "source_name": "Seoul National University", "street_adddress": "\uc11c\uc6b8\ub300\ud559\uad50, \uc11c\ud638\ub3d9\ub85c, \uc11c\ub454\ub3d9, \uad8c\uc120\uad6c, \uc218\uc6d0\uc2dc, \uacbd\uae30, 16614, \ub300\ud55c\ubbfc\uad6d", "lat": "37.26728000", "lng": "126.98411510", "type": "edu", "country": "South Korea"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.09587.pdf"], "doi": []}, {"id": "0e08cf0b19f0600dadce0f6694420d643ea9828b", "title": "The Middle Child Problem: Revisiting Parametric Min-Cut and Seeds for Object Proposals", "addresses": [{"name": "Georgia Institute of Technology", "source_name": "Georgia Institute of Technology", "street_adddress": "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu", "country": "United States"}, {"name": "Oregon State University", "source_name": "Oregon State University", "street_adddress": "OSU Beaver Store, 538, Southwest 6th Avenue, Portland Downtown, Portland, Multnomah County, Oregon, 97204, USA", "lat": "45.51982890", "lng": "-122.67797964", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["http://openaccess.thecvf.com/content_iccv_2015/papers/Humayun_The_Middle_Child_ICCV_2015_paper.pdf", "http://web.engr.oregonstate.edu/~lif/Middle_Child_ICCV15.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Humayun_The_Middle_Child_ICCV_2015_paper.pdf", "https://smartech.gatech.edu/bitstream/handle/1853/55478/The%20Middle%20Child%20Problem-%20Revisiting%20Parametric%20Min-cut%20and%20Seeds%20for%20Object%20Proposals.pdf?isAllowed=y&sequence=1"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410544", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2015.187", "http://doi.org/10.1109/ICCV.2015.187"]}, {"id": "3e0a1884448bfd7f416c6a45dfcdfc9f2e617268", "title": "Understanding and Controlling User Linkability in Decentralized Learning", "addresses": [{"name": "Max Planck Institute for Informatics", "source_name": "Max Planck Institute for Informatics", "street_adddress": "MPII, E1 4, Campus, Universit\u00e4t, Sankt Johann, Bezirk Mitte, Saarbr\u00fccken, Regionalverband Saarbr\u00fccken, Saarland, 66123, Deutschland", "lat": "49.25795660", "lng": "7.04577417", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.05838.pdf"], "doi": []}, {"id": "5d165ff5b0b389e32809c17838a2afc218a91d62", "title": "Object Detectors Emerge in Deep Scene CNNs", "addresses": [{"name": "MIT", "source_name": "Massachusetts Institute", "street_adddress": "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu", "country": "United States"}], "year": "2014", "pdf": ["https://arxiv.org/pdf/1412.6856.pdf"], "doi": []}, {"id": "dc9b95afcbd972d973f3ae29f05bbc8fa45d6a16", "title": "Learning deep structured network for weakly supervised change detection", "addresses": [{"name": "Australian National University", "source_name": "Australian National University", "street_adddress": "Canberra ACT 0200, Australia", "lat": "-35.27769990", "lng": "149.11852700", "type": "edu", "country": "Australia"}, {"name": "ShanghaiTech University", "source_name": "ShanghaiTech University", "street_adddress": "Yueyang Rd, Xuhui Qu, Shanghai Shi, China", "lat": "31.20254500", "lng": "121.45308600", "type": "edu", "country": "China"}, {"name": "University of Western Australia", "source_name": "University of Western Australia", "street_adddress": "UWA, 35, Underwood Avenue, Daglish, Perth, Western Australia, 6009, Australia", "lat": "-31.95040445", "lng": "115.79790037", "type": "edu", "country": "Australia"}, {"name": "Murdoch University", "source_name": "Murdoch University, Murdoch, WA, Australia", "street_adddress": "90 South St, Murdoch WA 6150, Australia", "lat": "-32.06651350", "lng": "115.83583130", "type": "edu", "country": "Australia"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1606.02009.pdf"], "doi": []}, {"id": "9d62a78b006b09fe8f20eb7cb72e2b542cb5fbad", "title": "ImagineNet : Style Transfer from Fine Art to Graphical User Interfaces", "addresses": [{"name": "Stanford University", "source_name": "Stanford University", "street_adddress": "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/9d62/a78b006b09fe8f20eb7cb72e2b542cb5fbad.pdf"], "doi": []}, {"id": "0ac43cbd4c25994ea2687743c5b666d498831687", "title": "Robust Adversarial Perturbation on Deep Proposal-based Models", "addresses": [{"name": "State University of New York", "source_name": "University at Albany, State University of New York, Albany, USA", "street_adddress": "353 Broadway, Albany, NY 12207, USA", "lat": "42.64805160", "lng": "-73.74957600", "type": "edu", "country": "United States"}, {"name": "GE Global Research Center", "source_name": "GE Global Research Center", "street_adddress": "GE Global Research Center, Aqueduct, Niskayuna, Schenectady County, New York, USA", "lat": "42.82982480", "lng": "-73.87719385", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.05962.pdf"], "doi": []}, {"id": "95f74ce5a69fdcd2abda908724d2ab4977e72100", "title": "Using Syntax to Ground Referring Expressions in Natural Images", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.10547.pdf"], "doi": []}, {"id": "01100c14d0a06376dbb0fae6fe7995f7b3aed8b6", "title": "Active learning for structured probabilistic models with histogram approximation", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}, {"name": "Virginia Tech", "source_name": "Virginia Tech", "street_adddress": "Blacksburg, VA 24061, USA", "lat": "37.22838430", "lng": "-80.42341670", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/2B_030.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/2B_030_ext.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2015/ext/2B_030_ext.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Sun_Active_Learning_for_2015_CVPR_paper.pdf", "https://filebox.ece.vt.edu/~dbatra/papers/slb_cvpr15.pdf", "https://www.cc.gatech.edu/~dbatra/papers/slb_cvpr15.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7298984", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2015.7298984", "http://doi.org/10.1109/CVPR.2015.7298984"]}, {"id": "a1b5b0697e46eecc9657954311828cc9b4113a26", "title": "Semantic Segmentation With Object Clique Potentials", "addresses": [{"name": "Chinese University of Hong Kong", "source_name": "Chinese University of Hong Kong", "street_adddress": "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "lat": "22.41626320", "lng": "114.21093180", "type": "edu", "country": "China"}], "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/fd6c/8c23edc6ce6bc97d44b6c739dcfe81b9dcc4.pdf"], "doi": []}, {"id": "ccd02b5cb6acee7db170c0fb7f4cf0dd64a8499f", "title": "Generation with Recursive Neural Networks", "addresses": [{"name": "Stanford University", "source_name": "Stanford University", "street_adddress": "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/ccd0/2b5cb6acee7db170c0fb7f4cf0dd64a8499f.pdf"], "doi": []}, {"id": "1cc85b17137c4d6d75e4c418976e7dceb3d7559e", "title": "Open Logo Detection Challenge", "addresses": [{"name": "Queen Mary University of London", "source_name": "Queen Mary University of London", "street_adddress": "Queen Mary (University of London), Mile End Road, Globe Town, Mile End, London Borough of Tower Hamlets, London, Greater London, England, E1 4NS, UK", "lat": "51.52472720", "lng": "-0.03931035", "type": "edu", "country": "United Kingdom"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.01964.pdf"], "doi": []}, {"id": "cd7b872365cc5b5114e0ccb833e307e874a5c3aa", "title": "Video Object Segmentation with Language Referring Expressions", "addresses": [{"name": "Max Planck Institute for Informatics", "source_name": "Max Planck Institute for Informatics", "street_adddress": "MPII, E1 4, Campus, Universit\u00e4t, Sankt Johann, Bezirk Mitte, Saarbr\u00fccken, Regionalverband Saarbr\u00fccken, Saarland, 66123, Deutschland", "lat": "49.25795660", "lng": "7.04577417", "type": "edu", "country": "Germany"}, {"name": "University of California, Berkeley", "source_name": "University of California, Berkeley", "street_adddress": "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "lat": "37.86871260", "lng": "-122.25586815", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.08006.pdf"], "doi": []}, {"id": "1c0d70587340adc412c6e2afd71012d563c1e724", "title": "Could we create a training set for image captioning using automatic translation?", "addresses": [{"name": "Bilgisayar M\u00fchendisli\u011fi, Hacettepe \u00dcniversitesi, Ankara, T\u00fcrkiye", "source_name": "Bilgisayar Mühendisliği, Hacettepe Üniversitesi, Ankara, Türkiye", "street_adddress": "\u00dcniversiteler Mh., Hacettepe Beytepe Kamp\u00fcs\u00fc No:21, 06800 \u00c7ankaya/Ankara, Turkey", "lat": "39.87143010", "lng": "32.73636570", "type": "edu", "country": "Turkey"}, {"name": "Bilgisayar M\u00fchendisli\u011fi, Orta Doggu Teknik \u00dcniversitesi, Ankara, T\u00fcrkiye", "source_name": "Bilgisayar Mühendisliği, Orta Doggu Teknik Üniversitesi, Ankara, Türkiye", "street_adddress": "\u00dcniversiteler Mh., 06800 \u00c7ankaya/Ankara, Turkey", "lat": "39.89183900", "lng": "32.78334710", "type": "edu", "country": "Poland"}], "year": "2017", "pdf": ["http://users.metu.edu.tr/snermin/papers/siu2017.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7960638", "http://doi.org/10.1109/SIU.2017.7960638"]}, {"id": "e0821e6bb9efb795b4593229e4eacd6d86cef7d9", "title": "Weakly and Semi Supervised Human Body Part Parsing via Pose-Guided Knowledge Transfer", "addresses": [{"name": "Shanghai Jiao Tong University", "source_name": "Shanghai Jiao Tong University", "street_adddress": "\u4e0a\u6d77\u4ea4\u901a\u5927\u5b66\uff08\u5f90\u6c47\u6821\u533a\uff09, \u6dee\u6d77\u897f\u8def, \u756a\u79ba\u5c0f\u533a, \u5e73\u9634\u6865, \u5f90\u6c47\u533a, \u4e0a\u6d77\u5e02, 200052, \u4e2d\u56fd", "lat": "31.20081505", "lng": "121.42840681", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.04310.pdf"], "doi": []}, {"id": "081307db6d8d709af26f49d24041086bb09abfd1", "title": "A general description generator for human activity images based on deep understanding framework", "addresses": [{"name": "Beijing Institute of Technology", "source_name": "Beijing Institute of Technology University", "street_adddress": "\u5317\u4eac\u7406\u5de5\u5927\u5b66, 5, \u4e2d\u5173\u6751\u5357\u5927\u8857, \u4e2d\u5173\u6751, \u7a3b\u9999\u56ed\u5357\u793e\u533a, \u6d77\u6dc0\u533a, \u5317\u4eac\u5e02, 100872, \u4e2d\u56fd", "lat": "39.95866520", "lng": "116.30971281", "type": "edu", "country": "China"}, {"name": "Guangxi University", "source_name": "Electronics and Information, Guangxi University", "street_adddress": "Chongwen Rd, Xixiangtang Qu, Nanning Shi, Guangxi Zhuangzuzizhiqu, China, 530001", "lat": "22.83760000", "lng": "108.28983900", "type": "edu", "country": "China"}], "year": "2015", "pdf": [], "doi": ["http://doi.org/10.1007/s00521-015-2171-x"]}, {"id": "3b08ef7aa0cf9528da42b2b594b66e4a6f7fdb7f", "title": "Active Learning for Delineation of Curvilinear Structures", "addresses": [{"name": "University of Bern", "source_name": "University of Bern, Neubr\u00fcckstrasse 10, Bern, Switzerland", "street_adddress": "Hochschulstrasse 6, 3012 Bern, Switzerland", "lat": "46.95048960", "lng": "7.43811900", "type": "edu", "country": "Switzerland"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1512.00747.pdf"], "doi": []}, {"id": "0e5d673111e398f6c083623e31c2f498f0bf7b5f", "title": "Resolving References to Objects in Photographs using the Words-As-Classifiers Model", "addresses": [{"name": "Bielefeld University", "source_name": "Bielefeld University", "street_adddress": "Fachhochschule Bielefeld FB Gestaltung, 3, Lampingstra\u00dfe, Mitte, Bielefeld, Regierungsbezirk Detmold, Nordrhein-Westfalen, 33615, Deutschland", "lat": "52.02804210", "lng": "8.51148270", "type": "edu", "country": "Germany"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1510.02125.pdf"], "doi": []}, {"id": "0910a4c470a410fac446f4026f7c8ef512ae7427", "title": "Hierarchical Question-Image Co-Attention for Visual Question Answering", "addresses": [{"name": "Virginia Tech", "source_name": "Virginia Tech", "street_adddress": "Blacksburg, VA 24061, USA", "lat": "37.22838430", "lng": "-80.42341670", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1606.00061.pdf"], "doi": []}, {"id": "431140620ecf6cbb7c4118a65f7f2b8f48089647", "title": "Segment-Phrase Table for Semantic Segmentation, Visual Entailment and Paraphrasing", "addresses": [{"name": "University of Washington", "source_name": "University of Washington", "street_adddress": "University of Washington, Rainier Vista, Montlake, University District, Seattle, King County, Washington, 98195, USA", "lat": "47.65432380", "lng": "-122.30800894", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1509.08075.pdf"], "doi": []}, {"id": "8481d4160bf5a9c760b5c4de60c82f102492317b", "title": "Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation", "addresses": [{"name": "Johns Hopkins University", "source_name": "Johns Hopkins University", "street_adddress": "Baltimore, MD 21218, USA", "lat": "39.32990130", "lng": "-76.62051770", "type": "edu", "country": "United States"}, {"name": "Google", "source_name": "Google, Inc.", "street_adddress": "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "lat": "37.42199990", "lng": "-122.08405750", "type": "company", "country": "United States"}, {"name": "Stanford University", "source_name": "Stanford University", "street_adddress": "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu", "country": "United States"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.02985.pdf"], "doi": []}, {"id": "8b5b8db6a2a2880c14894140ea70ceb5f96c3b9b", "title": "Learning a Text-Video Embedding from Incomplete and Heterogeneous Data", "addresses": [{"name": "INRIA", "source_name": "INRIA Grenoble Rhone-Alpes, Grenoble, France", "street_adddress": "655 Avenue de l'Europe, 38330 Montbonnot-Saint-Martin, France", "lat": "45.21788600", "lng": "5.80736900", "type": "edu", "country": "France"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.02516.pdf"], "doi": []}, {"id": "0c2875bb47db3698dbbb3304aca47066978897a4", "title": "Recurrent Models for Situation Recognition", "addresses": [{"name": "University of Illinois, Urbana-Champaign", "source_name": "University of Illinois, Urbana-Champaign", "street_adddress": "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.06233.pdf"], "doi": []}, {"id": "1eeca84f33079c6d7a95daf8994370b2d7a93443", "title": "Fingertip Detection and Tracking for Recognition of Air-Writing in Videos", "addresses": [{"name": "Indian Institute of Technology Bhubaneswar", "source_name": "Indian Institute of Technology Bhubaneswar, Bhubaneswar, India", "street_adddress": "Argul - Jatni Rd, Kansapada, Odisha 752050, India", "lat": "20.14389950", "lng": "85.67620330", "type": "edu", "country": "India"}, {"name": "Indian Institute of Technology Roorkee", "source_name": "Indian Institute of Technology, Roorkee", "street_adddress": "Indian Institute of Technology (IIT), Roorkee, LBS Jogging Track, Roorkee, Haridwar, Uttarakhand, 247667, India", "lat": "29.86624610", "lng": "77.89587081", "type": "edu", "country": "India"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.03016.pdf"], "doi": []}, {"id": "5a0209515ab62e008efeca31f80fa0a97031cd9d", "title": "Dataset fingerprints: Exploring image collections through data mining", "addresses": [{"name": "Georgia Tech", "source_name": "Georgia Tech, Atlanta, GA, USA", "street_adddress": "North Ave NW, Atlanta, GA 30332, USA", "lat": "33.77561780", "lng": "-84.39628500", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/3B_046.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/3B_046_ext.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2015/ext/3B_046_ext.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Rematas_Dataset_Fingerprints_Exploring_2015_CVPR_paper.pdf", "https://homes.cs.washington.edu/~krematas/Publications/rematasCVPR2015.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7299120", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2015.7299120", "http://doi.org/10.1109/CVPR.2015.7299120"]}, {"id": "84036eb97d011ed2d7c9e4eb14fa346b5347c0ad", "title": "Revisiting Pre-training: An Efficient Training Method for Image Classification", "addresses": [{"name": "Beckman Institute", "source_name": "Beckman Institute", "street_adddress": "Beckman Institute, The Presidents' Walk, Urbana, Champaign County, Illinois, 61801-2341, USA", "lat": "40.11571585", "lng": "-88.22750772", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.09347.pdf"], "doi": []}, {"id": "2b0134725e7400f2211207fbe9bfb402b9fcacf3", "title": "Deep Attribute-preserving Metric Learning for Natural Language Object Retrieval", "addresses": [{"name": "Beijing Institute of Technology", "source_name": "Beijing Institute of Technology University", "street_adddress": "\u5317\u4eac\u7406\u5de5\u5927\u5b66, 5, \u4e2d\u5173\u6751\u5357\u5927\u8857, \u4e2d\u5173\u6751, \u7a3b\u9999\u56ed\u5357\u793e\u533a, \u6d77\u6dc0\u533a, \u5317\u4eac\u5e02, 100872, \u4e2d\u56fd", "lat": "39.95866520", "lng": "116.30971281", "type": "edu", "country": "China"}, {"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}, {"name": "National University of Singapore", "source_name": "National University of Singapore", "street_adddress": "NUS, Former 1936 British Outpost, Nepal Hill, Clementi, Southwest, 117542, Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu", "country": "Singapore"}], "year": "2017", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3123439"]}, {"id": "e959a426d02dd014c1346131ac38ed50114c17b7", "title": "A Focused Dynamic Attention Model for Visual Question Answering", "addresses": [{"name": "National University of Singapore", "source_name": "National University of Singapore", "street_adddress": "NUS, Former 1936 British Outpost, Nepal Hill, Clementi, Southwest, 117542, Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu", "country": "Singapore"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1604.01485.pdf"], "doi": []}, {"id": "5f94e354faeba1d330088b926d1f7886067bc93f", "title": "RefineNet : MultiPath Refinement Networks with Identity Mappings for High-Resolution Semantic Segmentation", "addresses": [{"name": "University of Adelaide", "source_name": "University of Adelaide", "street_adddress": "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu", "country": "Australia"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/5f94/e354faeba1d330088b926d1f7886067bc93f.pdf"], "doi": []}, {"id": "d42142285c46207a16bd4294e437d504e419a9b7", "title": "Varying image description tasks : spoken versus written descriptions", "addresses": [{"name": "Tilburg University", "source_name": "Tilburg center for Cognition and Communication, Tilburg University, Tilburg, The Netherlands", "street_adddress": "Warandelaan 2, 5037 AB Tilburg, Netherlands", "lat": "51.56314060", "lng": "5.04197360", "type": "edu", "country": "Netherlands"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/d421/42285c46207a16bd4294e437d504e419a9b7.pdf"], "doi": []}, {"id": "ccd99008d942b890cecd308a31ba61240eac9e54", "title": "Learning to Segment Every Thing", "addresses": [{"name": "UC Berkeley", "source_name": "UC Berkeley", "street_adddress": "Berkeley, CA, USA", "lat": "37.87189920", "lng": "-122.25853990", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.10370.pdf"], "doi": []}, {"id": "91c184e7fb0c7cce5319b8db85c1488b3861976f", "title": "Visual Question Answer Diversity", "addresses": [{"name": "University of Texas at Austin", "source_name": "University of Texas at Austin", "street_adddress": "University of Texas at Austin, 1, East 23rd Street, The Drag, Austin, Travis County, Texas, 78712, USA", "lat": "30.28415100", "lng": "-97.73195598", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/b357/d44a34cc0f692b09a789802f5a905e12a726.pdf"], "doi": []}, {"id": "31c197a0e30f1aeb1414634968d1649e74cd8d0f", "title": "Deep correlation for matching images and text", "addresses": [{"name": "University of Surrey", "source_name": "University of Surrey", "street_adddress": "University of Surrey, Spine Road, Guildford Park, Guildford, Surrey, South East, England, GU2 7XH, UK", "lat": "51.24303255", "lng": "-0.59001382", "type": "edu", "country": "United Kingdom"}], "year": "2015", "pdf": ["http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/2B_012.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/2B_012_ext.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2015/ext/2B_012_ext.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Yan_Deep_Correlation_for_2015_CVPR_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7298966", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2015.7298966", "http://doi.org/10.1109/CVPR.2015.7298966"]}, {"id": "5b8b27d1339d788eb3e0e96888c3633a7b92dc1e", "title": "Hierarchical Image Segmentation Ensemble for Objectness in RGB-D Images", "addresses": [{"name": "Beihang University", "source_name": "Beihang University", "street_adddress": "\u5317\u4eac\u822a\u7a7a\u822a\u5929\u5927\u5b66, 37, \u5b66\u9662\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100083, \u4e2d\u56fd", "lat": "39.98083330", "lng": "116.34101249", "type": "edu", "country": "China"}, {"name": "South China University of Technology", "source_name": "South China University of Technology", "street_adddress": "\u534e\u5357\u7406\u5de5\u5927\u5b66, \u5927\u5b66\u57ce\u4e2d\u73af\u4e1c\u8def, \u5e7f\u5dde\u5927\u5b66\u57ce, \u65b0\u9020, \u756a\u79ba\u533a (Panyu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510006, \u4e2d\u56fd", "lat": "23.05020420", "lng": "113.39880323", "type": "edu", "country": "China"}], "year": "2019", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8116651"]}, {"id": "da437db062e751d49528914971ecdc868b557648", "title": "Improved Image Captioning via Policy Gradient optimization of SPIDEr", "addresses": [{"name": "University of Oxford", "source_name": "University of Oxford", "street_adddress": "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "lat": "51.75345380", "lng": "-1.25400997", "type": "edu", "country": "United Kingdom"}, {"name": "Google", "source_name": "Google, Inc.", "street_adddress": "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "lat": "37.42199990", "lng": "-122.08405750", "type": "company", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1612.00370.pdf"], "doi": []}, {"id": "ee098ed493af3abe873ce89354599e1f6bdf65be", "title": "Progressively Diffused Networks for Semantic Image Segmentation", "addresses": [{"name": "Sun Yat-Sen University", "source_name": "Sun Yat-Sen University", "street_adddress": "\u4e2d\u5927, \u65b0\u6e2f\u897f\u8def, \u9f99\u8239\u6ed8, \u5eb7\u4e50, \u6d77\u73e0\u533a (Haizhu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510105, \u4e2d\u56fd", "lat": "23.09461185", "lng": "113.28788994", "type": "edu", "country": "China"}, {"name": "Chinese University of Hong Kong", "source_name": "Chinese University of Hong Kong", "street_adddress": "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "lat": "22.41626320", "lng": "114.21093180", "type": "edu", "country": "China"}, {"name": "SenseTime", "source_name": "SenseTime", "street_adddress": "China, Beijing Shi, Haidian Qu, WuDaoKou, Zhongguancun E Rd, 1\u53f7-7", "lat": "39.99300800", "lng": "116.32988200", "type": "company", "country": "China"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1702.05839.pdf"], "doi": []}, {"id": "b1db174463b0bbc54a61fcc83acfb89ad3e3d18f", "title": "Loss Functions for Multiset Prediction", "addresses": [{"name": "New York University", "source_name": "New York University", "street_adddress": "NYU, West 4th Street, NoHo Historic District, NoHo, Manhattan, Manhattan Community Board 2, New York County, NYC, New York, 10012, USA", "lat": "40.72925325", "lng": "-73.99625394", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.05246.pdf"], "doi": []}, {"id": "2ebadff3e2a573c947d49aba987e7917a9285ce5", "title": "Investigating the feature collection for semantic segmentation via single skip connection", "addresses": [{"name": "Ajou University", "source_name": "Ajou University", "street_adddress": "\uc544\uc8fc\ub300\ud559\uad50, \uc131\ud638\ub300\uad50, \uc774\uc758\ub3d9, \uc601\ud1b5\uad6c, \uc218\uc6d0\uc2dc, \uacbd\uae30, 16499, \ub300\ud55c\ubbfc\uad6d", "lat": "37.28300030", "lng": "127.04548469", "type": "edu", "country": "Korea"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1710.08192.pdf"], "doi": []}, {"id": "f6ce7e947f1cfe75abda61f018c3ca7e38fceb20", "title": "NLE@MediaEval'17: Combining Cross-Media Similarity and Embeddings for Retrieving Diverse Social Images", "addresses": [{"name": "Naver Labs Europe, Meylan, France", "source_name": "Naver Labs Europe, Meylan, France", "street_adddress": "6 Chemin de Maupertuis, 38240 Meylan, France", "lat": "45.21739890", "lng": "5.79213490", "type": "edu", "country": "France"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/c352/159a5a280e2f7df34d9e8e1444c789e5b912.pdf"], "doi": []}, {"id": "bb6548b43c737dca642298c46ec4648a403e1b11", "title": "A Fast Multi-Task CNN for Spatial Understanding of Traffic Scenes", "addresses": [{"name": "TU Dortmund University", "source_name": "Institute of Control Theory and Systems Engineering, TU Dortmund University, Otto-Hahn-Str. 8, Dortmund, 44227, Germany", "street_adddress": "Emil-Figge-Stra\u00dfe 50, 44227 Dortmund, Germany", "lat": "51.49219020", "lng": "7.41413620", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8569822", "http://doi.org/10.1109/ITSC.2018.8569822"]}, {"id": "256623ff025f36d343588bcd0b966c1fd26afcf8", "title": "Looking for ELMo's friends: Sentence-Level Pretraining Beyond Language Modeling.", "addresses": [{"name": "New York University", "source_name": "New York University", "street_adddress": "NYU, West 4th Street, NoHo Historic District, NoHo, Manhattan, Manhattan Community Board 2, New York County, NYC, New York, 10012, USA", "lat": "40.72925325", "lng": "-73.99625394", "type": "edu", "country": "United States"}, {"name": "Johns Hopkins University", "source_name": "Johns Hopkins University", "street_adddress": "Baltimore, MD 21218, USA", "lat": "39.32990130", "lng": "-76.62051770", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.10860.pdf"], "doi": []}, {"id": "e762f25f13d6dbb95dc59af5e6fbb2160fcf4d55", "title": "Zero-Shot Detection", "addresses": [{"name": "Boston University", "source_name": "Boston University", "street_adddress": "BU, Bay State Road, Fenway, Boston, Suffolk County, Massachusetts, 02215, USA", "lat": "42.35042530", "lng": "-71.10056114", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.07113.pdf"], "doi": []}, {"id": "a3be1951ddb2fa2682385c7f22c2904f5c22a66d", "title": "Traffic-Sign Detection and Classification in the Wild", "addresses": [{"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}, {"name": "Beijing, China", "source_name": "Beijing, China", "street_adddress": "Beijing, China", "lat": "39.90419990", "lng": "116.40739630", "type": "edu", "country": "China"}, {"name": "Lehigh University", "source_name": "Lehigh University", "street_adddress": "Lehigh University, Library Drive, Sayre Park, Bethlehem, Northampton County, Pennsylvania, 18015, USA", "lat": "40.60680280", "lng": "-75.37824880", "type": "edu", "country": "United States"}, {"name": "Tencent", "source_name": "Tencent", "street_adddress": "Ke Ji Zhong Yi Lu, Nanshan Qu, Shenzhen Shi, Guangdong Sheng, China, 518057", "lat": "22.54471540", "lng": "113.93571640", "type": "company", "country": "United States"}], "year": "2016", "pdf": ["http://cg.cs.tsinghua.edu.cn/traffic-sign/0682.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Zhu_Traffic-Sign_Detection_and_CVPR_2016_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780601", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.232", "http://doi.org/10.1109/CVPR.2016.232"]}, {"id": "012876a5f45da258675add1614ad7608a210141a", "title": "What are the Visual Features Underlying Human Versus Machine Vision?", "addresses": [{"name": "Brown University", "source_name": "Brown University", "street_adddress": "Brown University, Waterman Street, College Hill, Providence, Bristol, Rhode Island, 02912, USA", "lat": "41.82686820", "lng": "-71.40123146", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1701.02704.pdf"], "doi": []}, {"id": "c5f6ed9efc222fe2773135ffb4e5c567d98e64ea", "title": "Image Captioning with Word Level Attention", "addresses": [{"name": "Tongji University", "source_name": "Tongji University", "street_adddress": "\u540c\u6d4e\u5927\u5b66, 1239, \u56db\u5e73\u8def, \u6c5f\u6e7e, \u8679\u53e3\u533a, \u4e0a\u6d77\u5e02, 200092, \u4e2d\u56fd", "lat": "31.28473925", "lng": "121.49694909", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8451558", "http://doi.org/10.1109/ICIP.2018.8451558"]}, {"id": "bb4650130c460f413e97b0328624a485bf094967", "title": "Dynamic Lexicon Generation for Natural Scene Images", "addresses": [{"name": "IIIT Hyderabad", "source_name": "CVIT, IIIT Hyderabad", "street_adddress": "IIIT, Gachibowli, Gachibowli, Hyderabad, Telangana 500032, India", "lat": "17.44509810", "lng": "78.34976780", "type": "edu", "country": "India"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/bb46/50130c460f413e97b0328624a485bf094967.pdf"], "doi": []}, {"id": "2f0486b7770c0a8d9cd37e0d73ea3495562511f3", "title": "Extreme Clicking for Efficient Object Annotation", "addresses": [{"name": "University of Edinburgh", "source_name": "University of Edinburgh", "street_adddress": "New College, New College Courtyard, The Mound, Old Town, Edinburgh, City of Edinburgh, Scotland, EH1 2LX, UK", "lat": "55.94951105", "lng": "-3.19534913", "type": "edu", "country": "United Kingdom"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.02750.pdf"], "doi": []}, {"id": "43cb50f669a0d492256d11c6cc4128ba0ce79a3e", "title": "Per-Pixel Feedback for improving Semantic Segmentation", "addresses": [{"name": "Indian Institute of Technology Roorkee", "source_name": "Indian Institute of Technology, Roorkee", "street_adddress": "Indian Institute of Technology (IIT), Roorkee, LBS Jogging Track, Roorkee, Haridwar, Uttarakhand, 247667, India", "lat": "29.86624610", "lng": "77.89587081", "type": "edu", "country": "India"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1712.02861.pdf"], "doi": []}, {"id": "e7928bd33d09fd00a588617736b102063ca9d070", "title": "A Non-Technical Survey on Deep Convolutional Neural Network Architectures", "addresses": [{"name": "Technical University of Munich", "source_name": "Computer Aided Medical Procedures, Technical University of Munich, Garching, Germany", "street_adddress": "Boltzmannstra\u00dfe 3, 85748 Garching bei M\u00fcnchen, Germany", "lat": "48.26301100", "lng": "11.66685700", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.02129.pdf"], "doi": []}, {"id": "ab6c09ee2e466ceef2492f16472aeb76cd34009a", "title": "Data Augmentation for Cnn-Based People Detection in Aerial Images", "addresses": [{"name": "National Chiao Tung University", "source_name": "National Chiao Tung University", "street_adddress": "NCTU;\u4ea4\u5927;\u4ea4\u901a\u5927\u5b78;\u4ea4\u5927\u5149\u5fa9\u6821\u5340;\u4ea4\u901a\u5927\u5b78\u5149\u5fa9\u6821\u5340, 1001, \u5927\u5b78\u8def, \u5149\u660e\u91cc, \u8d64\u571f\u5d0e, \u6771\u5340, \u65b0\u7af9\u5e02, 30010, \u81fa\u7063", "lat": "24.78676765", "lng": "120.99724412", "type": "edu", "country": "Taiwan"}, {"name": "Feng Chia University", "source_name": "Feng Chia University", "street_adddress": "\u9022\u7532\u5927\u5b78, 100, \u6587\u83ef\u8def, \u897f\u5e73\u91cc, \u897f\u5c6f\u5340, \u81fa\u4e2d\u5e02, 40724, \u81fa\u7063", "lat": "24.18005755", "lng": "120.64836072", "type": "edu", "country": "Taiwan"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8551501", "http://doi.ieeecomputersociety.org/10.1109/ICMEW.2018.8551501", "http://doi.org/10.1109/ICMEW.2018.8551501"]}, {"id": "b1f9657ad8033bca6f25a7aef019a1cb45b75ce2", "title": "High performance and fast object detection in road environments", "addresses": [{"name": "DGIST", "source_name": "DGIST", "street_adddress": "South Korea, Daegu, Dalseong-gun, Yuga-myeon, \ud14c\ud06c\ub178\uc911\uc559\ub300\ub85c 333", "lat": "35.70528600", "lng": "128.45710200", "type": "edu", "country": "South Korea"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8310148", "http://doi.org/10.1109/IPTA.2017.8310148"]}, {"id": "51c765b8d872c206f6dd781ab26bd5a8c2feb81e", "title": "Semantic Image Segmentation via Deep Parsing Network", "addresses": [{"name": "Chinese University of Hong Kong", "source_name": "Chinese University of Hong Kong", "street_adddress": "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "lat": "22.41626320", "lng": "114.21093180", "type": "edu", "country": "China"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1509.02634.pdf"], "doi": []}, {"id": "3fde03e7479f2fbff16f7849a2d038dbd29b1762", "title": "SAVOIAS: A Diverse, Multi-Category Visual Complexity Dataset", "addresses": [{"name": "Boston University", "source_name": "Boston University", "street_adddress": "BU, Bay State Road, Fenway, Boston, Suffolk County, Massachusetts, 02215, USA", "lat": "42.35042530", "lng": "-71.10056114", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.01771.pdf"], "doi": []}, {"id": "2fa45a5b0421578a9a0d5124678dafc689e2bf82", "title": "Fake Sentence Detection as a Training Task for Sentence Encoding", "addresses": [{"name": "Stony Brook University", "source_name": "Stony Brook University", "street_adddress": "Stony Brook University, 100, Nicolls Road, Stony Brook, Suffolk County, New York, 11794, USA", "lat": "40.91531960", "lng": "-73.12706260", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.03840.pdf"], "doi": []}, {"id": "059582bee125512b127296364e7700ebd9f80436", "title": "Action-driven 3D indoor scene evolution", "addresses": [{"name": "Simon Fraser University", "source_name": "Simon Fraser University", "street_adddress": "SFU Burnaby, South Campus Road, Barnet, Burnaby, Metro Vancouver, British Columbia, V5A 4X6, Canada", "lat": "49.27674540", "lng": "-122.91777375", "type": "edu", "country": "Canada"}, {"name": "Shandong University", "source_name": "Shandong University", "street_adddress": "\u5c71\u4e1c\u5927\u5b66, \u6cf0\u5b89\u8857, \u9ccc\u5c71\u536b\u8857\u9053, \u5373\u58a8\u533a, \u9752\u5c9b\u5e02, \u5c71\u4e1c\u7701, 266200, \u4e2d\u56fd", "lat": "36.36934730", "lng": "120.67381800", "type": "edu", "country": "China"}, {"name": "Zhejiang University", "source_name": "Zhejiang University", "street_adddress": "\u6d59\u6c5f\u5927\u5b66\u4e4b\u6c5f\u6821\u533a, \u4e4b\u6c5f\u8def, \u8f6c\u5858\u8857\u9053, \u897f\u6e56\u533a (Xihu), \u676d\u5dde\u5e02 Hangzhou, \u6d59\u6c5f\u7701, 310008, \u4e2d\u56fd", "lat": "30.19331415", "lng": "120.11930822", "type": "edu", "country": "China"}, {"name": "Microsoft", "source_name": "Microsoft Corporation, Redmond, WA, USA", "street_adddress": "One Microsoft Way, Redmond, WA 98052, USA", "lat": "47.64233180", "lng": "-122.13693020", "type": "company", "country": "United States"}], "year": "2016", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=2980223"]}, {"id": "c580b0a8dc655a8831ddbb7954bb929b1f236ebc", "title": "Looking deeper and transferring attention for image captioning", "addresses": [{"name": "Tongji University", "source_name": "Tongji University", "street_adddress": "\u540c\u6d4e\u5927\u5b66, 1239, \u56db\u5e73\u8def, \u6c5f\u6e7e, \u8679\u53e3\u533a, \u4e0a\u6d77\u5e02, 200092, \u4e2d\u56fd", "lat": "31.28473925", "lng": "121.49694909", "type": "edu", "country": "China"}, {"name": "Shanghai Engineering Research Center of Industrial Vision Perception & Intelligent Computing, Shanghai, China", "source_name": "Shanghai Engineering Research Center of Industrial Vision Perception & Intelligent Computing, Shanghai, China", "street_adddress": "Shanghai, China", "lat": "31.23039040", "lng": "121.47370210", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://doi.org/10.1007/s11042-018-6228-6"]}, {"id": "537afabc561a2efa79a903f4859ca63e6592f340", "title": "Algorithms for Semantic Segmentation of Multispectral Remote Sensing Imagery using Deep Learning", "addresses": [{"name": "Rochester Institute of Technology", "source_name": "Rochester Institute of Technology", "street_adddress": "Rochester Institute of Technology (RIT), 1, Lomb Memorial Drive, Bailey, Henrietta Town, Monroe County, New York, 14623, USA", "lat": "43.08250655", "lng": "-77.67121663", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.06452.pdf"], "doi": []}, {"id": "ccd3dcbccae7d903608530bddf6381db8e723a7d", "title": "Unsupervised Domain Adaptation for Semantic Segmentation with GANs", "addresses": [{"name": "University of Maryland", "source_name": "University of Maryland", "street_adddress": "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu", "country": "United States"}, {"name": "GE Global Research", "source_name": "General Electric Global Research, Niskayuna, NY, USA", "street_adddress": "1 Research Cir, Niskayuna, NY 12309, USA", "lat": "42.82715560", "lng": "-73.87804810", "type": "company", "country": "United States"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/ccd3/dcbccae7d903608530bddf6381db8e723a7d.pdf"], "doi": []}, {"id": "dec7bbc3e9eeb940c47214d6ea61e14945ab6e7c", "title": "Prototype GOD: prototype Generic Objects Dataset for an Object Detection System based on Bird\u2019s \u2013Eye View", "addresses": [{"name": "Electronics and Telecommunications Research Institute, Korea", "source_name": "Electronics and Telecommunications Research Institute, Korea", "street_adddress": "1110-6 Oryong-dong, Buk-gu, Kwangju, South Korea", "lat": "35.22537080", "lng": "126.84618340", "type": "edu", "country": "South Korea"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8539407", "http://doi.org/10.1109/ICTC.2018.8539407"]}, {"id": "52d9ad99874f6b76184ad9abe45e824a6568617b", "title": "Large-Scale Active Learning with Approximations of Expected Model Output Changes", "addresses": [{"name": "Friedrich Schiller University Jena", "source_name": "Computer Vision Group, Friedrich Schiller University Jena, Germany", "street_adddress": "Ernst-Abbe-Platz 2, 07743 Jena, Germany", "lat": "50.92776710", "lng": "11.58217290", "type": "edu", "country": "Germany"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/52d9/ad99874f6b76184ad9abe45e824a6568617b.pdf"], "doi": []}, {"id": "1eb4ea011a3122dc7ef3447e10c1dad5b69b0642", "title": "Contextual Visual Recognition from Images and Videos", "addresses": [{"name": "University of California at Berkeley", "source_name": "International Computer Science Institute, University of California at Berkeley, Berkeley, USA", "street_adddress": "1947 Center St, Berkeley, CA 94704, USA", "lat": "37.87015430", "lng": "-122.27123120", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/1eb4/ea011a3122dc7ef3447e10c1dad5b69b0642.pdf"], "doi": []}, {"id": "c5cfeac36fd9fc35de7752cd2c63939920eb1eb3", "title": "Dictionary-Guided Editing Networks for Paraphrase Generation", "addresses": [{"name": "Microsoft Research Asia", "source_name": "Microsoft Research Asia", "street_adddress": "1 Memorial Dr, Cambridge, MA 02142, USA", "lat": "42.36142560", "lng": "-71.08120920", "type": "company", "country": "United States"}, {"name": "Beihang University", "source_name": "Beihang University", "street_adddress": "\u5317\u4eac\u822a\u7a7a\u822a\u5929\u5927\u5b66, 37, \u5b66\u9662\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100083, \u4e2d\u56fd", "lat": "39.98083330", "lng": "116.34101249", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.08077.pdf"], "doi": []}, {"id": "72ff1a1dd7c24b51d40d2be7f337b9075bbb8d58", "title": "Where and Who? Automatic Semantic-Aware Person Composition", "addresses": [{"name": "University of Virginia", "source_name": "University of Virginia", "street_adddress": "University of Virginia, Rotunda Alley, Carr's Hill, Albemarle County, Virginia, 22904-4119, USA", "lat": "38.03536820", "lng": "-78.50353220", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1706.01021.pdf"], "doi": []}, {"id": "a32878e85941b5392d58d28e5248f94e16e25d78", "title": "Quality Classified Image Analysis with Application to Face Detection and Recognition", "addresses": [{"name": "University of Nottingham Ningbo China", "source_name": "University of Nottingham Ningbo China", "street_adddress": "199 Taikang E Rd, Yinzhou Qu, Ningbo Shi, Zhejiang Sheng, China, 315000", "lat": "29.80344900", "lng": "121.56160900", "type": "edu", "country": "China"}, {"name": "Shenzhen University", "source_name": "Shenzhen University", "street_adddress": "\u6df1\u5733\u5927\u5b66, 3688, \u5357\u6d77\u5927\u9053, \u86c7\u53e3, \u540c\u4e50\u6751, \u5357\u5c71\u533a, \u6df1\u5733\u5e02, \u5e7f\u4e1c\u7701, 518060, \u4e2d\u56fd", "lat": "22.53521465", "lng": "113.93159110", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1801.06445.pdf"], "doi": []}, {"id": "3244699e06b145ffa65d0fbddb2ce6e5da889418", "title": "Do You See What I Mean? Visual Resolution of Linguistic Ambiguities", "addresses": [{"name": "Weizmann Institute of Science", "source_name": "Weizmann Institute of Science", "street_adddress": "\u05de\u05db\u05d5\u05df \u05d5\u05d9\u05e6\u05de\u05df \u05dc\u05de\u05d3\u05e2, \u05e9\u05d3\u05e8\u05ea \u05de\u05e8\u05db\u05d5\u05e1 \u05d6\u05d9\u05d5, \u05de\u05e2\u05d5\u05e0\u05d5\u05ea \u05e9\u05d9\u05d9\u05df, \u05d0\u05d7\u05d5\u05d6\u05d5\u05ea \u05d4\u05e0\u05e9\u05d9\u05d0, \u05e8\u05d7\u05d5\u05d1\u05d5\u05ea, \u05de\u05d7\u05d5\u05d6 \u05d4\u05de\u05e8\u05db\u05d6, NO, \u05d9\u05e9\u05e8\u05d0\u05dc", "lat": "31.90784990", "lng": "34.81334092", "type": "edu", "country": "Israel"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1603.08079.pdf"], "doi": []}, {"id": "9e64582b644481a734b018304a22b536886ed024", "title": "ALFA: Agglomerative Late Fusion Algorithm for Object Detection", "addresses": [{"name": "Czech Technical University", "source_name": "Czech Technical University", "street_adddress": "\u010cesk\u00e9 vysok\u00e9 u\u010den\u00ed technick\u00e9 v Praze, Resslova, Nov\u00e9 M\u011bsto, Praha, okres Hlavn\u00ed m\u011bsto Praha, Hlavn\u00ed m\u011bsto Praha, Praha, 11121, \u010cesko", "lat": "50.07642960", "lng": "14.41802312", "type": "edu", "country": "Czech Republic"}, {"name": "Kazan Federal University", "source_name": "Institute of Computational Mathematics and Information Technologies, Kazan Federal University, Russia", "street_adddress": "Kremlyovskaya St, 18, Kazan, Respublika Tatarstan, Russia, 420008", "lat": "55.79044700", "lng": "49.12143490", "type": "edu", "country": "Russia"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8545182", "http://doi.ieeecomputersociety.org/10.1109/ICPR.2018.8545182", "http://doi.org/10.1109/ICPR.2018.8545182"]}, {"id": "c85340a0d428ff0b47f1a4d92fc92157cb7664f0", "title": "Multi-Label Music Genre Classification from Audio, Text and Images Using Deep Features", "addresses": [{"name": "Universitat Pompeu Fabra", "source_name": "Universitat Pompeu Fabra", "street_adddress": "Dip\u00f2sit de les Aig\u00fces, Carrer de Wellington, la Vila Ol\u00edmpica del Poblenou, Ciutat Vella, Barcelona, BCN, CAT, 08071, Espa\u00f1a", "lat": "41.39044285", "lng": "2.18891949", "type": "edu", "country": "Spain"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.04916.pdf"], "doi": []}, {"id": "511fad07b943f088e487ea09ffc6c89114bb3c3e", "title": "Towards an Integrated Method of Detection and Description for Face Authentication System", "addresses": [{"name": "University of Ulsan", "source_name": "University of Ulsan, Korea", "street_adddress": "93 Daehak-ro, Mugeo-dong, Nam-gu, Ulsan, South Korea", "lat": "35.54374110", "lng": "129.25628430", "type": "edu", "country": "South Korea"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8430774", "http://doi.org/10.1109/HSI.2018.8430774"]}, {"id": "6bd1f2782d6c8c3066d4e7d7e3afb995d79fa3dd", "title": "Deep Neural Networks for Semantic Segmentation of Multispectral Remote Sensing Imagery", "addresses": [{"name": "Rochester Institute of Technology", "source_name": "Rochester Institute of Technology", "street_adddress": "Rochester Institute of Technology (RIT), 1, Lomb Memorial Drive, Bailey, Henrietta Town, Monroe County, New York, 14623, USA", "lat": "43.08250655", "lng": "-77.67121663", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/6bd1/f2782d6c8c3066d4e7d7e3afb995d79fa3dd.pdf"], "doi": []}, {"id": "d09a3ec68311af4ebd3cbf7ed906aadffa94a464", "title": "Pedestrian Detection by Feature Selected Self-Similarity Features", "addresses": [{"name": "Shanghai Jiao Tong University", "source_name": "Shanghai Jiao Tong University", "street_adddress": "\u4e0a\u6d77\u4ea4\u901a\u5927\u5b66\uff08\u5f90\u6c47\u6821\u533a\uff09, \u6dee\u6d77\u897f\u8def, \u756a\u79ba\u5c0f\u533a, \u5e73\u9634\u6865, \u5f90\u6c47\u533a, \u4e0a\u6d77\u5e02, 200052, \u4e2d\u56fd", "lat": "31.20081505", "lng": "121.42840681", "type": "edu", "country": "China"}, {"name": "University College London", "source_name": "University College London", "street_adddress": "UCL Institute of Education, 20, Bedford Way, Holborn, Bloomsbury, London Borough of Camden, London, Greater London, England, WC1H 0AL, UK", "lat": "51.52316070", "lng": "-0.12820370", "type": "edu", "country": "United Kingdom"}, {"name": "Sichuan Open University", "source_name": "Engineering and Technology College, Sichuan Open University, Chengdu, China", "street_adddress": "\u4e00 Baiye Rd, Pixian, Chengdu Shi, Sichuan Sheng, China", "lat": "30.72886200", "lng": "103.96638100", "type": "edu", "country": "China"}, {"name": "University of Electronic Science and Technology of China", "source_name": "University of Electronic Science and Technology of China", "street_adddress": "2 Jianshe North Rd 2nd Section, Jianshe Road, Chenghua Qu, Chengdu Shi, Sichuan Sheng, China, 610054", "lat": "30.67272100", "lng": "104.09880600", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8286891", "http://doi.org/10.1109/ACCESS.2018.2803160"]}, {"id": "e096003fc0dad2a09334044ebcc01601fdc0afd6", "title": "Subitizing with Variational Autoencoders", "addresses": [{"name": "University of Amsterdam", "source_name": "University of Amsterdam", "street_adddress": "Institute for Logic, Language and Computation (ILLC), 107, Science Park, Oost-Watergraafsmeer, Amsterdam, Oost, Amsterdam, Noord-Holland, Nederland, 1098XG, Nederland", "lat": "52.35536550", "lng": "4.95016440", "type": "edu", "country": "Netherlands"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.00257.pdf"], "doi": []}, {"id": "43c5be1f64e0135fb3d6e43a9c33caaaa58f7213", "title": "The Emotional Impact of Audio-Visual Stimuli", "addresses": [{"name": "Rochester Institute of Technology", "source_name": "Rochester Institute of Technology", "street_adddress": "Rochester Institute of Technology (RIT), 1, Lomb Memorial Drive, Bailey, Henrietta Town, Monroe County, New York, 14623, USA", "lat": "43.08250655", "lng": "-77.67121663", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/43c5/be1f64e0135fb3d6e43a9c33caaaa58f7213.pdf"], "doi": []}, {"id": "80fc9efde5bb28550d17363d882fd5bc6d805c26", "title": "Question Type Guided Attention in Visual Question Answering", "addresses": [{"name": "University of California, Irvine", "source_name": "University of California, Irvine", "street_adddress": "Irvine, CA 92697, USA", "lat": "33.64049520", "lng": "-117.84429620", "type": "edu", "country": "United States"}, {"name": "University of Southern California", "source_name": "University of Southern California", "street_adddress": "University of Southern California, Watt Way, Saint James Park, LA, Los Angeles County, California, 90089, USA", "lat": "34.02241490", "lng": "-118.28634407", "type": "edu", "country": "United States"}, {"name": "California Institute of Technology", "source_name": "California Institute of Technology", "street_adddress": "California Institute of Technology, San Pasqual Walk, Madison Heights, Pasadena, Los Angeles County, California, 91126, USA", "lat": "34.13710185", "lng": "-118.12527487", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.02088.pdf"], "doi": []}, {"id": "4a9d906935c9de019c61aedc10b77ee10e3aec63", "title": "Cross Modal Distillation for Supervision Transfer", "addresses": [{"name": "University of California, Berkeley", "source_name": "University of California, Berkeley", "street_adddress": "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "lat": "37.86871260", "lng": "-122.25586815", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1507.00448.pdf"], "doi": []}, {"id": "350af77e01e78e8e3534f42b80b5dd35a602e73c", "title": "Hierarchical Recurrent Neural Encoder for Video Representation with Application to Captioning", "addresses": [{"name": "University of Technology Sydney", "source_name": "University of Technology Sydney", "street_adddress": "University of Technology Sydney, Omnibus Lane, Ultimo, Sydney, NSW, 2007, Australia", "lat": "-33.88096510", "lng": "151.20107299", "type": "edu", "country": "Australia"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1511.03476.pdf"], "doi": []}, {"id": "db0a4af734dab1854c2e8dfe499fe0e353226e45", "title": "Hot Anchors: A Heuristic Anchors Sampling Method in RCNN-Based Object Detection", "addresses": [{"name": "Chinese Academy of Sciences", "source_name": "Chinese Academy of Sciences", "street_adddress": "\u4e2d\u56fd\u79d1\u5b66\u9662\u5fc3\u7406\u7814\u7a76\u6240, 16, \u6797\u8403\u8def, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100101, \u4e2d\u56fd", "lat": "40.00447950", "lng": "116.37023800", "type": "edu", "country": "China"}, {"name": "University of Chinese Academy of Sciences", "source_name": "University of Chinese Academy of Sciences", "street_adddress": "University of Chinese Academy of Sciences, UCAS, Yuquanlu, \u7389\u6cc9\u8def, \u7530\u6751, \u6d77\u6dc0\u533a, 100049, \u4e2d\u56fd", "lat": "39.90828040", "lng": "116.24585270", "type": "edu", "country": "China"}, {"name": "Xi\u2019an Jiaotong University", "source_name": "Institute of Information and System Sciences, Faculty of Mathematics and Statistics, Xi\u2019an Jiaotong University, Xi\u2019an, China", "street_adddress": "28 Xianning W Rd, JiaoDa ShangYe JieQu, Beilin Qu, Xian Shi, Shaanxi Sheng, China", "lat": "34.25080300", "lng": "108.98369300", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/db0a/4af734dab1854c2e8dfe499fe0e353226e45.pdf"], "doi": []}, {"id": "0171bdeb1c6e333287be655c667cfba5edb89b76", "title": "Aggregated Residual Transformations for Deep Neural Networks", "addresses": [{"name": "UC San Diego", "source_name": "UC San Diego", "street_adddress": "9500 Gilman Dr, La Jolla, CA 92093, USA", "lat": "32.88006040", "lng": "-117.23401350", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1611.05431.pdf"], "doi": []}, {"id": "6759fd391e3f8a1aea7673d617d3e1b04d069804", "title": "Pose Flow: Efficient Online Pose Tracking", "addresses": [{"name": "Shanghai Jiao Tong University", "source_name": "Shanghai Jiao Tong University", "street_adddress": "\u4e0a\u6d77\u4ea4\u901a\u5927\u5b66\uff08\u5f90\u6c47\u6821\u533a\uff09, \u6dee\u6d77\u897f\u8def, \u756a\u79ba\u5c0f\u533a, \u5e73\u9634\u6865, \u5f90\u6c47\u533a, \u4e0a\u6d77\u5e02, 200052, \u4e2d\u56fd", "lat": "31.20081505", "lng": "121.42840681", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.00977.pdf"], "doi": []}, {"id": "fa93e027e795e98405dc72f123aadebafc5d80d8", "title": "Explaining the Ambiguity of Object Detection and 6D Pose from Visual Data", "addresses": [{"name": "TU Munich", "source_name": "Faculty of Electrical Engineering and Information Technology, Technische Universit\u00e4t M\u00fcnchen, 85290, Germany", "street_adddress": "Mies-van-der-Rohe-Stra\u00dfe 15, 52074 Aachen, Germany", "lat": "50.77892190", "lng": "6.06563870", "type": "edu", "country": "Germany"}, {"name": "University of Oxford", "source_name": "University of Oxford", "street_adddress": "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "lat": "51.75345380", "lng": "-1.25400997", "type": "edu", "country": "United Kingdom"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.00287.pdf"], "doi": []}, {"id": "5fa04523ff13a82b8b6612250a39e1edb5066521", "title": "Dockerface: an easy to install and use Faster R-CNN face detector in a Docker container", "addresses": [{"name": "Georgia Institute of Technology", "source_name": "Georgia Institute of Technology", "street_adddress": "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.04370.pdf"], "doi": []}, {"id": "4443d51f54a9df679efc5ae65115f60f8e58a1a0", "title": "Spott: On-the-Spot e-Commerce for Television Using Deep Learning-Based Video Analysis Techniques", "addresses": [{"name": "Ghent University - imec - MICT", "source_name": "Ghent University - imec - MICT, Korte Meer, Ghent", "street_adddress": "Miriam Makebaplein 1, 9000 Gent, Belgium", "lat": "51.04893030", "lng": "3.72886530", "type": "edu", "country": "Belgium"}, {"name": "Ghent University", "source_name": "Ghent University", "street_adddress": "St. Pietersnieuwstraat 33, 9000 Gent, Belgium", "lat": "51.04656190", "lng": "3.72791810", "type": "edu", "country": "Belgium"}], "year": "2017", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3092834"]}, {"id": "a8fd9be2f7775b123f62094eadd59d18bbbef027", "title": "Peephole: Predicting Network Performance Before Training", "addresses": [{"name": "Beihang University", "source_name": "Beihang University", "street_adddress": "\u5317\u4eac\u822a\u7a7a\u822a\u5929\u5927\u5b66, 37, \u5b66\u9662\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100083, \u4e2d\u56fd", "lat": "39.98083330", "lng": "116.34101249", "type": "edu", "country": "China"}, {"name": "SenseTime", "source_name": "SenseTime", "street_adddress": "China, Beijing Shi, Haidian Qu, WuDaoKou, Zhongguancun E Rd, 1\u53f7-7", "lat": "39.99300800", "lng": "116.32988200", "type": "company", "country": "China"}, {"name": "Chinese University of Hong Kong", "source_name": "Chinese University of Hong Kong", "street_adddress": "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "lat": "22.41626320", "lng": "114.21093180", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1712.03351.pdf"], "doi": []}, {"id": "812e11fc86e5d183337257978e5a0f26b5668218", "title": "Evaluating ResNeXt Model Architecture for Image Classification", "addresses": [{"name": "University of Waterloo", "source_name": "University of Waterloo", "street_adddress": "University of Waterloo, 200, University Avenue West, Northdale, Beechwood, Waterloo, Regional Municipality of Waterloo, Ontario, N2L 3G1, Canada", "lat": "43.47061295", "lng": "-80.54724732", "type": "edu", "country": "Canada"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.08700.pdf"], "doi": []}, {"id": "a71b99357b0952858f98867ed0cbc87738899e1a", "title": "ScratchDet : Training Single-Shot Object Detectors from Scratch", "addresses": [{"name": "University of Chinese Academy of Sciences", "source_name": "University of Chinese Academy of Sciences", "street_adddress": "University of Chinese Academy of Sciences, UCAS, Yuquanlu, \u7389\u6cc9\u8def, \u7530\u6751, \u6d77\u6dc0\u533a, 100049, \u4e2d\u56fd", "lat": "39.90828040", "lng": "116.24585270", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/a71b/99357b0952858f98867ed0cbc87738899e1a.pdf"], "doi": []}, {"id": "faa3b7034b89c9ab7ca5360a14311f2fd36ef7b9", "title": "AutoFocus: Efficient Multi-Scale Inference", "addresses": [{"name": "University of Maryland", "source_name": "University of Maryland", "street_adddress": "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.01600.pdf"], "doi": []}, {"id": "044e0d86e2db70d4c0b767bf0994913e90e105e3", "title": "Answer-Type Prediction for Visual Question Answering", "addresses": [{"name": "Rochester Institute of Technology", "source_name": "Rochester Institute of Technology", "street_adddress": "Rochester Institute of Technology (RIT), 1, Lomb Memorial Drive, Bailey, Henrietta Town, Monroe County, New York, 14623, USA", "lat": "43.08250655", "lng": "-77.67121663", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2016/papers/Kafle_Answer-Type_Prediction_for_CVPR_2016_paper.pdf", "http://www.chriskanan.com/wp-content/uploads/Kafle2016.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Kafle_Answer-Type_Prediction_for_CVPR_2016_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780907", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.538", "http://doi.org/10.1109/CVPR.2016.538", "http://scholarworks.rit.edu/cgi/viewcontent.cgi?article=1919&context=other"]}, {"id": "d5873c4f169227ab002366db3b55d1fede9f473f", "title": "Multi-modal deep feature learning for RGB-D object detection", "addresses": [{"name": "Nanjing University", "source_name": "Nanjing University", "street_adddress": "NJU, \u4e09\u6c5f\u8def, \u9f13\u697c\u533a, \u5357\u4eac\u5e02, \u6c5f\u82cf\u7701, 210093, \u4e2d\u56fd", "lat": "32.05659570", "lng": "118.77408833", "type": "edu", "country": "China"}, {"name": "University of Rochester", "source_name": "University of Rochester", "street_adddress": "Memorial Art Gallery, 500, University Avenue, East End, Rochester, Monroe County, New York, 14607, USA", "lat": "43.15769690", "lng": "-77.58829158", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["http://mcg.nju.edu.cn/publication/2017/xiangyang-2017.pdf"], "doi": ["http://doi.org/10.1016/j.patcog.2017.07.026"]}, {"id": "a89e1fc2681a9a399cc5008ea34b5ec3fe7ca845", "title": "Improving Fast Segmentation With Teacher-Student Learning", "addresses": [{"name": "Sun Yat-Sen University", "source_name": "Sun Yat-Sen University", "street_adddress": "\u4e2d\u5927, \u65b0\u6e2f\u897f\u8def, \u9f99\u8239\u6ed8, \u5eb7\u4e50, \u6d77\u73e0\u533a (Haizhu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510105, \u4e2d\u56fd", "lat": "23.09461185", "lng": "113.28788994", "type": "edu", "country": "China"}, {"name": "Nanyang Technological University", "source_name": "Nanyang Technological University", "street_adddress": "NTU, Faculty Avenue, Jurong West, Southwest, 637460, Singapore", "lat": "1.34841040", "lng": "103.68297965", "type": "edu", "country": "Singapore"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.08476.pdf"], "doi": []}, {"id": "55af092ce75ade8a26d2afe97d57de2191d44b5f", "title": "Unsupervised Ensemble Regression", "addresses": [{"name": "Weizmann Institute of Science", "source_name": "Weizmann Institute of Science", "street_adddress": "\u05de\u05db\u05d5\u05df \u05d5\u05d9\u05e6\u05de\u05df \u05dc\u05de\u05d3\u05e2, \u05e9\u05d3\u05e8\u05ea \u05de\u05e8\u05db\u05d5\u05e1 \u05d6\u05d9\u05d5, \u05de\u05e2\u05d5\u05e0\u05d5\u05ea \u05e9\u05d9\u05d9\u05df, \u05d0\u05d7\u05d5\u05d6\u05d5\u05ea \u05d4\u05e0\u05e9\u05d9\u05d0, \u05e8\u05d7\u05d5\u05d1\u05d5\u05ea, \u05de\u05d7\u05d5\u05d6 \u05d4\u05de\u05e8\u05db\u05d6, NO, \u05d9\u05e9\u05e8\u05d0\u05dc", "lat": "31.90784990", "lng": "34.81334092", "type": "edu", "country": "Israel"}, {"name": "IBM T.J. Watson Research Center", "source_name": "IBM T. J. Watson Research, Center, New York, USA", "street_adddress": "1101 Kitchawan Rd, Yorktown Heights, NY 10598, USA", "lat": "41.20975160", "lng": "-73.80264670", "type": "company", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.02965.pdf"], "doi": []}, {"id": "5f94969b9491db552ffebc5911a45def99026afe", "title": "Multimodal Learning and Reasoning for Visual Question Answering", "addresses": [{"name": "National University of Singapore", "source_name": "National University of Singapore", "street_adddress": "NUS, Former 1936 British Outpost, Nepal Hill, Clementi, Southwest, 117542, Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu", "country": "Singapore"}, {"name": "Electrical and Computer Engineering", "source_name": "Electrical and Computer Engineering", "street_adddress": "Electrical and Computer Engineering, Boston Avenue, South Overton, Lubbock, Lubbock County, Texas, 79409, USA", "lat": "33.58667840", "lng": "-101.87539204", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/5f94/969b9491db552ffebc5911a45def99026afe.pdf"], "doi": []}, {"id": "91a972eadf78f44bdc03cc5ebe27899091bc94e1", "title": "AutoMarkov DNNs for object classification", "addresses": [{"name": "University Politehnica of Bucharest", "source_name": "University Politehnica of Bucharest", "street_adddress": "Universitatea Politehnica din Bucure\u0219ti, Novum Invest, Bucure\u0219ti, Militari, Sector 6, Municipiul Bucure\u0219ti, 060042, Rom\u00e2nia", "lat": "44.43918115", "lng": "26.05044565", "type": "edu", "country": "Romania"}], "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7900168", "http://doi.org/10.1109/ICPR.2016.7900168"]}, {"id": "55d1342900e0abc59495afd44cde0a0052367b42", "title": "Traits & Transferability of Adversarial Examples against Instance Segmentation & Object Detection", "addresses": [{"name": "University of Illinois, Urbana-Champaign", "source_name": "University of Illinois, Urbana-Champaign", "street_adddress": "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.01452.pdf"], "doi": []}, {"id": "267bd60e442d87c44eaae3290610138e63d663ab", "title": "PoseTrack: Joint Multi-person Pose Estimation and Tracking", "addresses": [{"name": "University of Bonn", "source_name": "University of Bonn", "street_adddress": "Rheinische Friedrich-Wilhelms-Universit\u00e4t Bonn, Arkadenhof, Bonn-Zentrum, Stadtbezirk Bonn, Bonn, Regierungsbezirk K\u00f6ln, Nordrhein-Westfalen, 53113, Deutschland", "lat": "50.73381240", "lng": "7.10224650", "type": "edu", "country": "Germany"}, {"name": "University of Adelaide", "source_name": "University of Adelaide", "street_adddress": "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu", "country": "Australia"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1611.07727.pdf"], "doi": []}, {"id": "6583d293734d56c9dd2a34ffa5887c6c323aacf5", "title": "Integrating Local Material Recognition with Large-Scale Perceptual Attribute Discovery", "addresses": [{"name": "Drexel University", "source_name": "Drexel University", "street_adddress": "Drexel University, Arch Street, Powelton Village, Philadelphia, Philadelphia County, Pennsylvania, 19104, USA", "lat": "39.95740000", "lng": "-75.19026706", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1604.01345.pdf"], "doi": []}, {"id": "bfce448a3409d87ba281de53ed696b09119f2ba9", "title": "Object segmentation in depth maps with one user click and a synthetically trained fully convolutional network", "addresses": [{"name": "INRIA", "source_name": "INRIA Grenoble Rhone-Alpes, Grenoble, France", "street_adddress": "655 Avenue de l'Europe, 38330 Montbonnot-Saint-Martin, France", "lat": "45.21788600", "lng": "5.80736900", "type": "edu", "country": "France"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1801.01281.pdf"], "doi": []}, {"id": "66c6aebf10410a11623e32e23295213dfd7c557f", "title": "Fast and Accurate Semantic Mapping through Geometric-based Incremental Segmentation", "addresses": [{"name": "TU Munich", "source_name": "Faculty of Electrical Engineering and Information Technology, Technische Universit\u00e4t M\u00fcnchen, 85290, Germany", "street_adddress": "Mies-van-der-Rohe-Stra\u00dfe 15, 52074 Aachen, Germany", "lat": "50.77892190", "lng": "6.06563870", "type": "edu", "country": "Germany"}, {"name": "Keio University", "source_name": "Keio University", "street_adddress": "\u7db1\u5cf6\u5e02\u6c11\u306e\u68ee, \u3051\u3064\u308f\u308a\u5742, \u6e2f\u5317\u533a, \u6a2a\u6d5c\u5e02, \u795e\u5948\u5ddd\u770c, \u95a2\u6771\u5730\u65b9, 223-0053, \u65e5\u672c", "lat": "35.54169690", "lng": "139.63471840", "type": "edu", "country": "Japan"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8593993"]}, {"id": "267c8798a5c602dae05908b63f031dbdb81fc42b", "title": "Amodal Instance Segmentation", "addresses": [{"name": "University of California, Berkeley", "source_name": "University of California, Berkeley", "street_adddress": "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "lat": "37.86871260", "lng": "-122.25586815", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1604.08202.pdf"], "doi": []}, {"id": "c1d1b1197667facd360196059796ab8cb7b46e96", "title": "PolyMapper: Extracting City Maps using Polygons", "addresses": [{"name": "ETH Z\u00fcrich", "source_name": "ETH Z\u00fcrich", "street_adddress": "ETH Z\u00fcrich, 101, R\u00e4mistrasse, Hochschulen, Altstadt, Z\u00fcrich, Bezirk Z\u00fcrich, Z\u00fcrich, 8092, Schweiz/Suisse/Svizzera/Svizra", "lat": "47.37645340", "lng": "8.54770931", "type": "edu", "country": "Switzerland"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.01497.pdf"], "doi": []}, {"id": "a0a49f50d9b76ad4ba7ce5acd14a3d4b31a520d6", "title": "HiDDeN: Hiding Data With Deep Networks", "addresses": [{"name": "Stanford University", "source_name": "Stanford University", "street_adddress": "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.09937.pdf"], "doi": []}, {"id": "333f083671da1010cbb080c6ce607ed87c19d73d", "title": "Multiple Instance Learning Convolutional Neural Networks for object recognition", "addresses": [{"name": "Electrical and Computer Engineering", "source_name": "Electrical and Computer Engineering", "street_adddress": "Electrical and Computer Engineering, Boston Avenue, South Overton, Lubbock, Lubbock County, Texas, 79409, USA", "lat": "33.58667840", "lng": "-101.87539204", "type": "edu", "country": "United States"}, {"name": "University of Missouri", "source_name": "University of Missouri", "street_adddress": "L1, Maguire Boulevard, Lemone Industrial Park, Columbia, Boone County, Missouri, 65201, USA", "lat": "38.92676100", "lng": "-92.29193783", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1610.03155.pdf"], "doi": []}, {"id": "a2c97ced4981a4505a6aa7f26e1c499df98f525d", "title": "Shape and Pose Estimation for Closely Interacting Persons Using Multi-view Images", "addresses": [{"name": "Tianjin University", "source_name": "Tianjin University", "street_adddress": "\u6cf0\u5c71\u822a\u7a7a\u6e2f/\u5929\u6d25\u5927\u53a6, \u67a3\u884c\u8def, \u67a3\u884c \u9ad8\u738b\u5bfa, \u957f\u57ce\u8def, \u5927\u6cb3, \u5cb1\u5cb3\u533a (Daiyue), \u6cf0\u5b89\u5e02, \u5c71\u4e1c\u7701, 271000, \u4e2d\u56fd", "lat": "36.20304395", "lng": "117.05842113", "type": "edu", "country": "China"}, {"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}, {"name": "Southeast University", "source_name": "Southeast University", "street_adddress": "SEU, \u4f53\u80b2\u9986\u8def, \u65b0\u8857\u53e3, \u6708\u5b63\u56ed, \u7384\u6b66\u533a, \u5357\u4eac\u5e02, \u6c5f\u82cf\u7701, 210008, \u4e2d\u56fd", "lat": "32.05752790", "lng": "118.78682252", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://www.yangangwang.com/papers/LI-SPE-2018-08.pdf"], "doi": ["http://doi.org/10.1111/cgf.13574"]}, {"id": "21819624b83b40586afce41c3c9ae7abf6c9a2ab", "title": "A vision-grounded dataset for predicting typical locations for verbs", "addresses": [{"name": "Max Planck Institute for Informatics", "source_name": "Max Planck Institute for Informatics", "street_adddress": "MPII, E1 4, Campus, Universit\u00e4t, Sankt Johann, Bezirk Mitte, Saarbr\u00fccken, Regionalverband Saarbr\u00fccken, Saarland, 66123, Deutschland", "lat": "49.25795660", "lng": "7.04577417", "type": "edu", "country": "Germany"}, {"name": "Saarland University", "source_name": "Mathematical Image Analysis Group, Faculty of Mathematics and Computer Science, Saarland University, Saarbr\u00fccken, Germany", "street_adddress": "66123 Saarbr\u00fccken, Germany", "lat": "49.25502840", "lng": "7.04097500", "type": "edu", "country": "Germany"}, {"name": "University of California at Berkeley", "source_name": "International Computer Science Institute, University of California at Berkeley, Berkeley, USA", "street_adddress": "1947 Center St, Berkeley, CA 94704, USA", "lat": "37.87015430", "lng": "-122.27123120", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/2181/9624b83b40586afce41c3c9ae7abf6c9a2ab.pdf"], "doi": []}, {"id": "744089e18ef246785cdec2875d2b3872ef1d71b6", "title": "Parallel Attention: A Unified Framework for Visual Object Discovery Through Dialogs and Queries", "addresses": [{"name": "University of Adelaide", "source_name": "University of Adelaide", "street_adddress": "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu", "country": "Australia"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.06370.pdf"], "doi": []}, {"id": "ff772950f66ac6a57f4201ce1f02f0013ccdc1bb", "title": "Receptive Field Block Net for Accurate and Fast Object Detection", "addresses": [{"name": "Beihang University", "source_name": "Beihang University", "street_adddress": "\u5317\u4eac\u822a\u7a7a\u822a\u5929\u5927\u5b66, 37, \u5b66\u9662\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100083, \u4e2d\u56fd", "lat": "39.98083330", "lng": "116.34101249", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.07767.pdf"], "doi": []}, {"id": "658c802890c7133e2ade778b5d88b68bcd0dca9c", "title": "Learning to Segment via Cut-and-Paste", "addresses": [{"name": "Google", "source_name": "Google, Inc.", "street_adddress": "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "lat": "37.42199990", "lng": "-122.08405750", "type": "company", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.06414.pdf"], "doi": []}, {"id": "606cfdcc43203351dbb944a3bb3719695e557e37", "title": "Ex Paucis Plura : Learning Affordance Segmentation from Very Few Examples", "addresses": [{"name": "University of Bonn", "source_name": "University of Bonn", "street_adddress": "Rheinische Friedrich-Wilhelms-Universit\u00e4t Bonn, Arkadenhof, Bonn-Zentrum, Stadtbezirk Bonn, Bonn, Regierungsbezirk K\u00f6ln, Nordrhein-Westfalen, 53113, Deutschland", "lat": "50.73381240", "lng": "7.10224650", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/606c/fdcc43203351dbb944a3bb3719695e557e37.pdf"], "doi": []}, {"id": "1bd9db88bdab930f0dd380942b65c1449383166b", "title": "Robot Classification of Human Interruptibility and a Study of Its Effects", "addresses": [{"name": "Georgia Institute of Technology", "source_name": "Georgia Institute of Technology", "street_adddress": "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu", "country": "United States"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3277902"]}, {"id": "83e5e6fc0f086017b3e099ec063df94f47427d2c", "title": "Fast, Diverse and Accurate Image Captioning Guided By Part-of-Speech", "addresses": [{"name": "University of Illinois, Urbana-Champaign", "source_name": "University of Illinois, Urbana-Champaign", "street_adddress": "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.12589.pdf"], "doi": []}, {"id": "39836fbbcd2a664edb31119e88870c38b83df352", "title": "Adaptively Attending to Visual Attributes and Linguistic Knowledge for Captioning", "addresses": [{"name": "University of Electronic Science and Technology of China", "source_name": "University of Electronic Science and Technology of China", "street_adddress": "2 Jianshe North Rd 2nd Section, Jianshe Road, Chenghua Qu, Chengdu Shi, Sichuan Sheng, China, 610054", "lat": "30.67272100", "lng": "104.09880600", "type": "edu", "country": "China"}, {"name": "University of Queensland", "source_name": "University of Queensland", "street_adddress": "University of Queensland, University Drive, Hill End, St Lucia, Brisbane, QLD, 4072, Australia", "lat": "-27.49741805", "lng": "153.01316956", "type": "edu", "country": "Australia"}], "year": "2017", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3123391"]}, {"id": "c72e6992f44ce75a40f44be4365dc4f264735cfb", "title": "Story Understanding in Video Advertisements", "addresses": [{"name": "University of Pittsburgh", "source_name": "University of Pittsburgh", "street_adddress": "University of Pittsburgh, Sutherland Drive, West Oakland, PGH, Allegheny County, Pennsylvania, 15240, USA", "lat": "40.44415295", "lng": "-79.96243993", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.11122.pdf"], "doi": []}, {"id": "25dba68e4db0ce361032126b91f734f9252cae7c", "title": "DeepSetNet: Predicting Sets with Deep Neural Networks", "addresses": [{"name": "University of Adelaide", "source_name": "University of Adelaide", "street_adddress": "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu", "country": "Australia"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1611.08998.pdf"], "doi": []}, {"id": "3a0f23dcb731762f9cc968d63385183b301eef89", "title": "Towards Segmenting Everything That Moves", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1902.03715.pdf"], "doi": []}, {"id": "8bce31108f598986558e9afb1061eb988ea4f3be", "title": "Automated Image Annotation based on YOLOv3", "addresses": [{"name": "Vilnius Gediminas Technical University", "source_name": "Vilnius Gediminas Technical University, Naugarduko g. 41-413, Vilnius LT-03227, Lithuania", "street_adddress": "Naugarduko g. 41, Vilnius 03227, Lithuania", "lat": "54.67377770", "lng": "25.26622250", "type": "edu", "country": "Lithuania"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8592167"]}, {"id": "fdbe50ca6741ddad66fb289960624627c6869cfc", "title": "Weakly Semi-Supervised Deep Learning for Multi-Label Image Annotation", "addresses": [{"name": "Zhejiang University", "source_name": "Zhejiang University", "street_adddress": "\u6d59\u6c5f\u5927\u5b66\u4e4b\u6c5f\u6821\u533a, \u4e4b\u6c5f\u8def, \u8f6c\u5858\u8857\u9053, \u897f\u6e56\u533a (Xihu), \u676d\u5dde\u5e02 Hangzhou, \u6d59\u6c5f\u7701, 310008, \u4e2d\u56fd", "lat": "30.19331415", "lng": "120.11930822", "type": "edu", "country": "China"}, {"name": "University of Rochester", "source_name": "University of Rochester", "street_adddress": "Memorial Art Gallery, 500, University Avenue, East End, Rochester, Monroe County, New York, 14607, USA", "lat": "43.15769690", "lng": "-77.58829158", "type": "edu", "country": "United States"}, {"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}, {"name": "University of Technology Sydney", "source_name": "University of Technology Sydney", "street_adddress": "University of Technology Sydney, Omnibus Lane, Ultimo, Sydney, NSW, 2007, Australia", "lat": "-33.88096510", "lng": "151.20107299", "type": "edu", "country": "Australia"}], "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7317747"]}, {"id": "1855818c492d5f42dbe14814e4dd9b5733d54790", "title": "Densely Connected Discriminative Correlation Filters for Visual Tracking", "addresses": [{"name": "Shanghai Jiao Tong University", "source_name": "Shanghai Jiao Tong University", "street_adddress": "\u4e0a\u6d77\u4ea4\u901a\u5927\u5b66\uff08\u5f90\u6c47\u6821\u533a\uff09, \u6dee\u6d77\u897f\u8def, \u756a\u79ba\u5c0f\u533a, \u5e73\u9634\u6865, \u5f90\u6c47\u533a, \u4e0a\u6d77\u5e02, 200052, \u4e2d\u56fd", "lat": "31.20081505", "lng": "121.42840681", "type": "edu", "country": "China"}, {"name": "Auckland University of Technology", "source_name": "Computer and Mathematical Sciences, Auckland University of Technology, Auckland, New Zealand", "street_adddress": "31 Symonds St, Auckland, 1010, New Zealand", "lat": "-36.85444260", "lng": "174.76761040", "type": "edu", "country": "New Zealand"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8359334"]}, {"id": "f857cdf601379064bde3d4738f40aed30e266dbf", "title": "Training Very Deep CNNs for General Non-Blind Deconvolution", "addresses": [{"name": "University of Sydney", "source_name": "University of Sydney", "street_adddress": "USyd, Fisher Road, Camperdown, Sydney, NSW, 2006, Australia", "lat": "-33.88890695", "lng": "151.18943366", "type": "edu", "country": "Australia"}, {"name": "Union Visual Innovation Technology Co., Ltd., Shenzhen, China", "source_name": "Union Visual Innovation Technology Co., Ltd., Shenzhen, China", "street_adddress": "Shenzhen, Guangdong, China", "lat": "22.54309600", "lng": "114.05786500", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8315039"]}, {"id": "8d0dffcf36e76ebbb5ff9389750264d9fb77265f", "title": "Comparison of Visual Datasets for Machine Learning", "addresses": [{"name": "Purdue University", "source_name": "Purdue University", "street_adddress": "Purdue University, West Stadium Avenue, West Lafayette, Tippecanoe County, Indiana, 47907, USA", "lat": "40.43197220", "lng": "-86.92389368", "type": "edu", "country": "United States"}, {"name": "University of Miami", "source_name": "University of Miami", "street_adddress": "University of Miami, Theo Dickenson Drive, Coral Gables, Miami-Dade County, Florida, 33124, USA", "lat": "25.71733390", "lng": "-80.27866887", "type": "edu", "country": "United States"}, {"name": "Florida International University", "source_name": "Florida International University", "street_adddress": "FIU, Southwest 14th Street, Sweetwater, University Park, Miami-Dade County, Florida, 33199, USA", "lat": "25.75533775", "lng": "-80.37628897", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["http://rvc.eng.miami.edu/Paper/2017/IRI17_Gauen.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8102956", "http://doi.ieeecomputersociety.org/10.1109/IRI.2017.59", "http://doi.org/10.1109/IRI.2017.59", "http://ecommons.luc.edu/cgi/viewcontent.cgi?article=1148&context=cs_facpubs"]}, {"id": "8c4c723a74fe479c2b8af7d911817377dd6d85c9", "title": "Understanding Neural Networks Through Deep Visualization", "addresses": [{"name": "Cornell University", "source_name": "Cornell University", "street_adddress": "Cornell University, Forest Home Drive, Forest Home, Tompkins County, New York, 14853, USA", "lat": "42.45055070", "lng": "-76.47835130", "type": "edu", "country": "United States"}, {"name": "California Institute of Technology", "source_name": "California Institute of Technology", "street_adddress": "California Institute of Technology, San Pasqual Walk, Madison Heights, Pasadena, Los Angeles County, California, 91126, USA", "lat": "34.13710185", "lng": "-118.12527487", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1506.06579.pdf"], "doi": []}, {"id": "e0c3c1b9744a695cfeab11ceb23069c38844932c", "title": "Non-parametric human segmentation using support vector machine", "addresses": [{"name": "Yonsei University", "source_name": "Yonsei University", "street_adddress": "\uc5f0\uc138\ub300, \uc5f0\uc138\ub85c, \uc2e0\ucd0c\ub3d9, \ucc3d\ucc9c\ub3d9, \uc11c\ub300\ubb38\uad6c, \uc11c\uc6b8\ud2b9\ubcc4\uc2dc, 03789, \ub300\ud55c\ubbfc\uad6d", "lat": "37.56004060", "lng": "126.93692480", "type": "edu", "country": "South Korea"}], "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7430551"]}, {"id": "fe0edc34d9bdf51c1544a3f70e83917e5d917681", "title": "An End-to-End Quadrilateral Regression Network for Comic Panel Extraction", "addresses": [{"name": "Peking University", "source_name": "Peking University", "street_adddress": "\u5317\u4eac\u5927\u5b66, 5\u53f7, \u9890\u548c\u56ed\u8def, \u7a3b\u9999\u56ed\u5357\u793e\u533a, \u6d77\u6dc0\u533a, \u5317\u4eac\u5e02, 100871, \u4e2d\u56fd", "lat": "39.99223790", "lng": "116.30393816", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3240555"]}, {"id": "e431de776590f52a5ae2be2d71900136c91b7136", "title": "Towards a Robust Interactive and Learning Social Robot", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}, {"name": "Karlsruhe Institute of Technology", "source_name": "Karlsruhe Institute of Technology", "street_adddress": "KIT, Leopoldshafener Allee, Linkenheim, Linkenheim-Hochstetten, Landkreis Karlsruhe, Regierungsbezirk Karlsruhe, Baden-W\u00fcrttemberg, 76351, Deutschland", "lat": "49.10184375", "lng": "8.43312560", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/e431/de776590f52a5ae2be2d71900136c91b7136.pdf"], "doi": []}, {"id": "474c8f4e31a51e2cb3c1e9fed83202b4483efb35", "title": "Computer Vision \u2013 ECCV 2018", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}, {"name": "Google Research, Zurich, Switzerland", "source_name": "Google Research, Zurich, Switzerland", "street_adddress": "Brandschenkestrasse 110, 8002 Z\u00fcrich, Switzerland", "lat": "47.36554640", "lng": "8.52483910", "type": "company", "country": "Switzerland"}, {"name": "Hebrew University of Jerusalem", "source_name": "The Hebrew University of Jerusalem", "street_adddress": "\u05d4\u05d0\u05d5\u05e0\u05d9\u05d1\u05e8\u05e1\u05d9\u05d8\u05d4 \u05d4\u05e2\u05d1\u05e8\u05d9\u05ea \u05d1\u05d9\u05e8\u05d5\u05e9\u05dc\u05d9\u05dd, Reagan Plaza, \u05e7\u05e8\u05d9\u05ea \u05de\u05e0\u05d7\u05dd \u05d1\u05d2\u05d9\u05df, \u05d4\u05e8 \u05d4\u05e6\u05d5\u05e4\u05d9\u05dd, \u05d9\u05e8\u05d5\u05e9\u05dc\u05d9\u05dd, \u05de\u05d7\u05d5\u05d6 \u05d9\u05e8\u05d5\u05e9\u05dc\u05d9\u05dd, NO, \u05d9\u05e9\u05e8\u05d0\u05dc", "lat": "31.79185550", "lng": "35.24472300", "type": "edu", "country": "Israel"}], "year": "2018", "pdf": [], "doi": ["http://doi.org/10.1007/978-3-030-01228-1"]}, {"id": "62a6220c8cb5b74e958870e52affd9e7542216fc", "title": "Street object detection / tracking for AI city traffic analysis", "addresses": [{"name": "State University of New York", "source_name": "University at Albany, State University of New York, Albany, USA", "street_adddress": "353 Broadway, Albany, NY 12207, USA", "lat": "42.64805160", "lng": "-73.74957600", "type": "edu", "country": "United States"}, {"name": "University of Chinese Academy of Sciences", "source_name": "University of Chinese Academy of Sciences", "street_adddress": "University of Chinese Academy of Sciences, UCAS, Yuquanlu, \u7389\u6cc9\u8def, \u7530\u6751, \u6d77\u6dc0\u533a, 100049, \u4e2d\u56fd", "lat": "39.90828040", "lng": "116.24585270", "type": "edu", "country": "China"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8397669"]}, {"id": "cdeee5eed68e7c8eb06185f7fcb1a072af784886", "title": "Deep Learning for Object Saliency Detection and Image Segmentation", "addresses": [{"name": "York University", "source_name": "York University", "street_adddress": "York University, Keele Campus, Campus Walk, North York, Toronto, Ontario, M3J 2S5, Canada", "lat": "43.77439110", "lng": "-79.50481085", "type": "edu", "country": "Canada"}, {"name": "Stanford University", "source_name": "Stanford University", "street_adddress": "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1505.01173.pdf"], "doi": []}, {"id": "164f3b9740d9ceb14658237fddede0f86b5e0c47", "title": "Deep Category-Aware Semantic Edge Detection", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "", "pdf": ["https://pdfs.semanticscholar.org/1b61/41d3fbe8b97fd414ec931a47aa1d019347d9.pdf"], "doi": []}, {"id": "30f464c09779c6210397204901d025c0def1fe10", "title": "Deep Reasoning with Knowledge Graph for Social Relationship Understanding", "addresses": [{"name": "Sun Yat-Sen University", "source_name": "Sun Yat-Sen University", "street_adddress": "\u4e2d\u5927, \u65b0\u6e2f\u897f\u8def, \u9f99\u8239\u6ed8, \u5eb7\u4e50, \u6d77\u73e0\u533a (Haizhu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510105, \u4e2d\u56fd", "lat": "23.09461185", "lng": "113.28788994", "type": "edu", "country": "China"}, {"name": "SenseTime", "source_name": "SenseTime", "street_adddress": "China, Beijing Shi, Haidian Qu, WuDaoKou, Zhongguancun E Rd, 1\u53f7-7", "lat": "39.99300800", "lng": "116.32988200", "type": "company", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.00504.pdf"], "doi": []}, {"id": "64a5709d41f4c2ef0383cee9932e89bb58085588", "title": "Surgeon Technical Skill Assessment using Computer Vision based Analysis", "addresses": [{"name": "University of Michigan", "source_name": "University of Michigan", "street_adddress": "University of Michigan, 500, Hayward Street, Ann Arbor, Washtenaw County, Michigan, 48109, USA", "lat": "42.29421420", "lng": "-83.71003894", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/64a5/709d41f4c2ef0383cee9932e89bb58085588.pdf"], "doi": []}, {"id": "0c65245bff0004961a5173709400479addbb9ee1", "title": "SemanticFusion: Dense 3D semantic mapping with convolutional neural networks", "addresses": [{"name": "Imperial College London", "source_name": "Imperial College London", "street_adddress": "Imperial College London, Exhibition Road, Brompton, Royal Borough of Kensington and Chelsea, London, Greater London, England, SW7 2AZ, UK", "lat": "51.49887085", "lng": "-0.17560797", "type": "edu", "country": "United Kingdom"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7989538"]}, {"id": "24e680c5e7f59b72984ebc344dfba0f9573fb38c", "title": "On the difficulty of a distributional semantics of spoken language", "addresses": [{"name": "Tilburg University", "source_name": "Tilburg center for Cognition and Communication, Tilburg University, Tilburg, The Netherlands", "street_adddress": "Warandelaan 2, 5037 AB Tilburg, Netherlands", "lat": "51.56314060", "lng": "5.04197360", "type": "edu", "country": "Netherlands"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.08869.pdf"], "doi": []}, {"id": "2e84deb2fbc518c0ed0ba4158fc063060e5ac1b3", "title": "Real-time Progressive 3D Semantic Segmentation for Indoor Scene", "addresses": [{"name": "Singapore University of Technology and Design", "source_name": "Singapore University of Technology and Design", "street_adddress": "Singapore University of Technology and Design, Simpang Bedok, Changi Business Park, Southeast, 486041, Singapore", "lat": "1.34021600", "lng": "103.96508900", "type": "edu", "country": "Singapore"}, {"name": "Deakin University", "source_name": "Deakin University", "street_adddress": "Deakin University, Pigdons Lane, Waurn Ponds, Geelong, City of Greater Geelong, Barwon South West, Victoria, 3216, Australia", "lat": "-38.19928505", "lng": "144.30365229", "type": "edu", "country": "Australia"}, {"name": "Hong Kong University of Science and Technology", "source_name": "Hong Kong University of Science and Technology", "street_adddress": "\u9999\u6e2f\u79d1\u6280\u5927\u5b78 Hong Kong University of Science and Technology, \u5927\u5b78\u9053 University Road, \u5927\u57d4\u4ed4 Tai Po Tsai, \u5927\u57d4\u4ed4\u6751 Tai Po Tsai Village, \u65b0\u754c New Territories, HK, DD253 1209, \u4e2d\u56fd", "lat": "22.33863040", "lng": "114.26203370", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.00257.pdf"], "doi": []}, {"id": "2d15a7546c16d5821ffa8f769eb7ec18e435e64d", "title": "Recognition in Terra Incognita", "addresses": [{"name": "Caltech", "source_name": "California Inst. of Technol., Pasadena, CA, USA", "street_adddress": "1200 E California Blvd, Pasadena, CA 91125, USA", "lat": "34.13765760", "lng": "-118.12526900", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.04975.pdf"], "doi": []}, {"id": "84a3478cf884b0cbba480c7c36dab565e778094b", "title": "Learning to detect chest radiographs containing lung nodules using visual attention networks", "addresses": [{"name": "King\u2019s College London", "source_name": "Institute of Psychiatry, King\u2019s College London, London, UK", "street_adddress": "16 De Crespigny Park, Camberwell, London SE5 8AF, UK", "lat": "51.47022750", "lng": "-0.09014280", "type": "edu", "country": "United Kingdom"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1712.00996.pdf"], "doi": []}, {"id": "fbace36d9161fbd062eefa0c005362bb210c7097", "title": "VPGNet: Vanishing Point Guided Network for Lane and Road Marking Detection and Recognition", "addresses": [{"name": "KAIST", "source_name": "KAIST", "street_adddress": "291 Daehak-ro, Eoeun-dong, Yuseong-gu, Daejeon, South Korea", "lat": "36.37214270", "lng": "127.36039000", "type": "edu", "country": "South Korea"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1710.06288.pdf"], "doi": []}, {"id": "d012f6d7fd45051adaff8da4ce0860de9f81d445", "title": "A Deep Multi-task Learning Approach to Skin Lesion Classification", "addresses": [{"name": "University of Rochester", "source_name": "University of Rochester", "street_adddress": "Memorial Art Gallery, 500, University Avenue, East End, Rochester, Monroe County, New York, 14607, USA", "lat": "43.15769690", "lng": "-77.58829158", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1812.03527.pdf"], "doi": []}, {"id": "fc027fccb19512a439fc17181c34ee1c3aad51b5", "title": "Joint Multi-person Pose Estimation and Semantic Part Segmentation", "addresses": [{"name": "UCLA", "source_name": "University of California, Los Angeles", "street_adddress": "Los Angeles, CA 90095, USA", "lat": "34.06892100", "lng": "-118.44518110", "type": "edu", "country": "United States"}, {"name": "Johns Hopkins University", "source_name": "Johns Hopkins University", "street_adddress": "Baltimore, MD 21218, USA", "lat": "39.32990130", "lng": "-76.62051770", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.03383.pdf"], "doi": []}, {"id": "50d6dcec7f1fcbde647237d43950fa5ec59d6984", "title": "Panoptic Segmentation with a Joint Semantic and Instance Segmentation Network", "addresses": [{"name": "TU Eindhoven", "source_name": "TU Eindhoven", "street_adddress": "Technische Universiteit Eindhoven, 2, De Rondom, Villapark, Eindhoven, Noord-Brabant, Nederland, 5600 MB, Nederland", "lat": "51.44866020", "lng": "5.49039957", "type": "edu", "country": "Netherlands"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.02110.pdf"], "doi": []}, {"id": "225c318f3143b9b9d6c0f7a87672bd1d9d2901f4", "title": "2 D-Driven 3 D Object Detection in RGB-D Images", "addresses": [{"name": "King Abdullah University of Science and Technology (KAUST)", "source_name": "King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia", "street_adddress": "Thuwal 23955, Saudi Arabia", "lat": "22.30946500", "lng": "39.10469700", "type": "edu", "country": "Saudi Arabia"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/225c/318f3143b9b9d6c0f7a87672bd1d9d2901f4.pdf"], "doi": []}, {"id": "37e1fc37a3ee90f24d85ad6fd3e5c51d3f5ab4fd", "title": "Attentive Explanations: Justifying Decisions and Pointing to the Evidence", "addresses": [{"name": "Max Planck Institute for Informatics", "source_name": "Max Planck Institute for Informatics", "street_adddress": "MPII, E1 4, Campus, Universit\u00e4t, Sankt Johann, Bezirk Mitte, Saarbr\u00fccken, Regionalverband Saarbr\u00fccken, Saarland, 66123, Deutschland", "lat": "49.25795660", "lng": "7.04577417", "type": "edu", "country": "Germany"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1612.04757.pdf"], "doi": []}, {"id": "475e16577be1bfc0dd1f74f67bb651abd6d63524", "title": "DAiSEE: Towards User Engagement Recognition in the Wild", "addresses": [{"name": "Microsoft", "source_name": "Microsoft Corporation, Redmond, WA, USA", "street_adddress": "One Microsoft Way, Redmond, WA 98052, USA", "lat": "47.64233180", "lng": "-122.13693020", "type": "company", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1609.01885.pdf"], "doi": []}, {"id": "503c16d9cb1560f13a7d6baedf8c9f889b22459d", "title": "Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation", "addresses": [{"name": "Google", "source_name": "Google, Inc.", "street_adddress": "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "lat": "37.42199990", "lng": "-122.08405750", "type": "company", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.02611.pdf"], "doi": []}, {"id": "18c57ddc9c0164ee792661f43a5578f7a00d0330", "title": "ChestX-Ray8: Hospital-Scale Chest X-Ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases", "addresses": [{"name": "National Institutes of Health", "source_name": "National Institutes of Health", "street_adddress": "NIH, Pooks Hill, Bethesda, Montgomery County, Maryland, USA", "lat": "39.00041165", "lng": "-77.10327775", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.02315.pdf"], "doi": []}, {"id": "f632790471b2bed7ba7c28b12cda9360ec586a63", "title": "Deep Binaries: Encoding Semantic-Rich Cues for Efficient Textual-Visual Cross Retrieval", "addresses": [{"name": "University of East Anglia", "source_name": "University of East Anglia", "street_adddress": "Arts (Lower Walkway Level), The Square, Westfield View, Earlham, Norwich, Norfolk, East of England, England, NR4 7TJ, UK", "lat": "52.62215710", "lng": "1.24091360", "type": "edu", "country": "United Kingdom"}, {"name": "University of Electronic Science and Technology of China", "source_name": "University of Electronic Science and Technology of China", "street_adddress": "2 Jianshe North Rd 2nd Section, Jianshe Road, Chenghua Qu, Chengdu Shi, Sichuan Sheng, China, 610054", "lat": "30.67272100", "lng": "104.09880600", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.02531.pdf"], "doi": []}, {"id": "197c406b95340dfcdef542db532e0f7a967b9cda", "title": "Softer-NMS: Rethinking Bounding Box Regression for Accurate Object Detection", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.08545.pdf"], "doi": []}, {"id": "0f54eacd2d9ad031a0b55166399e2f1d0f70b4b5", "title": "Joint Learning of Set Cardinality and State Distribution", "addresses": [{"name": "University of Adelaide", "source_name": "University of Adelaide", "street_adddress": "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu", "country": "Australia"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1709.04093.pdf"], "doi": []}, {"id": "1e54025a6b399bfc210a52a8c3314e8f570c2204", "title": "DenseCap: Fully Convolutional Localization Networks for Dense Captioning", "addresses": [{"name": "Stanford University", "source_name": "Stanford University", "street_adddress": "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1511.07571.pdf"], "doi": []}, {"id": "26203d84466488b168745334935f7ca82294e3e4", "title": "Visual Reasoning by Progressive Module Networks", "addresses": [{"name": "University of Toronto", "source_name": "University of Toronto", "street_adddress": "University of Toronto, St. George Street, Bloor Street Culture Corridor, Old Toronto, Toronto, Ontario, M5S 1A5, Canada", "lat": "43.66333345", "lng": "-79.39769975", "type": "edu", "country": "Canada"}, {"name": "NVIDIA", "source_name": "NVIDIA", "street_adddress": "2788 San Tomas Expy, Santa Clara, CA 95051, USA", "lat": "37.37062540", "lng": "-121.96718940", "type": "company", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.02453.pdf"], "doi": []}, {"id": "8b059a9851c23067afe247b59e54f3167caa9b34", "title": "Modality-Specific Cross-Modal Similarity Measurement With Recurrent Attention Network", "addresses": [{"name": "Peking University", "source_name": "Peking University", "street_adddress": "\u5317\u4eac\u5927\u5b66, 5\u53f7, \u9890\u548c\u56ed\u8def, \u7a3b\u9999\u56ed\u5357\u793e\u533a, \u6d77\u6dc0\u533a, \u5317\u4eac\u5e02, 100871, \u4e2d\u56fd", "lat": "39.99223790", "lng": "116.30393816", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8401908"]}, {"id": "3796fe0e5dd10b01fc9fb486d09e61b28eedf915", "title": "Instance Segmentation of Fibers from Low Resolution CT Scans via 3D Deep Embedding Learning", "addresses": [{"name": "Heidelberg University", "source_name": "Institute of Psychology, Heidelberg University, Heidelberg, Germany", "street_adddress": "Hauptstra\u00dfe 47-51, 69117 Heidelberg, Germany", "lat": "49.41092660", "lng": "8.69795290", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1901.01034.pdf"], "doi": []}, {"id": "11a8cc3fa18ab4f7158447cc1fc8800489e82f9c", "title": "AttResNet: Attention-based ResNet for Image Captioning", "addresses": [{"name": "National University of Defense Technology, China", "source_name": "National University of Defence Technology, Changsha 410000, China", "street_adddress": "\u56fd\u9632\u79d1\u5b66\u6280\u672f\u5927\u5b66, \u4e09\u4e00\u5927\u9053, \u5f00\u798f\u533a, \u5f00\u798f\u533a (Kaifu), \u957f\u6c99\u5e02 / Changsha, \u6e56\u5357\u7701, 410073, \u4e2d\u56fd", "lat": "28.22902090", "lng": "112.99483204", "type": "mil", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3302464"]}, {"id": "2e78e804ddfe86f112719d4a237c882f930a9d3b", "title": "Development of Real-time ADAS Object Detector for Deployment on CPU", "addresses": [{"name": "Intel", "source_name": "Intel Corp., 4600 S. Dobson Road, Chandler, AZ 85248", "street_adddress": "4500 S Dobson Rd, Chandler, AZ 85248, USA", "lat": "33.24160080", "lng": "-111.88390830", "type": "company", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.05894.pdf"], "doi": []}, {"id": "396aacab076a3607429f58ce442d5d57b5aaa794", "title": "Semantic Instance Annotation of Street Scenes by 3D to 2D Label Transfer", "addresses": [{"name": "University of Washington", "source_name": "University of Washington", "street_adddress": "University of Washington, Rainier Vista, Montlake, University District, Seattle, King County, Washington, 98195, USA", "lat": "47.65432380", "lng": "-122.30800894", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1511.03240.pdf"], "doi": []}, {"id": "6fe1439e40429c7cd7029ecf83ca6f36fd0c8040", "title": "Deep Matching and Validation Network: An End-to-End Solution to Constrained Image Splicing Localization and Detection", "addresses": [{"name": "Information Sciences Institute, Marina Del Rey, CA", "source_name": "Information Sciences Institute, Marina Del Rey, CA, USA", "street_adddress": "4676 Admiralty Way #1001, Marina Del Rey, CA 90292, USA", "lat": "33.98007070", "lng": "-118.44003850", "type": "edu", "country": "United States"}], "year": "2017", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3123411"]}, {"id": "5a40efdd3a50ab2e3bce106f92d921713ef068b3", "title": "Learning Saliency Prediction From Sparse Fixation Pixel Map", "addresses": [{"name": "Sichuan University, Chengdu", "source_name": "Sichuan Univ., Chengdu", "street_adddress": "\u56db\u5ddd\u5927\u5b66\uff08\u534e\u897f\u6821\u533a\uff09, \u6821\u4e1c\u8def, \u6b66\u4faf\u533a, \u6b66\u4faf\u533a (Wuhou), \u6210\u90fd\u5e02 / Chengdu, \u56db\u5ddd\u7701, 610014, \u4e2d\u56fd", "lat": "30.64276900", "lng": "104.06751175", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.00644.pdf"], "doi": []}, {"id": "745a913b6a3dd28f3d1c583e80497d6d627a9ca4", "title": "OBJ2TEXT: Generating Visually Descriptive Language from Object Layouts", "addresses": [{"name": "University of Virginia", "source_name": "University of Virginia", "street_adddress": "University of Virginia, Rotunda Alley, Carr's Hill, Albemarle County, Virginia, 22904-4119, USA", "lat": "38.03536820", "lng": "-78.50353220", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.07102.pdf"], "doi": []}, {"id": "a43280a668f12cffdb7b4c9917984aa55b12759b", "title": "Zoom Out-and-In Network with Recursive Training for Object Proposal", "addresses": [{"name": "Chinese University of Hong Kong", "source_name": "Chinese University of Hong Kong", "street_adddress": "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "lat": "22.41626320", "lng": "114.21093180", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1702.05711.pdf"], "doi": []}, {"id": "aa7914646c6a4bbad0727cb84ab9b05e5b381af4", "title": "Framework for Evaluating Vision-based Autonomous Steering Control Model", "addresses": [{"name": "DGIST", "source_name": "DGIST", "street_adddress": "South Korea, Daegu, Dalseong-gun, Yuga-myeon, \ud14c\ud06c\ub178\uc911\uc559\ub300\ub85c 333", "lat": "35.70528600", "lng": "128.45710200", "type": "edu", "country": "South Korea"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8569717"]}, {"id": "3ab93fe26a46f8bc0999e68af71a0907a63a5e65", "title": "ESTHER: Extremely Simple Image Translation Through Self-Regularization", "addresses": [{"name": "University of Southern California", "source_name": "University of Southern California", "street_adddress": "University of Southern California, Watt Way, Saint James Park, LA, Los Angeles County, California, 90089, USA", "lat": "34.02241490", "lng": "-118.28634407", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/3ab9/3fe26a46f8bc0999e68af71a0907a63a5e65.pdf"], "doi": []}, {"id": "1d82e7736268917cc3d87a2ee0896b03e02a5ff6", "title": "The Promise of Premise: Harnessing Question Premises in Visual Question Answering", "addresses": [{"name": "Virginia Tech", "source_name": "Virginia Tech", "street_adddress": "Blacksburg, VA 24061, USA", "lat": "37.22838430", "lng": "-80.42341670", "type": "edu", "country": "United States"}, {"name": "Georgia Institute of Technology", "source_name": "Georgia Institute of Technology", "street_adddress": "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.00601.pdf"], "doi": []}, {"id": "58d16e23e1192be4acaf6a29c1f5995817146554", "title": "Bringing back simplicity and lightliness into neural image captioning", "addresses": [{"name": "University of Mons", "source_name": "Faculty of Engineering, University of Mons, Belgium", "street_adddress": "Place du Parc 20, 7000 Mons, Belgium", "lat": "50.45877140", "lng": "3.95216520", "type": "edu", "country": "Belgium"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.06245.pdf"], "doi": []}, {"id": "7771807cd05f78a4591f2d0b094ddd3e0bd5339a", "title": "Adaptive Feeding: Achieving Fast and Accurate Detections by Adaptively Combining Object Detectors", "addresses": [{"name": "Nanjing University", "source_name": "Nanjing University", "street_adddress": "NJU, \u4e09\u6c5f\u8def, \u9f13\u697c\u533a, \u5357\u4eac\u5e02, \u6c5f\u82cf\u7701, 210093, \u4e2d\u56fd", "lat": "32.05659570", "lng": "118.77408833", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.06399.pdf"], "doi": []}, {"id": "b2c60061ad32e28eb1e20aff42e062c9160786be", "title": "Diverse and Controllable Image Captioning with Part-of-Speech Guidance", "addresses": [{"name": "University of Illinois, Urbana-Champaign", "source_name": "University of Illinois, Urbana-Champaign", "street_adddress": "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.12589.pdf"], "doi": []}, {"id": "20a91b0e7c2598d327169517cdeaafc433caa700", "title": "Inshore Ship Detection Based on Mask R-CNN", "addresses": [{"name": "Beihang University", "source_name": "Beihang University", "street_adddress": "\u5317\u4eac\u822a\u7a7a\u822a\u5929\u5927\u5b66, 37, \u5b66\u9662\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100083, \u4e2d\u56fd", "lat": "39.98083330", "lng": "116.34101249", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8519123"]}, {"id": "07f4ba45b771ed123b08261d88acda19406a7987", "title": "Real-Time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identification", "addresses": [{"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.04427.pdf"], "doi": []}, {"id": "cb4fc4d49783f2049c48a062169f04eb744443ec", "title": "Paying More Attention to Saliency: Image Captioning with Saliency and Context Attention", "addresses": [{"name": "University of Modena and Reggio Emilia", "source_name": "University of Modena and Reggio Emilia 41125, Modena, Italy", "street_adddress": "Via Universit\u00e0, 4, 41121 Modena MO, Italy", "lat": "44.64510460", "lng": "10.92792680", "type": "edu", "country": "Italy"}, {"name": "University of Udine", "source_name": "University of Udine, Italy", "street_adddress": "Universit\u00e0 degli Studi di Udine, Via delle Scienze, 206, 33100 Udine UD, Italy", "lat": "46.08107230", "lng": "13.21194740", "type": "edu", "country": "Italy"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1706.08474.pdf"], "doi": []}, {"id": "38262d92b09564aba747beb7150b92c92998170c", "title": "A Visual Attention Grounding Neural Model for Multimodal Machine Translation", "addresses": [{"name": "University of California, Davis", "source_name": "University of California, Davis", "street_adddress": "University of California, Davis, Apiary Drive, Yolo County, California, 95616-5270, USA", "lat": "38.53363490", "lng": "-121.79077264", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.08266.pdf"], "doi": []}]}
\ No newline at end of file
+{"id": "5e0f8c355a37a5a89351c02f174e7a5ddcb98683", "dataset": {"key": "coco", "name_short": "COCO", "name_display": "COCO Dataset", "name_full": "Microsoft COCO: Common Objects in Context", "purpose": "object and scene recognition", "comment": "First published in 2014, revised in 2015: dataset split in two", "created_by": "", "funded_by": "", "funded_by_short": "", "used_by": "", "license": "", "url": "http://cocodataset.org/", "verify_do": "Y", "verify_done": "", "cooperative": "N", "dl_im": "Y", "dl_meta": "", "dl_paper": "", "dl_web": "", "mp_pub": "N", "ft_share": "Y", "nyt_share": "Y", "indoor": "", "outdoor": "", "campus": "", "cyberspace": "Y", "parent": "", "sources": "www, google, bing, flickr", "source_cat": "", "usernames": "", "names": "", "flickr_meta": "", "year_start": "", "year_end": "", "year_published": "2014", "ongoing": "", "images": "328,000 ", "videos": "", "tracklets": "", "identities": "", "img_per_person": "", "num_cameras": "", "faces_or_persons": "", "female": "", "male": "", "landmarks": "", "width": "", "height": "", "color": "Y", "gray": "", "tags": "ped_detect, obj", "size_gb": "", "agreement": "", "agreement_signed": "", "flickr": "Y", "facebook": "", "youtube": "", "vimeo": "", "google": "", "bing": "", "adam": "", "berit": "", "charlie": "Y", "notes": "", "derivative_of": "", "": ""}, "paper": {"paper_id": "5e0f8c355a37a5a89351c02f174e7a5ddcb98683", "key": "coco", "title": "Microsoft COCO: Common Objects in Context", "year": "2014", "pdf": ["https://arxiv.org/pdf/1405.0312.pdf"], "address": "", "name": "COCO", "doi": []}, "addresses": [], "additional_papers": [], "citations": [{"id": "8b9377ead9b05d0e5d86f7092ce5084841c146a4", "title": "Asking for Help with the Right Question by Predicting Human Visual Performance", "addresses": [{"name": "University of California, Santa Barbara", "source_name": "University of California, Santa Barbara", "street_adddress": "UCSB, Santa Barbara County, California, 93106, USA", "lat": "34.41459370", "lng": "-119.84581950", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/ebbc/4569b767323c5bf6917c0efdce5d172e721d.pdf"], "doi": []}, {"id": "133f1f2679892d408420d8092283539010723359", "title": "What Makes for Effective Detection Proposals?", "addresses": [{"name": "Max Planck Institute for Informatics", "source_name": "Max Planck Institute for Informatics", "street_adddress": "MPII, E1 4, Campus, Universit\u00e4t, Sankt Johann, Bezirk Mitte, Saarbr\u00fccken, Regionalverband Saarbr\u00fccken, Saarland, 66123, Deutschland", "lat": "49.25795660", "lng": "7.04577417", "type": "edu", "country": "Germany"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1502.05082.pdf"], "doi": []}, {"id": "e0ef2d1e9bcde8da814bf510a31ce3dc90919ed8", "title": "SHPD: Surveillance Human Pose Dataset and Performance Evaluation for Coarse-Grained Pose Estimation", "addresses": [{"name": "Shanghai Jiao Tong University", "source_name": "Shanghai Jiao Tong University", "street_adddress": "\u4e0a\u6d77\u4ea4\u901a\u5927\u5b66\uff08\u5f90\u6c47\u6821\u533a\uff09, \u6dee\u6d77\u897f\u8def, \u756a\u79ba\u5c0f\u533a, \u5e73\u9634\u6865, \u5f90\u6c47\u533a, \u4e0a\u6d77\u5e02, 200052, \u4e2d\u56fd", "lat": "31.20081505", "lng": "121.42840681", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8451116", "http://doi.org/10.1109/ICIP.2018.8451116"]}, {"id": "55761bdf5cbbff5fbede8ee9d0573d1561a9254b", "title": "The Impact of Visual Saliency Prediction in Image Classification", "addresses": [{"name": "Dublin City University", "source_name": "DUBLIN CITY UNIVERSITY", "street_adddress": "Dublin City University Glasnevin Campus, Lower Car Park, Wad, Whitehall A ED, Dublin 9, Dublin, County Dublin, Leinster, D09 FW22, Ireland", "lat": "53.38522185", "lng": "-6.25740874", "type": "edu", "country": "Ireland"}, {"name": "Universitat Politecnica de Catalunya", "source_name": "Universitat Politcnica de Catalunya, EU, Spain", "street_adddress": "Campus Nord, Carrer de Jordi Girona, 1, 3, 08034 Barcelona, Spain", "lat": "41.38800400", "lng": "2.11328040", "type": "edu", "country": "Spain"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/5576/1bdf5cbbff5fbede8ee9d0573d1561a9254b.pdf"], "doi": []}, {"id": "a31a01827d809673a641877f21759633936d7da5", "title": "Reducing Network Agnostophobia", "addresses": [{"name": "University of Colorado, Colorado Springs", "source_name": "University of Colorado Colorado Springs", "street_adddress": "Main Hall, The Spine, Colorado Springs, El Paso County, Colorado, 80907, USA", "lat": "38.89207560", "lng": "-104.79716389", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.04110.pdf"], "doi": []}, {"id": "12a91c9d4a55fc93f15f4acef078c8908af3c9b9", "title": "Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.01642.pdf"], "doi": []}, {"id": "c32b66a9badc57e416cf15287c9c8861b264805b", "title": "Towards Closing the Gap in Weakly Supervised Semantic Segmentation with DCNNs: Combining Local and Global Models.", "addresses": [{"name": "ETH Z\u00fcrich", "source_name": "ETH Z\u00fcrich", "street_adddress": "ETH Z\u00fcrich, 101, R\u00e4mistrasse, Hochschulen, Altstadt, Z\u00fcrich, Bezirk Z\u00fcrich, Z\u00fcrich, 8092, Schweiz/Suisse/Svizzera/Svizra", "lat": "47.37645340", "lng": "8.54770931", "type": "edu", "country": "Switzerland"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.01625.pdf"], "doi": []}, {"id": "02a4462e6c63007dda36ca5305f6b57d03f1316f", "title": "The Real-Time Detection of Traffic Participants Using YOLO Algorithm", "addresses": [{"name": "RT-RK, Institute for Computer Based Systems, Novi Sad, Serbia", "source_name": "RT-RK, Institute for Computer Based Systems, Novi Sad, Serbia", "street_adddress": "Narodnog fronta 23A, Novi Sad 21000, Serbia", "lat": "45.23963230", "lng": "19.83640040", "type": "edu", "country": "Serbia"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8611986"]}, {"id": "0754d3d8fbae668880a3eb91b2bce89543ea467e", "title": "Natural Language Driven Image Edits using a Semantic Image Manipulation Language (SIMPL)", "addresses": [{"name": "Virginia Tech", "source_name": "Virginia Tech", "street_adddress": "Blacksburg, VA 24061, USA", "lat": "37.22838430", "lng": "-80.42341670", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/0754/d3d8fbae668880a3eb91b2bce89543ea467e.pdf"], "doi": []}, {"id": "47067114c681e93322a9152fe7ceb7a9178bb32b", "title": "Monitoring Scene Understanders with Conceptual Primitive Decomposition and Commonsense Knowledge", "addresses": [{"name": "MIT", "source_name": "Massachusetts Institute", "street_adddress": "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/4706/7114c681e93322a9152fe7ceb7a9178bb32b.pdf"], "doi": []}, {"id": "fbaceba60619d9f76f7acf6e639669cd6150049e", "title": "Automatic Semantic Content Removal by Learning to Neglect.", "addresses": [{"name": "University of California, Santa Cruz", "source_name": "University of California, Santa Cruz, Santa Cruz", "street_adddress": "1156 High St, Santa Cruz, CA 95064, USA", "lat": "36.99158470", "lng": "-122.05827710", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.07696.pdf"], "doi": []}, {"id": "b5cd9e5d81d14868f1a86ca4f3fab079f63a366d", "title": "Tag-based video retrieval by embedding semantic content in a continuous word space", "addresses": [{"name": "University of Southern California", "source_name": "University of Southern California", "street_adddress": "University of Southern California, Watt Way, Saint James Park, LA, Los Angeles County, California, 90089, USA", "lat": "34.02241490", "lng": "-118.28634407", "type": "edu", "country": "United States"}, {"name": "University of Amsterdam", "source_name": "University of Amsterdam", "street_adddress": "Institute for Logic, Language and Computation (ILLC), 107, Science Park, Oost-Watergraafsmeer, Amsterdam, Oost, Amsterdam, Noord-Holland, Nederland, 1098XG, Nederland", "lat": "52.35536550", "lng": "4.95016440", "type": "edu", "country": "Netherlands"}], "year": "2016", "pdf": ["https://ivi.fnwi.uva.nl/isis/publications/2016/AgharwalWCACV2016/AgharwalWCACV2016.pdf", "https://pure.uva.nl/ws/files/2779402/175913_AgharwalWCACV2016.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7477706", "http://doi.ieeecomputersociety.org/10.1109/WACV.2016.7477706", "http://doi.org/10.1109/WACV.2016.7477706"]}, {"id": "6e3e5f5fac0bfe1d54d6d414a1a8c2d8de586eee", "title": "Design Pseudo Ground Truth with Motion Cue for Unsupervised Video Object Segmentation.", "addresses": [{"name": "University of Southern California", "source_name": "University of Southern California", "street_adddress": "University of Southern California, Watt Way, Saint James Park, LA, Los Angeles County, California, 90089, USA", "lat": "34.02241490", "lng": "-118.28634407", "type": "edu", "country": "United States"}, {"name": "National Taiwan University", "source_name": "National Taiwan University", "street_adddress": "\u81fa\u5927;\u53f0\u5927, 1, \u7f85\u65af\u798f\u8def\u56db\u6bb5, \u5b78\u5e9c\u91cc, \u5927\u5b89\u5340, \u81fa\u5317\u5e02, 10617, \u81fa\u7063", "lat": "25.01682835", "lng": "121.53846924", "type": "edu", "country": "Taiwan"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.05206.pdf"], "doi": []}, {"id": "c486eeced06b1db66b7deb58496d71074b88fb86", "title": "ScratchDet: Exploring to Train Single-Shot Object Detectors from Scratch", "addresses": [{"name": "University of Chinese Academy of Sciences", "source_name": "University of Chinese Academy of Sciences", "street_adddress": "University of Chinese Academy of Sciences, UCAS, Yuquanlu, \u7389\u6cc9\u8def, \u7530\u6751, \u6d77\u6dc0\u533a, 100049, \u4e2d\u56fd", "lat": "39.90828040", "lng": "116.24585270", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.08425.pdf"], "doi": []}, {"id": "a3c93737a4497350768b0dda08dbc0826670dc5b", "title": "Diagnosing State-Of-The-Art Object Proposal Methods", "addresses": [{"name": "A*STAR", "source_name": "I2R, A*STAR, Singapore", "street_adddress": "1 Fusionopolis Way, #21-01 Connexis, Singapore 138632", "lat": "1.29889260", "lng": "103.78731070", "type": "edu", "country": "Singapore"}, {"name": "Nanyang Technological University", "source_name": "Nanyang Technological University", "street_adddress": "NTU, Faculty Avenue, Jurong West, Southwest, 637460, Singapore", "lat": "1.34841040", "lng": "103.68297965", "type": "edu", "country": "Singapore"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1507.04512.pdf"], "doi": []}, {"id": "bc2856e70ad3c8fe439dec6cc6a2e03d6e090fb7", "title": "What value high level concepts in vision to language problems ?", "addresses": [{"name": "University of Adelaide", "source_name": "University of Adelaide", "street_adddress": "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu", "country": "Australia"}], "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/ffcc/bb8218b3af88fb7ea9dcd89557cd0156fba7.pdf"], "doi": []}, {"id": "365117e2e47b83ec70014058de13d167619094ad", "title": "Adaptive Object Detection Using Adjacency and Zoom Prediction", "addresses": [{"name": "University of California, San Diego", "source_name": "University of California, San Diego", "street_adddress": "UCSD, 9500, Gilman Drive, Sixth College, University City, San Diego, San Diego County, California, 92093, USA", "lat": "32.87935255", "lng": "-117.23110049", "type": "edu", "country": "United States"}, {"name": "University of Illinois, Urbana-Champaign", "source_name": "University of Illinois, Urbana-Champaign", "street_adddress": "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1512.07711.pdf"], "doi": []}, {"id": "ad5950257e053b08657ea298f7b89ba358b8bfcf", "title": "Textually Enriched Neural Module Networks for Visual Question Answering", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.08697.pdf"], "doi": []}, {"id": "01efec88d36070dc3bc49f341a77476f74d373bc", "title": "Generation and Comprehension of Unambiguous Object Descriptions", "addresses": [{"name": "Google", "source_name": "Google, Inc.", "street_adddress": "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "lat": "37.42199990", "lng": "-122.08405750", "type": "company", "country": "United States"}, {"name": "UCLA", "source_name": "University of California, Los Angeles", "street_adddress": "Los Angeles, CA 90095, USA", "lat": "34.06892100", "lng": "-118.44518110", "type": "edu", "country": "United States"}, {"name": "University of Oxford", "source_name": "University of Oxford", "street_adddress": "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "lat": "51.75345380", "lng": "-1.25400997", "type": "edu", "country": "United Kingdom"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1511.02283.pdf"], "doi": []}, {"id": "2c3e7392b865b228f5d56ab025cd3123554be5e1", "title": "Linguistic Unit Discovery from Multi-Modal Inputs in Unwritten Languages: Summary of the \u201cSpeaking Rosetta\u201d JSALT 2017 Workshop", "addresses": [{"name": "Radboud University", "source_name": "Radboud University, Nijmegen, Netherlands", "street_adddress": "Houtlaan 4, 6525 XZ Nijmegen, Netherlands", "lat": "51.81670100", "lng": "5.86527200", "type": "edu", "country": "Netherlands"}, {"name": "University of Illinois", "source_name": "Advanced Digital Sciences Center (ADSC) of the University of Illinois, Singapore, Singapore", "street_adddress": "1 Create Way, 14-02 Create Tower, Singapore 138602", "lat": "1.30372570", "lng": "103.77377630", "type": "edu", "country": "Singapore"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.05092.pdf"], "doi": []}, {"id": "8b6493a65285fb72252221e7ef8ad1091bd96b32", "title": "TRAFFIC ANALYSIS USING VISUAL OBJECT DETECTION AND TRACKING", "addresses": [{"name": "University at Albany", "source_name": "University at Albany, SUNY, 12222, United States", "street_adddress": "1400 Washington Ave, Albany, NY 12222, USA", "lat": "42.68502730", "lng": "-73.82479030", "type": "edu", "country": "United States"}, {"name": "University of Chinese Academy of Sciences", "source_name": "University of Chinese Academy of Sciences", "street_adddress": "University of Chinese Academy of Sciences, UCAS, Yuquanlu, \u7389\u6cc9\u8def, \u7530\u6751, \u6d77\u6dc0\u533a, 100049, \u4e2d\u56fd", "lat": "39.90828040", "lng": "116.24585270", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/8b64/93a65285fb72252221e7ef8ad1091bd96b32.pdf"], "doi": []}, {"id": "7ce9e79cb63e33faa3be0c534664076e420dd7a1", "title": "Semantic Segmentation of Complex Road Environments from Aerial Images Using Convolutional Neural Networks", "addresses": [{"name": "US Army Engineer Research and Development Center, Vicksburg, MS", "source_name": "Information Technology Laboratory, U.S. Army Engineer Research and Development Center, Vicksburg, MS, United States", "street_adddress": "3909 Halls Ferry Rd, Vicksburg, MS 39180, USA", "lat": "32.30127170", "lng": "-90.87140670", "type": "mil", "country": "United States"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8622284", "http://doi.org/10.1109/BigData.2018.8622284"]}, {"id": "2281d8282dc6315eaa5c31821310c1a349ea18b0", "title": "Fast Efficient Object Detection Using Selective Attention", "addresses": [{"name": "RMIT University", "source_name": "RMIT University", "street_adddress": "RMIT University, 124, La Trobe Street, Melbourne City, City of Melbourne, Victoria, 3000, Australia", "lat": "-37.80874650", "lng": "144.96388750", "type": "edu", "country": "Australia"}, {"name": "University of Tokyo", "source_name": "University of Tokyo", "street_adddress": "\u6771\u4eac\u5927\u5b66 \u67cf\u30ad\u30e3\u30f3\u30d1\u30b9, \u5b66\u878d\u5408\u306e\u9053, \u67cf\u5e02, \u5343\u8449\u770c, \u95a2\u6771\u5730\u65b9, 277-8583, \u65e5\u672c", "lat": "35.90204480", "lng": "139.93622009", "type": "edu", "country": "Japan"}, {"name": "IBM Research, North Carolina", "source_name": "IBM Research", "street_adddress": "IBM, East Cornwallis Road, Research Triangle Park, Nelson, Durham County, North Carolina, 27709, USA", "lat": "35.90422720", "lng": "-78.85565763", "type": "company", "country": "United States"}, {"name": "University of Sydney", "source_name": "University of Sydney", "street_adddress": "USyd, Fisher Road, Camperdown, Sydney, NSW, 2006, Australia", "lat": "-33.88890695", "lng": "151.18943366", "type": "edu", "country": "Australia"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.07502.pdf"], "doi": []}, {"id": "7bfa04eb7ba2830a682a15206370abec49cffd2a", "title": "Learning Semantic Segmentation from Synthetic Data: A Geometrically Guided Input-Output Adaptation Approach", "addresses": [{"name": "Computer Vision Laboratory, ETH Zurich", "source_name": "Computer Vision Laboratory ETH Zurich, UK", "street_adddress": "Sternwartstrasse 7, 8092 Z\u00fcrich, Switzerland", "lat": "47.37723980", "lng": "8.55216180", "type": "edu", "country": "Switzerland"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.05040.pdf"], "doi": []}, {"id": "0871062654a6ddd18dba940009676aaa1230f879", "title": "Road Damage Detection And Classification In Smartphone Captured Images Using Mask R-CNN", "addresses": [{"name": "Indian Institute of Science Bangalore", "source_name": "Indian Institute of Science Bangalore", "street_adddress": "IISc, Gulmohar Marg, RMV Stage II - 1st Block, Aramane Nagara Ward, West Zone, Bengaluru, Bangalore Urban, Karnataka, 560012, India", "lat": "13.02223470", "lng": "77.56718325", "type": "edu", "country": "India"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.04535.pdf"], "doi": []}, {"id": "ce142b327974580b297fb84c2c1c799f838bdda5", "title": "VADRA: Visual Adversarial Domain Randomization and Augmentation", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.00491.pdf"], "doi": []}, {"id": "6b6afc9557dc0670bf2792bde4c4389ac52c707f", "title": "What Action Causes This? Towards Naive Physical Action-Effect Prediction", "addresses": [{"name": "Michigan State University", "source_name": "Michigan State University", "street_adddress": "Michigan State University, Farm Lane, East Lansing, Ingham County, Michigan, 48824, USA", "lat": "42.71856800", "lng": "-84.47791571", "type": "edu", "country": "United States"}, {"name": "Microsoft", "source_name": "Microsoft Corporation, Redmond, WA, USA", "street_adddress": "One Microsoft Way, Redmond, WA 98052, USA", "lat": "47.64233180", "lng": "-122.13693020", "type": "company", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/fa4f/7ec0d1a3e67c6170638a9502cbad81873b9c.pdf"], "doi": []}, {"id": "1536579229a334640735725e0b886f8d03aca1e8", "title": "Rank of Experts: Detection Network Ensemble", "addresses": [{"name": "Incheon National University", "source_name": "Incheon National University, Incheon, South Korea", "street_adddress": "119 Academy-ro, Songdo 1(il)-dong, Yeonsu-gu, Incheon, South Korea", "lat": "37.37505480", "lng": "126.63289980", "type": "edu", "country": "South Korea"}, {"name": "Electronics and Telecommunications Research Institute, Daejeon, South Korea", "source_name": "Electronics and Telecommunications Research Institute, Daejeon, South Korea", "street_adddress": "Electronics and Telecommunications Research Institute, Sinseong-dong, Daejeon, South Korea", "lat": "36.38376500", "lng": "127.36694000", "type": "edu", "country": "South Korea"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1712.00185.pdf"], "doi": []}, {"id": "19441b8be551e8134dd9eb33238309bc2de0a42f", "title": "Playing for Benchmarks", "addresses": [{"name": "TU Darmstadt", "source_name": "TU Darmstadt", "street_adddress": "Karolinenpl. 5, 64289 Darmstadt, Germany", "lat": "49.87482770", "lng": "8.65632810", "type": "edu", "country": "Germany"}, {"name": "Intel Labs", "source_name": "Intel Labs", "street_adddress": "4720 Forbes Ave, Pittsburgh, PA 15213, USA", "lat": "40.44397890", "lng": "-79.94646340", "type": "company", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1709.07322.pdf"], "doi": []}, {"id": "597bca76d9c983f0b71ff1143d80ea91bf97cb25", "title": "Semi-automatic video object segmentation by advanced manipulation of segmentation hierarchies", "addresses": [{"name": "Disney Research Zurich", "source_name": "Disney Research Zurich", "street_adddress": "Stampfenbachstrasse 48, 8006 Z\u00fcrich, Switzerland", "lat": "47.38047690", "lng": "8.54299640", "type": "company", "country": "Switzerland"}], "year": "2015", "pdf": ["http://www.disneyresearch.com/wp-content/uploads/Semi-Automatic-Video-Object-Segmentation-by-Advanced-Manipulation-of-Segmentation-Hierarchies-Paper.pdf", "https://s3-us-west-1.amazonaws.com/disneyresearch/wp-content/uploads/20150605225535/Semi-Automatic-Video-Object-Segmentation-by-Advanced-Manipulation-of-Segmentation-Hierarchies-Paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7153600", "http://doi.org/10.1109/CBMI.2015.7153600"]}, {"id": "db7e48d2655521c1a89b579d8cb839a95d6e6a14", "title": "Boosted Attention: Leveraging Human Attention for Image Captioning", "addresses": [{"name": "University of Minnesota", "source_name": "University of Minnesota", "street_adddress": "WeismanArt, 333, East River Parkway, Marcy-Holmes, Phillips, Minneapolis, Hennepin County, Minnesota, 55455, USA", "lat": "44.97308605", "lng": "-93.23708813", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/db7e/48d2655521c1a89b579d8cb839a95d6e6a14.pdf"], "doi": []}, {"id": "28bf62416b5b0f3ca87332b83c3944f515505f66", "title": "Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks", "addresses": [{"name": "University of Oxford", "source_name": "University of Oxford", "street_adddress": "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "lat": "51.75345380", "lng": "-1.25400997", "type": "edu", "country": "United Kingdom"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.12348.pdf"], "doi": []}, {"id": "3081b725e1764ec754bee1fe5487000b7adf7936", "title": "Slum Segmentation and Change Detection : A Deep Learning Approach", "addresses": [{"name": "Indian Institute of Science Bangalore", "source_name": "Indian Institute of Science Bangalore", "street_adddress": "IISc, Gulmohar Marg, RMV Stage II - 1st Block, Aramane Nagara Ward, West Zone, Bengaluru, Bangalore Urban, Karnataka, 560012, India", "lat": "13.02223470", "lng": "77.56718325", "type": "edu", "country": "India"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.07896.pdf"], "doi": []}, {"id": "35159d9a4b77f5f8ec63f96822316eb4f7aacb1b", "title": "Training Deep Networks with Structured Layers by Matrix Backpropagation", "addresses": [{"name": "Lund University", "source_name": "Lund University", "street_adddress": "TEM at Lund University, 9, Klostergatan, Stadsk\u00e4rnan, Centrum, Lund, Sk\u00e5ne, G\u00f6taland, 22222, Sverige", "lat": "55.70395710", "lng": "13.19020110", "type": "edu", "country": "Sweden"}, {"name": "University of Bonn", "source_name": "University of Bonn", "street_adddress": "Rheinische Friedrich-Wilhelms-Universit\u00e4t Bonn, Arkadenhof, Bonn-Zentrum, Stadtbezirk Bonn, Bonn, Regierungsbezirk K\u00f6ln, Nordrhein-Westfalen, 53113, Deutschland", "lat": "50.73381240", "lng": "7.10224650", "type": "edu", "country": "Germany"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1509.07838.pdf"], "doi": []}, {"id": "c32b09f20badd9ce04309d7c5ebea88336a3345a", "title": "Token-level and sequence-level loss smoothing for RNN language models", "addresses": [{"name": "INRIA", "source_name": "INRIA Grenoble Rhone-Alpes, Grenoble, France", "street_adddress": "655 Avenue de l'Europe, 38330 Montbonnot-Saint-Martin, France", "lat": "45.21788600", "lng": "5.80736900", "type": "edu", "country": "France"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.05062.pdf"], "doi": []}, {"id": "4cb2d5ea093d52a9dbb5141bde20cbea576efa24", "title": "A cascaded long short-term memory (LSTM) driven generic visual question answering (VQA)", "addresses": [{"name": "Queensland University of Technology", "source_name": "Queensland University of Technology", "street_adddress": "Queensland University of Technology, Macgregor Lane, Merthyr, South Brisbane, Brisbane, QLD, 4000, Australia", "lat": "-27.47715625", "lng": "153.02841004", "type": "edu", "country": "Australia"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8296600", "http://doi.org/10.1109/ICIP.2017.8296600"]}, {"id": "c45681fa9d9c36a6a196017ef283ac38904f91bb", "title": "Pixel-wise object tracking", "addresses": [{"name": "New York University", "source_name": "New York University", "street_adddress": "NYU, West 4th Street, NoHo Historic District, NoHo, Manhattan, Manhattan Community Board 2, New York County, NYC, New York, 10012, USA", "lat": "40.72925325", "lng": "-73.99625394", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1711.07377.pdf"], "doi": []}, {"id": "27e15e5ae496a228653b69195e7d62a758b73cfa", "title": "Adversarial Removal of Gender from Deep Image Representations", "addresses": [{"name": "University of Virginia", "source_name": "University of Virginia", "street_adddress": "University of Virginia, Rotunda Alley, Carr's Hill, Albemarle County, Virginia, 22904-4119, USA", "lat": "38.03536820", "lng": "-78.50353220", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.08489.pdf"], "doi": []}, {"id": "eddd45f8b2febf3800db7642357731cb63116acc", "title": "On the Effects of Spam Filtering and Incremental Learning for Web-Supervised Visual Concept Classification", "addresses": [{"name": "Leibniz Universit\u00e4t Hannover, Hannover, Germany", "source_name": "Leibniz Universit\u00e4t Hannover, Hannover, Germany", "street_adddress": "Welfengarten 1, 30167 Hannover, Germany", "lat": "52.38296410", "lng": "9.71969890", "type": "edu", "country": "Germany"}], "year": "2016", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=2912072"]}, {"id": "f2653257faa6d1b718a4cff004f4c7ad66d89c55", "title": "Advances in deep learning approaches for image tagging", "addresses": [{"name": "Microsoft", "source_name": "Microsoft Corporation, Redmond, WA, USA", "street_adddress": "One Microsoft Way, Redmond, WA 98052, USA", "lat": "47.64233180", "lng": "-122.13693020", "type": "company", "country": "United States"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/f265/3257faa6d1b718a4cff004f4c7ad66d89c55.pdf"], "doi": []}, {"id": "5b610d9492a940d3e64bbf0cea8de4622e07d8b4", "title": "Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning", "addresses": [{"name": "Cornell University", "source_name": "Cornell University", "street_adddress": "Cornell University, Forest Home Drive, Forest Home, Tompkins County, New York, 14853, USA", "lat": "42.45055070", "lng": "-76.47835130", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.06193.pdf"], "doi": []}, {"id": "0ab65b963f8b71e31bfec188056023147f75303e", "title": "SPNet: Superpixel Pyramid Network for Scene Parsing", "addresses": [{"name": "Beijing University of Technologyy", "source_name": "Faculty of Information Technology, Beijing University of Technologyy, Beijing, 100124, China", "street_adddress": "Chaoyang, China, 100124", "lat": "39.87161100", "lng": "116.47952900", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8623025"]}, {"id": "98025d3d44e9379736adb1228919272ded9298ae", "title": "Visual Question Answering Dataset for Bilingual Image Understanding: A Study of Cross-Lingual Transfer Using Attention Maps", "addresses": [{"name": "Tokyo Institute of Technology", "source_name": "Tokyo Institute of Technology", "street_adddress": "\u6771\u4eac\u5de5\u696d\u5927\u5b66, \u539a\u6728\u8857\u9053, \u7dd1\u533a, \u753a\u7530\u5e02, \u795e\u5948\u5ddd\u770c, \u95a2\u6771\u5730\u65b9, 226-0026, \u65e5\u672c", "lat": "35.51675380", "lng": "139.48342251", "type": "edu", "country": "Japan"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/9802/5d3d44e9379736adb1228919272ded9298ae.pdf"], "doi": []}, {"id": "eea248baa16162da661fbb9255e2cfcd5b9f0c05", "title": "Bachelor Project Image Captioning with Convolutional Neural Networks", "addresses": [{"name": "Czech Technical University", "source_name": "Czech Technical University", "street_adddress": "\u010cesk\u00e9 vysok\u00e9 u\u010den\u00ed technick\u00e9 v Praze, Resslova, Nov\u00e9 M\u011bsto, Praha, okres Hlavn\u00ed m\u011bsto Praha, Hlavn\u00ed m\u011bsto Praha, Praha, 11121, \u010cesko", "lat": "50.07642960", "lng": "14.41802312", "type": "edu", "country": "Czech Republic"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/eea2/48baa16162da661fbb9255e2cfcd5b9f0c05.pdf"], "doi": []}, {"id": "cc5d91b20c8769d1f040ff9a5166f76cc19d2d55", "title": "Self-Supervised Learning of Visual Features through Embedding Images into Text Topic Spaces", "addresses": [{"name": "CVIT, KCIS, IIIT Hyderabad, India", "source_name": "CVIT, KCIS, IIIT Hyderabad, India", "street_adddress": "IIIT, Gachibowli, Gachibowli, Hyderabad, Telangana 500032, India", "lat": "17.44509810", "lng": "78.34976780", "type": "edu", "country": "India"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.08631.pdf"], "doi": []}, {"id": "233b52f79d37363d924041e047c6b9d9609cbb17", "title": "Refining faster-RCNN for accurate object detection", "addresses": [{"name": "Kakao Corp.", "source_name": "Kakao corp., 242, Cheomdan-ro, Jeju-si, Jeju-do, Korea", "street_adddress": "242 Cheomdan-ro, Ara-dong, Cheju, Jeju-do, South Korea", "lat": "33.45073890", "lng": "126.57079340", "type": "company", "country": "South Korea"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7986913"]}, {"id": "32bc9334ad0edaec29540320b9f00c9a7aab81f8", "title": "Zero-Shot Object Detection", "addresses": [{"name": "University of Maryland", "source_name": "University of Maryland", "street_adddress": "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu", "country": "United States"}, {"name": "SRI International", "source_name": "SRI International", "street_adddress": "SRI International Building, West 1st Street, Menlo Park, San Mateo County, California, 94025, USA", "lat": "37.45857960", "lng": "-122.17560525", "type": "edu", "country": "United States"}, {"name": "NEC Labs, Cupertino, CA", "source_name": "NEC Labs, Cupertino, CA", "street_adddress": "10080 N Wolfe Rd # Sw3350, Cupertino, CA 95014, USA", "lat": "37.32391770", "lng": "-122.01296930", "type": "company", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.04340.pdf"], "doi": []}, {"id": "2d541bf669dda499f86b4dd2ac4e263134a3cd4c", "title": "Pixel Objectness", "addresses": [{"name": "University of Texas at Austin", "source_name": "University of Texas at Austin", "street_adddress": "University of Texas at Austin, 1, East 23rd Street, The Drag, Austin, Travis County, Texas, 78712, USA", "lat": "30.28415100", "lng": "-97.73195598", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1701.05349.pdf"], "doi": []}, {"id": "b9dc8cc479cacda1f23b91df00eb03f88cc0c260", "title": "Event Specific Multimodal Pattern Mining for Knowledge Base Construction", "addresses": [{"name": "Columbia Univeristy, New York, NY, USA", "source_name": "Columbia Univeristy, New York, NY, USA", "street_adddress": "116th St & Broadway, New York, NY 10027, United States", "lat": "40.80753550", "lng": "-73.96257270", "type": "edu", "country": "United States"}, {"name": "Rensselaer Polytechnic Institute", "source_name": "Rensselaer Polytechnic Institute", "street_adddress": "Rensselaer Polytechnic Institute, Sage Avenue, Downtown, City of Troy, Rensselaer County, New York, 12180, USA", "lat": "42.72984590", "lng": "-73.67950216", "type": "edu", "country": "United States"}], "year": "2016", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=2964287"]}, {"id": "9528e2e8c20517ab916f803c0371abb4f0ed488b", "title": "Shallow and Deep Convolutional Networks for Saliency Prediction", "addresses": [{"name": "Universitat Politecnica de Catalunya", "source_name": "Universitat Politcnica de Catalunya, EU, Spain", "street_adddress": "Campus Nord, Carrer de Jordi Girona, 1, 3, 08034 Barcelona, Spain", "lat": "41.38800400", "lng": "2.11328040", "type": "edu", "country": "Spain"}, {"name": "Dublin City University", "source_name": "DUBLIN CITY UNIVERSITY", "street_adddress": "Dublin City University Glasnevin Campus, Lower Car Park, Wad, Whitehall A ED, Dublin 9, Dublin, County Dublin, Leinster, D09 FW22, Ireland", "lat": "53.38522185", "lng": "-6.25740874", "type": "edu", "country": "Ireland"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1603.00845.pdf"], "doi": []}, {"id": "3ea8d289313b0fe14031ea0d29f517f92a3b0fd3", "title": "Probability-based Detection Quality (PDQ): A Probabilistic Approach to Detection Evaluation", "addresses": [{"name": "Queensland University of Technology (QUT)", "source_name": "Queensland University of Technology (QUT)", "street_adddress": "2 George St, Brisbane City QLD 4000, Australia", "lat": "-27.47735700", "lng": "153.02841500", "type": "edu", "country": "Australia"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.10800.pdf"], "doi": []}, {"id": "98735e57075ed6e8ef9d98d7ca4895013492e35b", "title": "Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbation", "addresses": [{"name": "Pennsylvania State University", "source_name": "Pennsylvania State University", "street_adddress": "Old Main, State College, PA 16801, USA", "lat": "40.79821330", "lng": "-77.85990840", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.10307.pdf"], "doi": []}, {"id": "36679b7ea9eb8418410db7a6e2f15aeaf1b8e059", "title": "Weakly Supervised Vehicle Detection in Satellite Images via Multiple Instance Ranking", "addresses": [{"name": "Xiamen University", "source_name": "Xiamen University", "street_adddress": "\u53a6\u95e8\u5927\u5b66, \u601d\u660e\u5357\u8def Siming South Road, \u601d\u660e\u533a, \u601d\u660e\u533a (Siming), \u53a6\u95e8\u5e02 / Xiamen, \u798f\u5efa\u7701, 361005, \u4e2d\u56fd", "lat": "24.43994190", "lng": "118.09301781", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8546267", "http://doi.ieeecomputersociety.org/10.1109/ICPR.2018.8546267", "http://doi.org/10.1109/ICPR.2018.8546267"]}, {"id": "0e0fbead3da9e16b03894b63efc6816fa3ef6d0e", "title": "Open-vocabulary Phrase Detection", "addresses": [{"name": "Boston University", "source_name": "Boston University", "street_adddress": "BU, Bay State Road, Fenway, Boston, Suffolk County, Massachusetts, 02215, USA", "lat": "42.35042530", "lng": "-71.10056114", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.07212.pdf"], "doi": []}, {"id": "51f5e7b847e65a4cd0634ed9efc6b19819742b70", "title": "End-to-End Airplane Detection Using Transfer Learning in Remote Sensing Images", "addresses": [{"name": "Huazhong University of Science and Technology", "source_name": "Huazhong University of Science and Technology", "street_adddress": "\u534e\u4e2d\u5927, \u73de\u55bb\u8def, \u4e1c\u6e56\u65b0\u6280\u672f\u5f00\u53d1\u533a, \u5173\u4e1c\u8857\u9053, \u4e1c\u6e56\u65b0\u6280\u672f\u5f00\u53d1\u533a\uff08\u6258\u7ba1\uff09, \u6d2a\u5c71\u533a (Hongshan), \u6b66\u6c49\u5e02, \u6e56\u5317\u7701, 430074, \u4e2d\u56fd", "lat": "30.50975370", "lng": "114.40628810", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/51f5/e7b847e65a4cd0634ed9efc6b19819742b70.pdf"], "doi": []}, {"id": "18f9a6045ba01cb079c4fa49a630d71bbd27cd92", "title": "A dataset of clinically generated visual questions and answers about radiology images", "addresses": [{"name": "Lister Hill National Center for Biomedical Communications", "source_name": "Lister Hill National Center for Biomedical Communications, U.S. National Library of Medicine, Bethesda, MD, USA", "street_adddress": "8600 Rockville Pike, Bethesda, MD 20894, USA", "lat": "38.99595080", "lng": "-77.09883230", "type": "gov", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/18f9/a6045ba01cb079c4fa49a630d71bbd27cd92.pdf"], "doi": []}, {"id": "1aac36122c07ecccfd59d912c22865801f096190", "title": "Face2Text: Collecting an Annotated Image Description Corpus for the Generation of Rich Face Descriptions", "addresses": [{"name": "University of Malta", "source_name": "University of Malta", "street_adddress": "University of Malta, Ring Road, Japanese Garden, L-Imsida, Malta, MSD 9027, Malta", "lat": "35.90232260", "lng": "14.48341890", "type": "edu", "country": "Malta"}, {"name": "University of Copenhagen", "source_name": "University of Copenhagen", "street_adddress": "K\u00f8benhavns Universitet, Krystalgade, K\u00f8dbyen, Vesterbro, K\u00f8benhavn, K\u00f8benhavns Kommune, Region Hovedstaden, 1165, Danmark", "lat": "55.68015020", "lng": "12.57232700", "type": "edu", "country": "Denmark"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.03827.pdf"], "doi": []}, {"id": "4c7659079b3df5bc746f76b2b1685b0b539832d6", "title": "Domain Adaptive Faster R-CNN for Object Detection in the Wild", "addresses": [{"name": "ETH Zurich", "source_name": "ETH Zurich", "street_adddress": "R\u00e4mistrasse 101, 8092 Z\u00fcrich, Switzerland", "lat": "47.37631300", "lng": "8.54766990", "type": "edu", "country": "Switzerland"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.03243.pdf"], "doi": []}, {"id": "3e16de062b9cdeecfcbda0de022f1fc4e741a2e6", "title": "Learning Visually-Grounded Semantics from Contrastive Adversarial Samples", "addresses": [{"name": "Peking University", "source_name": "Peking University", "street_adddress": "\u5317\u4eac\u5927\u5b66, 5\u53f7, \u9890\u548c\u56ed\u8def, \u7a3b\u9999\u56ed\u5357\u793e\u533a, \u6d77\u6dc0\u533a, \u5317\u4eac\u5e02, 100871, \u4e2d\u56fd", "lat": "39.99223790", "lng": "116.30393816", "type": "edu", "country": "China"}, {"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.10348.pdf"], "doi": []}, {"id": "838420cebfdad4e93221f8fe203c09155983141a", "title": "Subspace Alignment Based Domain Adaptation for RCNN Detector", "addresses": [{"name": "IIT Kanpur", "source_name": "IIT Kanpur", "street_adddress": "Kalyanpur, Kanpur, Uttar Pradesh 208016, India", "lat": "26.51233880", "lng": "80.23290000", "type": "edu", "country": "India"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1507.05578.pdf"], "doi": []}, {"id": "80eab89ff1c5c2cfc1ea62e2088cfc9b62de8d35", "title": "Emergent Translation in Multi-Agent Communication", "addresses": [{"name": "New York University", "source_name": "New York University", "street_adddress": "NYU, West 4th Street, NoHo Historic District, NoHo, Manhattan, Manhattan Community Board 2, New York County, NYC, New York, 10012, USA", "lat": "40.72925325", "lng": "-73.99625394", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1710.06922.pdf"], "doi": []}, {"id": "d983ce0a7d249bb85d14a66a89225a7136cc783b", "title": "A Single-shot Object Detector with Feature Aggragation and Enhancement", "addresses": [{"name": "Xi\u2019an Jiaotong University", "source_name": "Institute of Information and System Sciences, Faculty of Mathematics and Statistics, Xi\u2019an Jiaotong University, Xi\u2019an, China", "street_adddress": "28 Xianning W Rd, JiaoDa ShangYe JieQu, Beilin Qu, Xian Shi, Shaanxi Sheng, China", "lat": "34.25080300", "lng": "108.98369300", "type": "edu", "country": "China"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1902.02923.pdf"], "doi": []}, {"id": "e05b4f3757a3b33324e96f8b9b71e7d4eb5a1fa9", "title": "Controllable Top-down Feature Transformer", "addresses": [{"name": "University of California, San Diego", "source_name": "University of California, San Diego", "street_adddress": "UCSD, 9500, Gilman Drive, Sixth College, University City, San Diego, San Diego County, California, 92093, USA", "lat": "32.87935255", "lng": "-117.23110049", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1712.02400.pdf"], "doi": []}, {"id": "35498b80ee457e409c0962e03a6e170a917c83af", "title": "Look into Person: Self-Supervised Structure-Sensitive Learning and a New Benchmark for Human Parsing", "addresses": [{"name": "Sun Yat-Sen University", "source_name": "Sun Yat-Sen University", "street_adddress": "\u4e2d\u5927, \u65b0\u6e2f\u897f\u8def, \u9f99\u8239\u6ed8, \u5eb7\u4e50, \u6d77\u73e0\u533a (Haizhu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510105, \u4e2d\u56fd", "lat": "23.09461185", "lng": "113.28788994", "type": "edu", "country": "China"}, {"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.05446.pdf"], "doi": []}, {"id": "ba7890a5e9e51bf6181cc3c03144796cb3e5e254", "title": "Query : \" A man in a red sweatshirt performing breakdance \"", "addresses": [{"name": "Max Planck Institute for Informatics", "source_name": "Max Planck Institute for Informatics", "street_adddress": "MPII, E1 4, Campus, Universit\u00e4t, Sankt Johann, Bezirk Mitte, Saarbr\u00fccken, Regionalverband Saarbr\u00fccken, Saarland, 66123, Deutschland", "lat": "49.25795660", "lng": "7.04577417", "type": "edu", "country": "Germany"}, {"name": "University of California, Berkeley", "source_name": "University of California, Berkeley", "street_adddress": "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "lat": "37.86871260", "lng": "-122.25586815", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/ba78/90a5e9e51bf6181cc3c03144796cb3e5e254.pdf"], "doi": []}, {"id": "24ff2797234e26bb2ffd4558eb4412df0625687e", "title": "Mind Your Language: Abuse and Offense Detection for Code-Switched Languages", "addresses": [{"name": "Adobe Systems", "source_name": "Adobe Systems", "street_adddress": "343 Preston St, Ottawa, ON K1S 1N4, Canada", "lat": "45.40242130", "lng": "-75.70955410", "type": "edu", "country": "South Korea"}, {"name": "IIIT, Delhi", "source_name": "IIIT, Delhi", "street_adddress": "Okhla Industrial Estate, Phase III, Near Govind Puri Metro Station, New Delhi, Delhi 110020, India", "lat": "28.54562820", "lng": "77.27315050", "type": "edu", "country": "India"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.08652.pdf"], "doi": []}, {"id": "d31d4bb58f5dd67016e77352ac7600e2ba71e38f", "title": "Deep Learning Object Detection Methods for Ecological Camera Trap Data", "addresses": [{"name": "University of Guelph", "source_name": "University of Guelph, Guelph, Ontario, Canada", "street_adddress": "University of Guelph, Guelph, ON N1G 1Y4, Canada", "lat": "43.52937320", "lng": "-80.22525020", "type": "edu", "country": "Canada"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.10842.pdf"], "doi": []}, {"id": "faf73a84c9ce13cdfc9014fa89ecde9927c8c84a", "title": "Meta Networks for Neural Style Transfer", "addresses": [{"name": "Peking University", "source_name": "Peking University", "street_adddress": "\u5317\u4eac\u5927\u5b66, 5\u53f7, \u9890\u548c\u56ed\u8def, \u7a3b\u9999\u56ed\u5357\u793e\u533a, \u6d77\u6dc0\u533a, \u5317\u4eac\u5e02, 100871, \u4e2d\u56fd", "lat": "39.99223790", "lng": "116.30393816", "type": "edu", "country": "China"}, {"name": "National University of Singapore", "source_name": "National University of Singapore", "street_adddress": "NUS, Former 1936 British Outpost, Nepal Hill, Clementi, Southwest, 117542, Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu", "country": "Singapore"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1709.04111.pdf"], "doi": []}, {"id": "0020784920bf7ff6cb51d0b6061b99fd77161c3e", "title": "Learning Instance-Aware Object Detection Using Determinantal Point Processes", "addresses": [{"name": "Seoul National University", "source_name": "Seoul National University", "street_adddress": "\uc11c\uc6b8\ub300\ud559\uad50, \uc11c\ud638\ub3d9\ub85c, \uc11c\ub454\ub3d9, \uad8c\uc120\uad6c, \uc218\uc6d0\uc2dc, \uacbd\uae30, 16614, \ub300\ud55c\ubbfc\uad6d", "lat": "37.26728000", "lng": "126.98411510", "type": "edu", "country": "South Korea"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.10765.pdf"], "doi": []}, {"id": "d7ed61f57d26c192a75d088854d937d549efa37c", "title": "A Multi-Layer Approach to Superpixel-based Higher-order Conditional Random Field for Semantic Image Segmentation", "addresses": [{"name": "University of Texas at Arlington", "source_name": "University of Texas at Arlington", "street_adddress": "University of Texas at Arlington, South Nedderman Drive, Arlington, Tarrant County, Texas, 76010, USA", "lat": "32.72836830", "lng": "-97.11201835", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.02032.pdf"], "doi": []}, {"id": "528d1ad4725277b25f17c951c7aa637f58da1c9e", "title": "Text and Object Detection on Billboards", "addresses": [{"name": "Faculty of Information Technology, King Mongkut\u2019s Institute of Technology Ladkrabang, Bangkok, 10520, Thailand", "source_name": "Faculty of Information Technology, King Mongkut\u2019s Institute of Technology Ladkrabang, Bangkok, 10520, Thailand", "street_adddress": "1 Thanon Chalong Krung, Lat Krabang, Khet Lat Krabang, Krung Thep Maha Nakhon 10520, Thailand", "lat": "13.73095530", "lng": "100.78117740", "type": "edu", "country": "Thailand"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8534879", "http://doi.org/10.1109/iciteed.2018.8534879"]}, {"id": "0c5f9f5083b9fca4dcdbc4b122099ac1f630728b", "title": "Visual Semantic Role Labeling", "addresses": [{"name": "UC Berkeley", "source_name": "UC Berkeley", "street_adddress": "Berkeley, CA, USA", "lat": "37.87189920", "lng": "-122.25853990", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1505.04474.pdf"], "doi": []}, {"id": "f4af49a1ead3c81cc5d023878cb67c5646dd8a04", "title": "Learning a Recurrent Visual Representation for Image Caption Generation", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}, {"name": "Microsoft", "source_name": "Microsoft Corporation, Redmond, WA, USA", "street_adddress": "One Microsoft Way, Redmond, WA 98052, USA", "lat": "47.64233180", "lng": "-122.13693020", "type": "company", "country": "United States"}], "year": "2014", "pdf": ["https://arxiv.org/pdf/1411.5654.pdf"], "doi": []}, {"id": "73b5261948b9b1e998bc84edf061efd354dac479", "title": "Watching the TV Watchers", "addresses": [{"name": "Georgia Institute of Technology", "source_name": "Georgia Institute of Technology", "street_adddress": "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu", "country": "United States"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3214291"]}, {"id": "9d27197ecc73ac0c3a664499c62975068251bf9c", "title": "Studying Object Naming with Online Photos and Caption", "addresses": [{"name": "Australian National University", "source_name": "Australian National University", "street_adddress": "Canberra ACT 0200, Australia", "lat": "-35.27769990", "lng": "149.11852700", "type": "edu", "country": "Australia"}, {"name": "NICTA / Australian National University", "source_name": "NICTA / Australian National University, Canberra, Australia", "street_adddress": "Canberra ACT 0200, Australia", "lat": "-35.27769990", "lng": "149.11852700", "type": "edu", "country": "Australia"}], "year": "2015", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=2814817"]}, {"id": "72d7c465ef199a9670b3da7a318b0227f5cc3229", "title": "Visual Referring Expression Recognition: What Do Systems Actually Learn?", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.11818.pdf"], "doi": []}, {"id": "2c761495cf3dd320e229586f80f868be12360d4e", "title": "Revisiting Unreasonable Effectiveness of Data in Deep Learning Era", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.02968.pdf"], "doi": []}, {"id": "c0006a2268d299644e9f1b455601bcbe89ddc2b5", "title": "Semantic Video Segmentation by Gated Recurrent Flow Propagation", "addresses": [{"name": "Lund University", "source_name": "Lund University", "street_adddress": "TEM at Lund University, 9, Klostergatan, Stadsk\u00e4rnan, Centrum, Lund, Sk\u00e5ne, G\u00f6taland, 22222, Sverige", "lat": "55.70395710", "lng": "13.19020110", "type": "edu", "country": "Sweden"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1612.08871.pdf"], "doi": []}, {"id": "52a08919efb7a1d0f28eda82bacd9d495639a6b3", "title": "Neighbourhood Watch: Referring Expression Comprehension via Language-guided Graph Attention Networks", "addresses": [{"name": "University of Adelaide", "source_name": "University of Adelaide", "street_adddress": "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu", "country": "Australia"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.04794.pdf"], "doi": []}, {"id": "96fdc0131dc80ffa6d7b9c526e07f080414c54ec", "title": "1 Paying More A ention to Saliency : Image Captioning with Saliency and Context A ention", "addresses": [{"name": "University of Modena and Reggio Emilia", "source_name": "University of Modena and Reggio Emilia 41125, Modena, Italy", "street_adddress": "Via Universit\u00e0, 4, 41121 Modena MO, Italy", "lat": "44.64510460", "lng": "10.92792680", "type": "edu", "country": "Italy"}, {"name": "University of Udine", "source_name": "University of Udine, Italy", "street_adddress": "Universit\u00e0 degli Studi di Udine, Via delle Scienze, 206, 33100 Udine UD, Italy", "lat": "46.08107230", "lng": "13.21194740", "type": "edu", "country": "Italy"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/96fd/c0131dc80ffa6d7b9c526e07f080414c54ec.pdf"], "doi": []}, {"id": "59d0d7ccec2db66cad20cac5721ce54a8a058294", "title": "Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference", "addresses": [{"name": "Google", "source_name": "Google, Inc.", "street_adddress": "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "lat": "37.42199990", "lng": "-122.08405750", "type": "company", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1712.05877.pdf"], "doi": []}, {"id": "cb8f0d0e529e27c67f04e748266f084c07679755", "title": "Scene Image Synthesis from Natural Sentences Using Hierarchical Syntactic Analysis", "addresses": [{"name": "University of Tokyo", "source_name": "University of Tokyo", "street_adddress": "\u6771\u4eac\u5927\u5b66 \u67cf\u30ad\u30e3\u30f3\u30d1\u30b9, \u5b66\u878d\u5408\u306e\u9053, \u67cf\u5e02, \u5343\u8449\u770c, \u95a2\u6771\u5730\u65b9, 277-8583, \u65e5\u672c", "lat": "35.90204480", "lng": "139.93622009", "type": "edu", "country": "Japan"}], "year": "2016", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=2967193"]}, {"id": "a875c22ca30a99a013d728313420e418e398fafd", "title": "Strong-Weak Distribution Alignment for Adaptive Object Detection.", "addresses": [{"name": "Boston University", "source_name": "Boston University", "street_adddress": "BU, Bay State Road, Fenway, Boston, Suffolk County, Massachusetts, 02215, USA", "lat": "42.35042530", "lng": "-71.10056114", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.04798.pdf"], "doi": []}, {"id": "eb7ddda1bfa709497af9d0b2010d61d659a1816f", "title": "Training CNNs from Synthetic Data for Part Handling in Industrial Environments", "addresses": [{"name": "BTU Cottbus-Senftenberg, Cottbus, Germany", "source_name": "BTU Cottbus-Senftenberg, Chair of Automation Technology, Cottbus, Germany", "street_adddress": "Platz der Deutschen Einheit 1, 03046 Cottbus, Germany", "lat": "51.76698700", "lng": "14.32695000", "type": "edu", "country": "Germany"}, {"name": "Mercedes-Benz-Cars Daimler AG, Stuttgart, Germany", "source_name": "Mercedes-Benz-Cars Daimler AG, Stuttgart, Germany", "street_adddress": "Stuttgarter Str. 90, 70736 Fellbach, Germany", "lat": "48.81313800", "lng": "9.26374900", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8560470", "http://doi.org/10.1109/COASE.2018.8560470"]}, {"id": "3f93ad8732ed2e92f09536ad744d1111cab93522", "title": "Weakly Supervised Attention Learning for Textual Phrases Grounding", "addresses": [{"name": "Arizona State University", "source_name": "Arizona State University", "street_adddress": "Arizona State University Polytechnic campus, East Texas Avenue, Mesa, Maricopa County, Arizona, 85212, USA", "lat": "33.30715065", "lng": "-111.67653157", "type": "edu", "country": "United States"}, {"name": "University of California, Irvine", "source_name": "University of California, Irvine", "street_adddress": "Irvine, CA 92697, USA", "lat": "33.64049520", "lng": "-117.84429620", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.00545.pdf"], "doi": []}, {"id": "1c5b168c29d1c8b3dc753865c741b9f3c56d0555", "title": "Auto-Encoding Scene Graphs for Image Captioning", "addresses": [{"name": "Nanyang Technological University", "source_name": "Nanyang Technological University", "street_adddress": "NTU, Faculty Avenue, Jurong West, Southwest, 637460, Singapore", "lat": "1.34841040", "lng": "103.68297965", "type": "edu", "country": "Singapore"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.02378.pdf"], "doi": []}, {"id": "20af3b2a011eabfdc3021a5e78995c5ce592575c", "title": "Learning to Classify Fine-Grained Categories with Privileged Visual-Semantic Misalignment", "addresses": [{"name": "Tampere University of Technology", "source_name": "Tampere University of Technology", "street_adddress": "TTY, 10, Korkeakoulunkatu, Finninm\u00e4ki, Hervanta, Tampere, Tampereen seutukunta, Pirkanmaa, L\u00e4nsi- ja Sis\u00e4-Suomen aluehallintovirasto, L\u00e4nsi-Suomi, Manner-Suomi, 33720, Suomi", "lat": "61.44964205", "lng": "23.85877462", "type": "edu", "country": "Finland"}, {"name": "Chinese Academy of Sciences", "source_name": "Chinese Academy of Sciences", "street_adddress": "\u4e2d\u56fd\u79d1\u5b66\u9662\u5fc3\u7406\u7814\u7a76\u6240, 16, \u6797\u8403\u8def, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100101, \u4e2d\u56fd", "lat": "40.00447950", "lng": "116.37023800", "type": "edu", "country": "China"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7552556", "http://doi.ieeecomputersociety.org/10.1109/TBDATA.2016.2602231", "http://doi.org/10.1109/TBDATA.2016.2602231"]}, {"id": "193a69489230de1013dff9af1232e5379cc5282f", "title": "Intelligent Multimodal Framework for Human Assistive Robotics Based on Computer Vision Algorithms", "addresses": [{"name": "Universitat Polit\u00e8cnica de Val\u00e8ncia", "source_name": "Integrated Management Coastal Research Institute, Universitat Polit\u00e8cnica de Val\u00e8ncia, Val\u00e8ncia, Spain", "street_adddress": "Cam\u00ed de Vera, s/n, 46022 Val\u00e8ncia, Valencia, Spain", "lat": "39.48083760", "lng": "-0.34095220", "type": "edu", "country": "Spain"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/193a/69489230de1013dff9af1232e5379cc5282f.pdf"], "doi": []}, {"id": "f9f01af981f8d25f0c96ea06d88be62dabb79256", "title": "Terahertz Image Detection with the Improved Faster Region-Based Convolutional Neural Network", "addresses": [{"name": "Xidian University", "source_name": "Xidian University", "street_adddress": "Xidian University (New Campus), 266\u53f7, \u94f6\u674f\u5927\u9053, \u5357\u96f7\u6751, \u957f\u5b89\u533a (Chang'an), \u897f\u5b89\u5e02, \u9655\u897f\u7701, 710126, \u4e2d\u56fd", "lat": "34.12358250", "lng": "108.83546000", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/f9f0/1af981f8d25f0c96ea06d88be62dabb79256.pdf"], "doi": []}, {"id": "3b8a3b4ed02a15b2ba329727596b704889123a39", "title": "Deep affordance learning for single- and multiple-instance object detection", "addresses": [{"name": "Institute for Infocomm Research Agency for Science, Technology and Research (A\u2217STAR) 1 Fusionopolis Way, #21-01 Connexis (South Tower) Singapore 138632", "source_name": "Institute for Infocomm Research Agency for Science, Technology and Research (A\u2217STAR) 1 Fusionopolis Way, #21-01 Connexis (South Tower) Singapore 138632", "street_adddress": "1 Fusionopolis Way, #21-01 Connexis, Singapore 138632", "lat": "1.29889260", "lng": "103.78731070", "type": "edu", "country": "Singapore"}], "year": "2017", "pdf": ["https://oar.a-star.edu.sg/jspui/bitstream/123456789/2242/1/1570379510(2).pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8227883"]}, {"id": "ade2266f249f91767b0949ae600fe1048237e567", "title": "Maya Codical Glyph Segmentation: A Crowdsourcing Approach", "addresses": [{"name": "IDIAP Research Institute", "source_name": "IDIAP Research Institute", "street_adddress": "Idiap Research Institute, Parking Centre du parc, Martigny, Valais/Wallis, 1920, Schweiz/Suisse/Svizzera/Svizra", "lat": "46.10923700", "lng": "7.08453549", "type": "edu", "country": "Switzerland"}], "year": "2018", "pdf": ["http://publications.idiap.ch/downloads/papers/2017/Can_IEEETMM_2017.pdf", "http://publications.idiap.ch/downloads/reports/2016/Can_Idiap-RR-01-2017.pdf", "http://publications.idiap.ch/downloads/reports/2017/Can_Idiap-RR-01-2017.pdf", "https://infoscience.epfl.ch/record/225945/files/Can_Idiap-RR-01-2017.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8048535", "http://doi.org/10.1109/TMM.2017.2755985"]}, {"id": "989282f579fdca0ebdc890cf05cac88c29f9eb49", "title": "Benchmarking and Error Diagnosis in Multi-instance Pose Estimation", "addresses": [{"name": "California Institute of Technology", "source_name": "California Institute of Technology", "street_adddress": "California Institute of Technology, San Pasqual Walk, Madison Heights, Pasadena, Los Angeles County, California, 91126, USA", "lat": "34.13710185", "lng": "-118.12527487", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.05388.pdf"], "doi": []}, {"id": "403537a81f9c295ab5770fd82abe4f7542be9200", "title": "Driver Pose Estimation by Hybrid Convolutional Network Architecture", "addresses": [{"name": "National Engineering Laboratory for Visual Information Processing and Applications, Xi'an, China", "source_name": "National Engineering Laboratory for Visual Information Processing and Applications, Xi'an, Shaanxi, 710049, China", "street_adddress": "Jiaoda Commerce Block, Beilin, Xi'an, Shaanxi, China, 710049", "lat": "34.24845540", "lng": "108.98873940", "type": "gov", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8623392"]}, {"id": "1695d0112d2e2c6df8bbe1d6abe18a457eba90dc", "title": "Classification of Crash and Near-Crash Events from Dashcam Videos and Telematics", "addresses": [{"name": "Verizon Connect Research, Florence, Italy", "source_name": "Verizon Connect Research, via Paisiello 16-20, Florence, 50144, Italy", "street_adddress": "Via Giovanni Paisiello, 20, 50144 Firenze FI, Italy", "lat": "43.78205540", "lng": "11.23259400", "type": "edu", "country": "Italy"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8569952", "http://doi.org/10.1109/ITSC.2018.8569952"]}, {"id": "2fc6647858a1c7d6f51c4c57368e50677f30c0a9", "title": "Simultaneous object detection and localization using convolutional neural networks", "addresses": [{"name": "Mohammed V University in Rabat", "source_name": "LRIT-CNRST URAC 29, Mohammed V University in Rabat, Faculty of Sciences Rabat, Morocco", "street_adddress": "Angle avenues des FAR et Allal El Fassi, Hay Ryad, B.P. 8027 N.U.\u060c Rabat 10102, Morocco", "lat": "33.97023350", "lng": "-6.87447300", "type": "edu", "country": "Morocco"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8354045"]}, {"id": "4066f186ff58d300090c652925ed0aed3355efec", "title": "Solving Visual Madlibs with Multiple Cues", "addresses": [{"name": "University of Illinois, Urbana-Champaign", "source_name": "University of Illinois, Urbana-Champaign", "street_adddress": "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1608.03410.pdf"], "doi": []}, {"id": "5de5848dc3fc35e40420ffec70a407e4770e3a8d", "title": "WebVision Database: Visual Learning and Understanding from Web Data", "addresses": [{"name": "Computer Vision Laboratory, ETH Zurich", "source_name": "Computer Vision Laboratory ETH Zurich, UK", "street_adddress": "Sternwartstrasse 7, 8092 Z\u00fcrich, Switzerland", "lat": "47.37723980", "lng": "8.55216180", "type": "edu", "country": "Switzerland"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.02862.pdf"], "doi": []}, {"id": "7897f6a19d5211bf6387f5c9e141c90a0cc84566", "title": "One-shot Texture Segmentation", "addresses": [{"name": "University of T\u00fcbingen", "source_name": "University of T\u00fcbingen", "street_adddress": "Geschwister-Scholl-Platz, 72074 T\u00fcbingen, Germany", "lat": "48.52947820", "lng": "9.04377400", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.02654.pdf"], "doi": []}, {"id": "947f2d465df60ec49f441f02733edbeb81dde2f2", "title": "Fast Object Localization Using a CNN Feature Map Based Multi-Scale Search", "addresses": [{"name": "U.S. Army Research Laboratory, Adelphi, MD, USA", "source_name": "U.S. Army Research Laboratory, Adelphi, MD, USA", "street_adddress": "2800 Powder Mill Rd, Adelphi, MD 20783, USA", "lat": "39.02985870", "lng": "-76.96380270", "type": "mil", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1604.03517.pdf"], "doi": []}, {"id": "5b1e42e0ff78880dccdf4d90cfd5c6e3e577f923", "title": "Deep Feature Pyramid Reconfiguration for Object Detection", "addresses": [{"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.07993.pdf"], "doi": []}, {"id": "d7221695df4de3f34d5e4a877b71c14bc88760d2", "title": "Proposal Incorporating Structural Bias into Neural Networks", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/d722/1695df4de3f34d5e4a877b71c14bc88760d2.pdf"], "doi": []}, {"id": "dc5fc803b64b49217babab378efe29f35b697d2f", "title": "Directional Edge Boxes: Exploiting Inner Normal Direction Cues for Effective Object Proposal Generation", "addresses": [{"name": "Shanghai University", "source_name": "Shanghai University", "street_adddress": "\u4e0a\u6d77\u5927\u5b66, \u9526\u79cb\u8def, \u5927\u573a\u9547, \u5b9d\u5c71\u533a (Baoshan), \u4e0a\u6d77\u5e02, 201906, \u4e2d\u56fd", "lat": "31.32235655", "lng": "121.38400941", "type": "edu", "country": "China"}, {"name": "Huazhong University of Science and Technology", "source_name": "Huazhong University of Science and Technology", "street_adddress": "\u534e\u4e2d\u5927, \u73de\u55bb\u8def, \u4e1c\u6e56\u65b0\u6280\u672f\u5f00\u53d1\u533a, \u5173\u4e1c\u8857\u9053, \u4e1c\u6e56\u65b0\u6280\u672f\u5f00\u53d1\u533a\uff08\u6258\u7ba1\uff09, \u6d2a\u5c71\u533a (Hongshan), \u6b66\u6c49\u5e02, \u6e56\u5317\u7701, 430074, \u4e2d\u56fd", "lat": "30.50975370", "lng": "114.40628810", "type": "edu", "country": "China"}], "year": "2017", "pdf": [], "doi": ["http://doi.org/10.1007/s11390-017-1752-9"]}, {"id": "4f69ad0e52e37ba06db1c2b89c180f3ba331cc4a", "title": "Automatic Generation of Grounded Visual Questions", "addresses": [{"name": "Tianjin University", "source_name": "Tianjin University", "street_adddress": "\u6cf0\u5c71\u822a\u7a7a\u6e2f/\u5929\u6d25\u5927\u53a6, \u67a3\u884c\u8def, \u67a3\u884c \u9ad8\u738b\u5bfa, \u957f\u57ce\u8def, \u5927\u6cb3, \u5cb1\u5cb3\u533a (Daiyue), \u6cf0\u5b89\u5e02, \u5c71\u4e1c\u7701, 271000, \u4e2d\u56fd", "lat": "36.20304395", "lng": "117.05842113", "type": "edu", "country": "China"}, {"name": "NanKai University", "source_name": "College of Information Technical Science, NanKai University, CITS, TianJin, China", "street_adddress": "China, Tianjin, Nankai, Lequn N Rd, \u5357\u5f00\u5927\u5b66\u7efc\u5408\u5b9e\u9a8c\u697cA\u533a604", "lat": "39.10335500", "lng": "117.16492700", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1612.06530.pdf"], "doi": []}, {"id": "8060ae8621a20e5cbf6e974aab12ad34c37e9651", "title": "Intelligent surveillance system for abandoned luggage", "addresses": [{"name": "Orta Do\u011fu Teknik \u00dcniversitesi", "source_name": "Bilgisayar M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc, Orta Do\u011fu Teknik \u00dcniversitesi, Kuzey K\u0131br\u0131s Kamp\u00fcs\u00fc, Kalkanl\u0131, Kuzey K\u0131br\u0131s", "street_adddress": "Kalkanl\u0131, G\u00fczelyurt", "lat": "35.24908700", "lng": "33.02407600", "type": "edu", "country": "Turkey"}, {"name": "Elektrik - Elektronik M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc, Orta Do\u011fu Teknik \u00dcniversitesi, Kuzey K\u0131br\u0131s Kamp\u00fcs\u00fc, Kalkanl\u0131, Kuzey K\u0131br\u0131s", "source_name": "Elektrik - Elektronik M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc, Orta Do\u011fu Teknik \u00dcniversitesi, Kuzey K\u0131br\u0131s Kamp\u00fcs\u00fc, Kalkanl\u0131, Kuzey K\u0131br\u0131s", "street_adddress": "Kalkanl\u0131, G\u00fczelyurt", "lat": "35.24908700", "lng": "33.02407600", "type": "edu", "country": "Turkey"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8404327", "http://doi.org/10.1109/SIU.2018.8404327"]}, {"id": "87fa9d667f8f41eb04831356dc8d68b190693e5e", "title": "Chat-crowd: A Dialog-based Platform for Visual Layout Composition", "addresses": [{"name": "University of Virginia", "source_name": "University of Virginia", "street_adddress": "University of Virginia, Rotunda Alley, Carr's Hill, Albemarle County, Virginia, 22904-4119, USA", "lat": "38.03536820", "lng": "-78.50353220", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.04081.pdf"], "doi": []}, {"id": "250c0c37947d6dc32e1923c8df99bf64dc5d7e10", "title": "Implicit Negative Sub-Categorization and Sink Diversion for Object Detection", "addresses": [{"name": "360 AI Institute, Beijing, China", "source_name": "360 AI Institute, Beijing, China", "street_adddress": "Beijing, China", "lat": "39.90419990", "lng": "116.40739630", "type": "edu", "country": "China"}, {"name": "Chinese Academy of Sciences", "source_name": "Chinese Academy of Sciences", "street_adddress": "\u4e2d\u56fd\u79d1\u5b66\u9662\u5fc3\u7406\u7814\u7a76\u6240, 16, \u6797\u8403\u8def, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100101, \u4e2d\u56fd", "lat": "40.00447950", "lng": "116.37023800", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8125749", "http://doi.org/10.1109/TIP.2017.2779270", "https://www.ncbi.nlm.nih.gov/pubmed/29324412", "https://www.wikidata.org/entity/Q50087459"]}, {"id": "9bda68ea52bddf5365e3230761c95424ff1ddec5", "title": "SSP: Supervised Sparse Projections for Large-Scale Retrieval in High Dimensions", "addresses": [{"name": "University of British Columbia", "source_name": "University of British Columbia", "street_adddress": "University of British Columbia, Eagles Drive, Hawthorn Place, University Endowment Lands, Metro Vancouver, British Columbia, V6T, Canada", "lat": "49.25839375", "lng": "-123.24658161", "type": "edu", "country": "Canada"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/9bda/68ea52bddf5365e3230761c95424ff1ddec5.pdf"], "doi": []}, {"id": "b674dae73fcb236ee951d8ae8a36be527d232678", "title": "A sequential guiding network with attention for image captioning", "addresses": [{"name": "Beihang University", "source_name": "Beihang University", "street_adddress": "\u5317\u4eac\u822a\u7a7a\u822a\u5929\u5927\u5b66, 37, \u5b66\u9662\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100083, \u4e2d\u56fd", "lat": "39.98083330", "lng": "116.34101249", "type": "edu", "country": "China"}, {"name": "North China Electric Power University", "source_name": "North China Electric Power University", "street_adddress": "\u534e\u5317\u7535\u529b\u5927\u5b66, \u6c38\u534e\u5317\u5927\u8857, \u83b2\u6c60\u533a, \u4fdd\u5b9a\u5e02, \u83b2\u6c60\u533a (Lianchi), \u4fdd\u5b9a\u5e02, \u6cb3\u5317\u7701, 071000, \u4e2d\u56fd", "lat": "38.87604460", "lng": "115.49738730", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.00228.pdf"], "doi": []}, {"id": "9ded64e83d3ba51513ea00de27c0c770a02b0cf4", "title": "Image Classification using Transfer Learning from Siamese Networks based on Text Metadata Similarity", "addresses": [{"name": "Stanford University", "source_name": "Stanford University", "street_adddress": "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/9ded/64e83d3ba51513ea00de27c0c770a02b0cf4.pdf"], "doi": []}, {"id": "5fedae3bccf86052ed725e5925bb4ef47f9389c1", "title": "Word Prior Detection Segmentation Input \" The left guy \" Image : Query : a guy left the youth Energy", "addresses": [{"name": "University of Illinois, Urbana-Champaign", "source_name": "University of Illinois, Urbana-Champaign", "street_adddress": "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu", "country": "United States"}, {"name": "IBM T.J. Watson Research Center", "source_name": "IBM T. J. Watson Research, Center, New York, USA", "street_adddress": "1101 Kitchawan Rd, Yorktown Heights, NY 10598, USA", "lat": "41.20975160", "lng": "-73.80264670", "type": "company", "country": "United States"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/5fed/ae3bccf86052ed725e5925bb4ef47f9389c1.pdf"], "doi": []}, {"id": "5d1d45c89ec13f3b0a83078759bb1dfbac695102", "title": "Segmentation of Nuclei in Histopathology Images by Deep Regression of the Distance Map", "addresses": [{"name": "PSL Research University", "source_name": "MINES ParisTech, PSL Research University, CAOR - Centre de Robotique, 60 Bd St Michel 75006. Paris, France", "street_adddress": "60 Boulevard Saint-Michel, 75006 Paris, France", "lat": "48.84496370", "lng": "2.33961050", "type": "edu", "country": "France"}], "year": "2019", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8438559"]}, {"id": "8e368144360042aad69703a6bffd56e1e72f2af4", "title": "Revisiting Graph Construction for Fast Image Segmentation", "addresses": [{"name": "University of Florida", "source_name": "University of Florida", "street_adddress": "University of Florida, Southwest 16th Avenue, Diamond Village Apartments, City of Gainesville Municipal Boundaries, Alachua County, Florida, 32611, USA", "lat": "29.63287840", "lng": "-82.34901330", "type": "edu", "country": "United States"}, {"name": "University of Colorado, Denver", "source_name": "University of Colorado Denver", "street_adddress": "University of Colorado (Denver Auraria campus), Lawrence Way, Auraria, Denver, Denver County, Colorado, 80217, USA", "lat": "39.74287785", "lng": "-105.00596398", "type": "edu", "country": "United States"}, {"name": "Xiamen University", "source_name": "Xiamen University", "street_adddress": "\u53a6\u95e8\u5927\u5b66, \u601d\u660e\u5357\u8def Siming South Road, \u601d\u660e\u533a, \u601d\u660e\u533a (Siming), \u53a6\u95e8\u5e02 / Xiamen, \u798f\u5efa\u7701, 361005, \u4e2d\u56fd", "lat": "24.43994190", "lng": "118.09301781", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1702.05650.pdf"], "doi": []}, {"id": "82317f5ac40e982b8ec5b2634f1214db259ca325", "title": "Multi-oriented Scene Text Detection via Corner Localization and Region Segmentation", "addresses": [{"name": "Huazhong University of Science and Technology", "source_name": "Huazhong University of Science and Technology", "street_adddress": "\u534e\u4e2d\u5927, \u73de\u55bb\u8def, \u4e1c\u6e56\u65b0\u6280\u672f\u5f00\u53d1\u533a, \u5173\u4e1c\u8857\u9053, \u4e1c\u6e56\u65b0\u6280\u672f\u5f00\u53d1\u533a\uff08\u6258\u7ba1\uff09, \u6d2a\u5c71\u533a (Hongshan), \u6b66\u6c49\u5e02, \u6e56\u5317\u7701, 430074, \u4e2d\u56fd", "lat": "30.50975370", "lng": "114.40628810", "type": "edu", "country": "China"}, {"name": "National University of Singapore", "source_name": "National University of Singapore", "street_adddress": "NUS, Former 1936 British Outpost, Nepal Hill, Clementi, Southwest, 117542, Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu", "country": "Singapore"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.08948.pdf"], "doi": []}, {"id": "205e895e03969c96f3c482b0bd26308b16a12bd0", "title": "Image Captioning with an Intermediate Attributes Layer", "addresses": [{"name": "University of Adelaide", "source_name": "University of Adelaide", "street_adddress": "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu", "country": "Australia"}], "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/205e/895e03969c96f3c482b0bd26308b16a12bd0.pdf"], "doi": []}, {"id": "8b485d7683e54d2b9c5d5ddf4ed31770bb323dbe", "title": "Hybrid Task Cascade for Instance Segmentation", "addresses": [{"name": "Chinese University of Hong Kong", "source_name": "Chinese University of Hong Kong", "street_adddress": "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "lat": "22.41626320", "lng": "114.21093180", "type": "edu", "country": "China"}, {"name": "University of Sydney", "source_name": "University of Sydney", "street_adddress": "USyd, Fisher Road, Camperdown, Sydney, NSW, 2006, Australia", "lat": "-33.88890695", "lng": "151.18943366", "type": "edu", "country": "Australia"}, {"name": "SenseTime", "source_name": "SenseTime", "street_adddress": "China, Beijing Shi, Haidian Qu, WuDaoKou, Zhongguancun E Rd, 1\u53f7-7", "lat": "39.99300800", "lng": "116.32988200", "type": "company", "country": "China"}, {"name": "Nanyang Technological University", "source_name": "Nanyang Technological University", "street_adddress": "NTU, Faculty Avenue, Jurong West, Southwest, 637460, Singapore", "lat": "1.34841040", "lng": "103.68297965", "type": "edu", "country": "Singapore"}, {"name": "Zhejiang University", "source_name": "Zhejiang University", "street_adddress": "\u6d59\u6c5f\u5927\u5b66\u4e4b\u6c5f\u6821\u533a, \u4e4b\u6c5f\u8def, \u8f6c\u5858\u8857\u9053, \u897f\u6e56\u533a (Xihu), \u676d\u5dde\u5e02 Hangzhou, \u6d59\u6c5f\u7701, 310008, \u4e2d\u56fd", "lat": "30.19331415", "lng": "120.11930822", "type": "edu", "country": "China"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.07518.pdf"], "doi": []}, {"id": "637648198f9e91654ce27eaaa40512f2dc870fc1", "title": "Survey of Visual Question Answering: Datasets and Techniques", "addresses": [{"name": "Indian Institute of Technology Delhi", "source_name": "IIIT-Delhi, India", "street_adddress": "IIIT-Delhi, Mathura Road, Friends Colony, South East Delhi, Delhi, 110020, India", "lat": "28.54632595", "lng": "77.27325504", "type": "edu", "country": "India"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.03865.pdf"], "doi": []}, {"id": "b99588bd0393a60a0c627970ab6cab7338d08ca6", "title": "Semantic segmentation based on iterative contraction and merging", "addresses": [{"name": "National Chiao Tung University", "source_name": "National Chiao Tung University", "street_adddress": "NCTU;\u4ea4\u5927;\u4ea4\u901a\u5927\u5b78;\u4ea4\u5927\u5149\u5fa9\u6821\u5340;\u4ea4\u901a\u5927\u5b78\u5149\u5fa9\u6821\u5340, 1001, \u5927\u5b78\u8def, \u5149\u660e\u91cc, \u8d64\u571f\u5d0e, \u6771\u5340, \u65b0\u7af9\u5e02, 30010, \u81fa\u7063", "lat": "24.78676765", "lng": "120.99724412", "type": "edu", "country": "Taiwan"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8296488", "http://doi.org/10.1109/ICIP.2017.8296488"]}, {"id": "bb127015474fdc51d4cd6b4dda7176a8c778ea49", "title": "Examining the Impact of Blur on Recognition by Convolutional Networks.", "addresses": [{"name": "University of Chicago", "source_name": "THE UNIVERSITY OF CHICAGO", "street_adddress": "University of Chicago, South Ellis Avenue, Woodlawn, Chicago, Cook County, Illinois, 60637, USA", "lat": "41.78468745", "lng": "-87.60074933", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1611.05760.pdf"], "doi": []}, {"id": "e10ca043fae02972f19292efacddd8e0f216b70c", "title": "Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel Concepts", "addresses": [{"name": "Australian National University", "source_name": "Australian National University", "street_adddress": "Canberra ACT 0200, Australia", "lat": "-35.27769990", "lng": "149.11852700", "type": "edu", "country": "Australia"}, {"name": "CSIRO", "source_name": "CSIRO-Data61, Canberra, Australia", "street_adddress": "North Road Australian National University, The Australian National University, Acton ACT 2601, Australia", "lat": "-35.27769990", "lng": "149.11852700", "type": "edu", "country": "Australia"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.06049.pdf"], "doi": []}, {"id": "030ab7710a1307cfa2159686dabd07e2b239fb10", "title": "Crowd-Guided Ensembles: How Can We Choreograph Crowd Workers for Video Segmentation?", "addresses": [{"name": "Massachusetts Institute of Technology & ETH Z\u00fcrich", "source_name": "Massachusetts Institute of Technology & ETH Z\u00fcrich, Cambridge, MA, USA", "street_adddress": "77 Massachusetts Ave, Cambridge, MA 02139, USA", "lat": "42.36009100", "lng": "-71.09416000", "type": "edu", "country": "United States"}, {"name": "MIT", "source_name": "Massachusetts Institute", "street_adddress": "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu", "country": "United States"}, {"name": "Microsoft", "source_name": "Microsoft Corporation, Redmond, WA, USA", "street_adddress": "One Microsoft Way, Redmond, WA 98052, USA", "lat": "47.64233180", "lng": "-122.13693020", "type": "company", "country": "United States"}, {"name": "Qatar Computing Research Institute, Doha, Qatar", "source_name": "Qatar Computing Research Institute, Doha, Qatar", "street_adddress": "Ar-Rayyan, Qatar", "lat": "25.32159140", "lng": "51.42577380", "type": "company", "country": "Qatar"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3173685"]}, {"id": "a3d96844dc4fc3b51f3b8361c72f156800794251", "title": "BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation", "addresses": [{"name": "Microsoft", "source_name": "Microsoft Corporation, Redmond, WA, USA", "street_adddress": "One Microsoft Way, Redmond, WA 98052, USA", "lat": "47.64233180", "lng": "-122.13693020", "type": "company", "country": "United States"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1503.01640.pdf"], "doi": []}, {"id": "cf2ab0e639c19877596036603a3000ce7a1deb35", "title": "Self-supervised Learning of Motion Capture", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}, {"name": "University of Pittsburgh", "source_name": "University of Pittsburgh", "street_adddress": "University of Pittsburgh, Sutherland Drive, West Oakland, PGH, Allegheny County, Pennsylvania, 15240, USA", "lat": "40.44415295", "lng": "-79.96243993", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1712.01337.pdf"], "doi": []}, {"id": "8a12540c85c6835eb6fd36131107d82c50d2b8d0", "title": "Dense Image Representation with Spatial Pyramid VLAD Coding of CNN for Locally Robust Captioning", "addresses": [{"name": "University of Tokyo", "source_name": "University of Tokyo", "street_adddress": "\u6771\u4eac\u5927\u5b66 \u67cf\u30ad\u30e3\u30f3\u30d1\u30b9, \u5b66\u878d\u5408\u306e\u9053, \u67cf\u5e02, \u5343\u8449\u770c, \u95a2\u6771\u5730\u65b9, 277-8583, \u65e5\u672c", "lat": "35.90204480", "lng": "139.93622009", "type": "edu", "country": "Japan"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1603.09046.pdf"], "doi": []}, {"id": "697f0e24f24b016cef9474db485fe61a667f07b8", "title": "VISER: Visual Self-Regularization", "addresses": [{"name": "University of Washington", "source_name": "University of Washington", "street_adddress": "University of Washington, Rainier Vista, Montlake, University District, Seattle, King County, Washington, 98195, USA", "lat": "47.65432380", "lng": "-122.30800894", "type": "edu", "country": "United States"}, {"name": "Yahoo Research", "source_name": "Yahoo Research, USA", "street_adddress": "1680 N Glenville Dr # 100, Richardson, TX 75081, USA", "lat": "32.97000100", "lng": "-96.70543110", "type": "company", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.02568.pdf"], "doi": []}, {"id": "9138045b7164876f9c2d6c5891d1f3d13a147d84", "title": "Combining Weakly and Webly Supervised Learning for Classifying Food Images", "addresses": [{"name": "Rutgers University", "source_name": "Rutgers University", "street_adddress": "Rutgers Cook Campus - North, Biel Road, New Brunswick, Middlesex County, New Jersey, 08901, USA", "lat": "40.47913175", "lng": "-74.43168868", "type": "edu", "country": "United States"}, {"name": "SRI International", "source_name": "SRI International", "street_adddress": "SRI International Building, West 1st Street, Menlo Park, San Mateo County, California, 94025, USA", "lat": "37.45857960", "lng": "-122.17560525", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1712.08730.pdf"], "doi": []}, {"id": "0ee3aa2a78f9680bb65a823bd9195c879572ec1c", "title": "What Makes an Object Memorable?", "addresses": [{"name": "King Abdullah University of Science and Technology", "source_name": "King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia", "street_adddress": "Thuwal 23955, Saudi Arabia", "lat": "22.30946500", "lng": "39.10469700", "type": "edu", "country": "Saudi Arabia"}, {"name": "University of California, Berkeley", "source_name": "University of California, Berkeley", "street_adddress": "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "lat": "37.86871260", "lng": "-122.25586815", "type": "edu", "country": "United States"}, {"name": "MIT", "source_name": "Massachusetts Institute", "street_adddress": "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu", "country": "United States"}, {"name": "University of California, Merced", "source_name": "University of California, Merced", "street_adddress": "University of California, Merced, Ansel Adams Road, Merced County, California, USA", "lat": "37.36566745", "lng": "-120.42158888", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["http://faculty.ucmerced.edu/mhyang/papers/iccv15_memorability.pdf", "http://openaccess.thecvf.com/content_iccv_2015/papers/Dubey_What_Makes_an_ICCV_2015_paper.pdf", "http://people.csail.mit.edu/khosla/papers/iccv2015_dubey.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Dubey_What_Makes_an_ICCV_2015_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410487", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2015.130", "http://doi.org/10.1109/ICCV.2015.130"]}, {"id": "bddf7da5a21a5d1915cc9ee784223adadbe0aec4", "title": "Question action relevance and editing for visual question answering", "addresses": [{"name": "George Mason University", "source_name": "George Mason University", "street_adddress": "George Mason University, Aquia Creek Lane, Country Club View, Blue Oaks, Fairfax County, Virginia, 22030-9998, USA", "lat": "38.83133325", "lng": "-77.30798839", "type": "edu", "country": "United States"}, {"name": "Dipartimento di Informatica, Universit\u00e0 di Salerno, Fisciano, Italy", "source_name": "Dipartimento di Informatica, Universit\u00e0 di Salerno, Fisciano, Italy", "street_adddress": "Universit\u00e0 di Salerno Via Papa, Via Giovanni Paolo II, 132, 84084 Fisciano SA, Italy", "lat": "40.77434920", "lng": "14.78901500", "type": "edu", "country": "Italy"}], "year": "2018", "pdf": [], "doi": ["http://doi.org/10.1007/s11042-018-6097-z"]}, {"id": "76b6577f47d6782bf75aca04e361a7b7381b4a84", "title": "Measuring and Modifying the Intrinsic Memorability of Images", "addresses": [{"name": "MIT", "source_name": "Massachusetts Institute", "street_adddress": "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/76b6/577f47d6782bf75aca04e361a7b7381b4a84.pdf"], "doi": []}, {"id": "41a96329d93e7b06ebd6b3a761cc0d50375c5f15", "title": "Visual Learning Beyond Direct Supervision", "addresses": [{"name": "University of California at Berkeley", "source_name": "International Computer Science Institute, University of California at Berkeley, Berkeley, USA", "street_adddress": "1947 Center St, Berkeley, CA 94704, USA", "lat": "37.87015430", "lng": "-122.27123120", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://www2.eecs.berkeley.edu/Pubs/TechRpts/2018/EECS-2018-128.pdf"], "doi": ["https://www.base-search.net/Record/2a66cc65fb84214dedf1e3019655a0c160d394ee4e1457c1e1301e57cce6ca94"]}, {"id": "8e325b234e9cb67c285fc256c7e51d5e326952d1", "title": "Single-Shot Bidirectional Pyramid Networks for High-Quality Object Detection", "addresses": [{"name": "Singapore Management University", "source_name": "Singapore Management University", "street_adddress": "Singapore Management University, Fort Canning Tunnel, Clarke Quay, City Hall, Singapore, Central, 178895, Singapore", "lat": "1.29500195", "lng": "103.84909214", "type": "edu", "country": "Singapore"}, {"name": "Zhejiang University", "source_name": "Zhejiang University", "street_adddress": "\u6d59\u6c5f\u5927\u5b66\u4e4b\u6c5f\u6821\u533a, \u4e4b\u6c5f\u8def, \u8f6c\u5858\u8857\u9053, \u897f\u6e56\u533a (Xihu), \u676d\u5dde\u5e02 Hangzhou, \u6d59\u6c5f\u7701, 310008, \u4e2d\u56fd", "lat": "30.19331415", "lng": "120.11930822", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.08208.pdf"], "doi": []}, {"id": "b90efd4e0a2267b1c47d31ead3c860acb4364cee", "title": "MetaAnchor: Learning to Detect Objects with Customized Anchors", "addresses": [{"name": "Fudan University", "source_name": "Fudan University", "street_adddress": "\u590d\u65e6\u5927\u5b66, 220, \u90af\u90f8\u8def, \u4e94\u89d2\u573a\u8857\u9053, \u6768\u6d66\u533a, \u4e0a\u6d77\u5e02, 200433, \u4e2d\u56fd", "lat": "31.30104395", "lng": "121.50045497", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.00980.pdf"], "doi": []}, {"id": "0489a21c77d1646ea3af48d678c3ad9645eef2a9", "title": "Large-Scale Sparse Learning From Noisy Tags for Semantic Segmentation", "addresses": [{"name": "Renmin University of China", "source_name": "Beijing Key Laboratory of Big Data Management and Analysis Methods, Renmin University of China, Beijing, 100872, China", "street_adddress": "59 Zhongguancun St, Haidian Qu, China, 100872", "lat": "39.96960620", "lng": "116.31881450", "type": "edu", "country": "China"}, {"name": "Peking University", "source_name": "Peking University", "street_adddress": "\u5317\u4eac\u5927\u5b66, 5\u53f7, \u9890\u548c\u56ed\u8def, \u7a3b\u9999\u56ed\u5357\u793e\u533a, \u6d77\u6dc0\u533a, \u5317\u4eac\u5e02, 100871, \u4e2d\u56fd", "lat": "39.99223790", "lng": "116.30393816", "type": "edu", "country": "China"}], "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7765089", "https://www.ncbi.nlm.nih.gov/pubmed/27925605"]}, {"id": "fa2d3c78981ef0e19557e51d85b6dda05345c380", "title": "Detection of valuable left-behind items in vehicle cabins", "addresses": [{"name": "Jaguar Land Rover Research, Coventry, UK", "source_name": "Jaguar Land Rover Research, Coventry, UK", "street_adddress": "Viscount Centre C, Milburn Hill Rd, Coventry CV4 7HS, United Kingdom", "lat": "52.38558050", "lng": "-1.56086400", "type": "company", "country": "United Kingdom"}, {"name": "University of Bristol", "source_name": "University of Bristol", "street_adddress": "Victoria Rooms, Whiteladies Road, Cliftonwood, Spike Island, Bristol, City of Bristol, South West England, England, BS8 2PY, UK", "lat": "51.45848370", "lng": "-2.60977520", "type": "edu", "country": "United Kingdom"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7995862", "http://doi.org/10.1109/IVS.2017.7995862"]}, {"id": "0000fcfd467a19cf0e59169c2f07d730a0f3a8b9", "title": "Exploring Visual Relationship for Image Captioning", "addresses": [{"name": "Sun Yat-Sen University", "source_name": "Sun Yat-Sen University", "street_adddress": "\u4e2d\u5927, \u65b0\u6e2f\u897f\u8def, \u9f99\u8239\u6ed8, \u5eb7\u4e50, \u6d77\u73e0\u533a (Haizhu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510105, \u4e2d\u56fd", "lat": "23.09461185", "lng": "113.28788994", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.07041.pdf"], "doi": []}, {"id": "c93e26b52cb22382ed2627bf32f86fa18d034cbf", "title": "Discriminative Learning of Open-Vocabulary Object Retrieval and Localization by Negative Phrase Augmentation", "addresses": [{"name": "University of Tokyo", "source_name": "University of Tokyo", "street_adddress": "\u6771\u4eac\u5927\u5b66 \u67cf\u30ad\u30e3\u30f3\u30d1\u30b9, \u5b66\u878d\u5408\u306e\u9053, \u67cf\u5e02, \u5343\u8449\u770c, \u95a2\u6771\u5730\u65b9, 277-8583, \u65e5\u672c", "lat": "35.90204480", "lng": "139.93622009", "type": "edu", "country": "Japan"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.09509.pdf"], "doi": []}, {"id": "57922243faec5a60473fb9ec32d9adcd94fb6cc8", "title": "Identifying Most Walkable Direction for Navigation in an Outdoor Environment", "addresses": [{"name": "University of Washington", "source_name": "University of Washington", "street_adddress": "University of Washington, Rainier Vista, Montlake, University District, Seattle, King County, Washington, 98195, USA", "lat": "47.65432380", "lng": "-122.30800894", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1711.08040.pdf"], "doi": []}, {"id": "89588a697c8b81e38d3793db5055a65c4abc4845", "title": "Swap Retrieval: Retrieving Images of Cats When the Query Shows a Dog", "addresses": [{"name": "KULeuven, Leuven, Belgium", "source_name": "KULeuven, Leuven, Belgium", "street_adddress": "Oude Markt 13, 3000 Leuven, Belgium", "lat": "50.87795450", "lng": "4.70029530", "type": "edu", "country": "Spain"}], "year": "2015", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=2749373"]}, {"id": "1b793cc5dceb98c95e816aebc2252205bfd71569", "title": "ADNet: A Deep Network for Detecting Adverts", "addresses": [{"name": "Trinity College Dublin", "source_name": "Trinity College Dublin, Dublin 2, Ireland", "street_adddress": "College Green, Dublin 2, Co. Dublin, Ireland", "lat": "53.34379350", "lng": "-6.25457160", "type": "edu", "country": "Ireland"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.04115.pdf"], "doi": []}, {"id": "532c089b43983935e1001c5e35aa35440263beaf", "title": "G-Distillation: Reducing Overconfident Errors on Novel Samples", "addresses": [{"name": "University of Illinois, Urbana-Champaign", "source_name": "University of Illinois, Urbana-Champaign", "street_adddress": "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.03166.pdf"], "doi": []}, {"id": "20e24a40dc855fa69aa3d85b4bfdcfb8c9dadb74", "title": "Multi-Networks Joint Learning for Large-Scale Cross-Modal Retrieval", "addresses": [{"name": "University of Chinese Academy of Sciences", "source_name": "University of Chinese Academy of Sciences", "street_adddress": "University of Chinese Academy of Sciences, UCAS, Yuquanlu, \u7389\u6cc9\u8def, \u7530\u6751, \u6d77\u6dc0\u533a, 100049, \u4e2d\u56fd", "lat": "39.90828040", "lng": "116.24585270", "type": "edu", "country": "China"}, {"name": "University of Texas at San Antonio", "source_name": "University of Texas at San Antonio", "street_adddress": "UTSA, Paseo Principal, San Antonio, Bexar County, Texas, 78249-1620, USA", "lat": "29.58333105", "lng": "-98.61944505", "type": "edu", "country": "United States"}], "year": "2017", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3123317"]}, {"id": "04e2b2eab1966ffb0079685baf169d4d7ad4ec8c", "title": "Detecting Sex From Handwritten Examples", "addresses": [{"name": "Independent University Bangladesh", "source_name": "Fab Lab, Independent University Bangladesh, Dhaka, Bangladesh", "street_adddress": "Independent University, Bangladesh Plot 16, \u0986\u09ab\u09a4\u09be\u09ac \u0989\u09a6\u09cd\u09a6\u09bf\u09a8 \u0986\u09b9\u09ae\u09c7\u09a6 \u09b0\u09cb\u09a1, \u09a2\u09be\u0995\u09be, Bangladesh", "lat": "23.81524690", "lng": "90.42796720", "type": "edu", "country": "Bangladesh"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8541214", "http://doi.org/10.1109/icscan.2018.8541214"]}, {"id": "00e19d93780ecf8f807c510a1105749d5bb1a2f3", "title": "Image Description using Deep Neural Networks", "addresses": [{"name": "Rochester Institute of Technology", "source_name": "Rochester Institute of Technology", "street_adddress": "Rochester Institute of Technology (RIT), 1, Lomb Memorial Drive, Bailey, Henrietta Town, Monroe County, New York, 14623, USA", "lat": "43.08250655", "lng": "-77.67121663", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/00e1/9d93780ecf8f807c510a1105749d5bb1a2f3.pdf"], "doi": []}, {"id": "6f3a1216e984c78e7374b3b7ab05612544d345eb", "title": "DeRPN: Taking a further step toward more general object detection", "addresses": [{"name": "South China University of Technology", "source_name": "South China University of Technology", "street_adddress": "\u534e\u5357\u7406\u5de5\u5927\u5b66, \u5927\u5b66\u57ce\u4e2d\u73af\u4e1c\u8def, \u5e7f\u5dde\u5927\u5b66\u57ce, \u65b0\u9020, \u756a\u79ba\u533a (Panyu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510006, \u4e2d\u56fd", "lat": "23.05020420", "lng": "113.39880323", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.06700.pdf"], "doi": []}, {"id": "e2d1e72fdb7e0b7a3ebb9ddc4cc161566ab74de2", "title": "Person Search via a Mask-Guided Two-Stream CNN Model", "addresses": [{"name": "Nanjing University", "source_name": "Nanjing University", "street_adddress": "NJU, \u4e09\u6c5f\u8def, \u9f13\u697c\u533a, \u5357\u4eac\u5e02, \u6c5f\u82cf\u7701, 210093, \u4e2d\u56fd", "lat": "32.05659570", "lng": "118.77408833", "type": "edu", "country": "China"}, {"name": "University of Sydney", "source_name": "University of Sydney", "street_adddress": "USyd, Fisher Road, Camperdown, Sydney, NSW, 2006, Australia", "lat": "-33.88890695", "lng": "151.18943366", "type": "edu", "country": "Australia"}, {"name": "Tencent", "source_name": "Tencent", "street_adddress": "Ke Ji Zhong Yi Lu, Nanshan Qu, Shenzhen Shi, Guangdong Sheng, China, 518057", "lat": "22.54471540", "lng": "113.93571640", "type": "company", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.08107.pdf"], "doi": []}, {"id": "10706113b871354248beb37fe5bb2f31925f7a68", "title": "A Vision-based Transfer Learning Approach for Recognizing Behavioral Symptoms in People with Dementia", "addresses": [{"name": "Edge Hill University", "source_name": "Edge Hill University", "street_adddress": "Edge Hill University, St Helens Road, West Lancashire, Lancs, North West England, England, L39 4QP, UK", "lat": "53.55821550", "lng": "-2.86904651", "type": "edu", "country": "United Kingdom"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8639371"]}, {"id": "3921afded8bc8471d784df86f64432fb14b8ef58", "title": "Egocentric Gesture Recognition for Head-Mounted AR devices", "addresses": [{"name": "Trinity College Dublin", "source_name": "Trinity College Dublin, Dublin 2, Ireland", "street_adddress": "College Green, Dublin 2, Co. Dublin, Ireland", "lat": "53.34379350", "lng": "-6.25457160", "type": "edu", "country": "Ireland"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.05380.pdf"], "doi": []}, {"id": "d9519d66f9844fcf306cc205593a55cf01090633", "title": "Image2song: Song Retrieval via Bridging Image Content and Lyric Words", "addresses": [{"name": "Chinese Academy of Sciences", "source_name": "Chinese Academy of Sciences", "street_adddress": "\u4e2d\u56fd\u79d1\u5b66\u9662\u5fc3\u7406\u7814\u7a76\u6240, 16, \u6797\u8403\u8def, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100101, \u4e2d\u56fd", "lat": "40.00447950", "lng": "116.37023800", "type": "edu", "country": "China"}, {"name": "Northwestern Polytechnical University", "source_name": "Northwestern Polytechnical University", "street_adddress": "\u897f\u5317\u5de5\u4e1a\u5927\u5b66 \u53cb\u8c0a\u6821\u533a, 127\u53f7, \u53cb\u8c0a\u897f\u8def, \u957f\u5b89\u8def, \u7891\u6797\u533a (Beilin), \u897f\u5b89\u5e02, \u9655\u897f\u7701, 710072, \u4e2d\u56fd", "lat": "34.24691520", "lng": "108.91061982", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.05851.pdf"], "doi": []}, {"id": "b5bfe824fc49fe78b538ac15f21c4cd6a9d44347", "title": "Image Caption with Synchronous Cross-Attention", "addresses": [{"name": "Beijing University of Posts and Telecommunications", "source_name": "Beijing University of Posts and Telecommunications", "street_adddress": "\u5317\u4eac\u90ae\u7535\u5927\u5b66, \u897f\u571f\u57ce\u8def, \u6d77\u6dc0\u533a, \u5317\u4eac\u5e02, 100082, \u4e2d\u56fd", "lat": "39.96014880", "lng": "116.35193921", "type": "edu", "country": "China"}], "year": "2017", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3126714"]}, {"id": "6220d0424bc7357e7e381d59baecdff91062ba81", "title": "A Fully Convolutional Two-Stream Fusion Network for Interactive Image Segmentation", "addresses": [{"name": "Loughborough University", "source_name": "Loughborough University", "street_adddress": "Computer Science, University Road, Charnwood, Leicestershire, East Midlands, England, LE11 3TP, UK", "lat": "52.76635770", "lng": "-1.22924610", "type": "edu", "country": "United Kingdom"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1807.02480.pdf"], "doi": []}, {"id": "c8671a739a95f57946a625c3eada1f4addc60aea", "title": "Transferable Interactiveness Prior for Human-Object Interaction Detection", "addresses": [{"name": "Shanghai Jiao Tong University", "source_name": "Shanghai Jiao Tong University", "street_adddress": "\u4e0a\u6d77\u4ea4\u901a\u5927\u5b66\uff08\u5f90\u6c47\u6821\u533a\uff09, \u6dee\u6d77\u897f\u8def, \u756a\u79ba\u5c0f\u533a, \u5e73\u9634\u6865, \u5f90\u6c47\u533a, \u4e0a\u6d77\u5e02, 200052, \u4e2d\u56fd", "lat": "31.20081505", "lng": "121.42840681", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.08264.pdf"], "doi": []}, {"id": "e38c7d4f8a4399f402ab6bb364ec662fe897bed1", "title": "PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentation", "addresses": [{"name": "RWTH Aachen University", "source_name": "RWTH Aachen University", "street_adddress": "RWTH Aachen, Mies-van-der-Rohe-Stra\u00dfe, K\u00f6nigsh\u00fcgel, Aachen-Mitte, Aachen, St\u00e4dteregion Aachen, Regierungsbezirk K\u00f6ln, Nordrhein-Westfalen, 52074, Deutschland", "lat": "50.77917030", "lng": "6.06728733", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.09190.pdf"], "doi": []}, {"id": "d3bbd57899d938e8c4bcafbbda10ceb59638e4db", "title": "Skip-Thought Vectors", "addresses": [{"name": "University of Toronto", "source_name": "University of Toronto", "street_adddress": "University of Toronto, St. George Street, Bloor Street Culture Corridor, Old Toronto, Toronto, Ontario, M5S 1A5, Canada", "lat": "43.66333345", "lng": "-79.39769975", "type": "edu", "country": "Canada"}, {"name": "MIT", "source_name": "Massachusetts Institute", "street_adddress": "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1506.06726.pdf"], "doi": []}, {"id": "11da2d589485685f792a8ac79d4c2e589e5f77bd", "title": "Show and tell: A neural image caption generator", "addresses": [{"name": "Google", "source_name": "Google, Inc.", "street_adddress": "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "lat": "37.42199990", "lng": "-122.08405750", "type": "company", "country": "United States"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1411.4555.pdf"], "doi": []}, {"id": "0ae247153afd87f98829359a8b5df0f68d788d75", "title": "A Corpus for Reasoning About Natural Language Grounded in Photographs", "addresses": [{"name": "Cornell University", "source_name": "Cornell University", "street_adddress": "Cornell University, Forest Home Drive, Forest Home, Tompkins County, New York, 14853, USA", "lat": "42.45055070", "lng": "-76.47835130", "type": "edu", "country": "United States"}, {"name": "University of Maryland", "source_name": "University of Maryland", "street_adddress": "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.00491.pdf"], "doi": []}, {"id": "30795da8026e875faaffa3d6f2fa03c9c5d14c55", "title": "Richer Semantic Visual and Language Representation for Video Captioning", "addresses": [{"name": "Tongji University", "source_name": "Tongji University", "street_adddress": "\u540c\u6d4e\u5927\u5b66, 1239, \u56db\u5e73\u8def, \u6c5f\u6e7e, \u8679\u53e3\u533a, \u4e0a\u6d77\u5e02, 200092, \u4e2d\u56fd", "lat": "31.28473925", "lng": "121.49694909", "type": "edu", "country": "China"}], "year": "2017", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3127895"]}, {"id": "2675a66b3f8743cf0551f284244af4f24537c19b", "title": "Learning Visually Grounded Sentence Representations", "addresses": [{"name": "UC Berkeley", "source_name": "UC Berkeley", "street_adddress": "Berkeley, CA, USA", "lat": "37.87189920", "lng": "-122.25853990", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1707.06320.pdf"], "doi": []}, {"id": "5f79398057bf0bbda9ff50067bc1f2950c2a2266", "title": "Progressive Neural Architecture Search", "addresses": [{"name": "Johns Hopkins University", "source_name": "Johns Hopkins University", "street_adddress": "Baltimore, MD 21218, USA", "lat": "39.32990130", "lng": "-76.62051770", "type": "edu", "country": "United States"}, {"name": "Stanford University", "source_name": "Stanford University", "street_adddress": "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1712.00559.pdf"], "doi": []}, {"id": "02588064dd2b4b56d1dad214c1af3a7518832a59", "title": "A survey on deep neural network-based image captioning", "addresses": [{"name": "Dalian Maritime University", "source_name": "Dalian Maritime University, Dalian, China", "street_adddress": "1 Linghai Rd, Ganjingzi Qu, Dalian Shi, Liaoning Sheng, China", "lat": "38.87004100", "lng": "121.53414100", "type": "edu", "country": "China"}, {"name": "Shandong University", "source_name": "Shandong University", "street_adddress": "\u5c71\u4e1c\u5927\u5b66, \u6cf0\u5b89\u8857, \u9ccc\u5c71\u536b\u8857\u9053, \u5373\u58a8\u533a, \u9752\u5c9b\u5e02, \u5c71\u4e1c\u7701, 266200, \u4e2d\u56fd", "lat": "36.36934730", "lng": "120.67381800", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://doi.org/10.1007/s00371-018-1566-y"]}, {"id": "bb93c56a44a244601daad96a7bb94e41609afc4d", "title": "Towards Improved Design and Evaluation of Epileptic Seizure Predictors", "addresses": [{"name": "Ghent University", "source_name": "Ghent University", "street_adddress": "St. Pietersnieuwstraat 33, 9000 Gent, Belgium", "lat": "51.04656190", "lng": "3.72791810", "type": "edu", "country": "Belgium"}, {"name": "TU Berlin", "source_name": "TU Berlin", "street_adddress": "Franklinstra\u00dfe 28-29, 10587 Berlin, Germany", "lat": "52.51806410", "lng": "13.32504250", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": ["https://biblio.ugent.be/publication/8519033/file/8520709.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7915772", "http://doi.org/10.1109/TBME.2017.2700086", "https://www.ncbi.nlm.nih.gov/pubmed/28475041", "https://www.wikidata.org/entity/Q38687464"]}, {"id": "19aa506d04d3f7241fc71b595d28b5f1bb99edad", "title": "Compact Generalized Non-local Network", "addresses": [{"name": "Central South University", "source_name": "Central South University, Changsha, People\u2019s Republic of China", "street_adddress": "932 Lushan S Rd, Yuelu Qu, Changsha Shi, Hunan Sheng, China", "lat": "28.16437000", "lng": "112.93251000", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.13125.pdf"], "doi": []}, {"id": "738947f9b0bc50d1b7d5cbe84856bc18fcaee386", "title": "Deep learning-based human head detection and extraction for robotic portrait drawing", "addresses": [{"name": "Northeastern University", "source_name": "Northeastern University", "street_adddress": "Snell Library, 360, Huntington Avenue, Roxbury Crossing, Fenway, Boston, Suffolk County, Massachusetts, 02115, USA", "lat": "42.33836680", "lng": "-71.08793524", "type": "edu", "country": "United States"}, {"name": "Shenzhen Academy of Robotics, Shenzhen, Guangdong, China", "source_name": "Shenzhen Academy of Robotics, Shenzhen, Guangdong, China", "street_adddress": "Shenzhen, Guangdong, China", "lat": "22.54309600", "lng": "114.05786500", "type": "edu", "country": "China"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8324594", "http://doi.org/10.1109/ROBIO.2017.8324594"]}, {"id": "80acc73e29fb324a3e01113bbeddccacaf5283f1", "title": "Generate, Segment and Replace: Towards Generic Manipulation Segmentation.", "addresses": [{"name": "University of Maryland", "source_name": "University of Maryland", "street_adddress": "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.09729.pdf"], "doi": []}, {"id": "b4c48aa7a93f38d2eb60209120a1a8daa61c4545", "title": "Diversity in Object Proposals", "addresses": [{"name": "University of Augsburg", "source_name": "Multimedia Computing Lab, University of Augsburg, Germany", "street_adddress": "Universit\u00e4tsstra\u00dfe 2, 86159 Augsburg, Germany", "lat": "48.33282440", "lng": "10.89656160", "type": "edu", "country": "Germany"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1603.04308.pdf"], "doi": []}, {"id": "26e425781e4090abfae65b5d68eac72282dd2e31", "title": "Image Captioning with Deep Bidirectional LSTMs", "addresses": [{"name": "University of Potsdam", "source_name": "Hasso Plattner Institute, University of Potsdam, Prof.-Dr.-Helmert-Str. 2-3, 14482, Germany", "street_adddress": "Prof.-Dr.-Helmert-Stra\u00dfe 2-3, 14482 Potsdam, Germany", "lat": "52.39399650", "lng": "13.13336570", "type": "edu", "country": "Germany"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1604.00790.pdf"], "doi": []}, {"id": "d6c3f9edf5459db8633f9155f55e6f735dd0ce8b", "title": "Edge-Cloud Collaborative Processing for Intelligent Internet of Things: A Case Study on Smart Surveillance", "addresses": [{"name": "Georgia Institute of Technology", "source_name": "Georgia Institute of Technology", "street_adddress": "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu", "country": "United States"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3196036"]}, {"id": "f831f81f34a9c9dde41c5250b1a9dadf8ec8963b", "title": "Video Object Segmentation with Re-identification", "addresses": [{"name": "Chinese University of Hong Kong", "source_name": "Chinese University of Hong Kong", "street_adddress": "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "lat": "22.41626320", "lng": "114.21093180", "type": "edu", "country": "China"}, {"name": "Harbin Institute of Technology", "source_name": "Harbin Institute of Technology", "street_adddress": "\u54c8\u5c14\u6ee8\u5de5\u4e1a\u5927\u5b66, \u53f8\u4ee4\u8857, \u5357\u5c97\u533a, \u54c8\u5c14\u6ee8\u5e02 / Harbin, \u9ed1\u9f99\u6c5f\u7701, 150000, \u4e2d\u56fd", "lat": "45.74139210", "lng": "126.62552755", "type": "edu", "country": "China"}, {"name": "SenseTime", "source_name": "SenseTime", "street_adddress": "China, Beijing Shi, Haidian Qu, WuDaoKou, Zhongguancun E Rd, 1\u53f7-7", "lat": "39.99300800", "lng": "116.32988200", "type": "company", "country": "China"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.00197.pdf"], "doi": []}, {"id": "b29c83b6ee10857e09ac3503916ae1b129642cae", "title": "Mo 2 Cap 2 : Real-time Mo bile 3 D Mo tion Cap ture with a Cap-mounted Fisheye Camera", "addresses": [{"name": "Stanford University", "source_name": "Stanford University", "street_adddress": "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/b29c/83b6ee10857e09ac3503916ae1b129642cae.pdf"], "doi": []}, {"id": "f3b24cdbd1e7fd94d7ad1fa077dfa051bcc8aa38", "title": "AUTOMATIC IMAGE ANNOTATION MODEL USING LSTM APPROACH", "addresses": [{"name": "Varanasi", "source_name": "Varanasi", "street_adddress": "Varanasi, Uttar Pradesh, India", "lat": "25.31764520", "lng": "82.97391440", "type": "edu", "country": "India"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/f3b2/4cdbd1e7fd94d7ad1fa077dfa051bcc8aa38.pdf"], "doi": []}, {"id": "4f0d7f2926061c9dd6081d95eb9755812f9a16c2", "title": "Videos as Space-Time Region Graphs", "addresses": [{"name": "Robotics Institute", "source_name": "Robotics Institute", "street_adddress": "Institute for Field Robotics, \u0e1b\u0e23\u0e30\u0e0a\u0e32\u0e2d\u0e38\u0e17\u0e34\u0e28, \u0e01\u0e23\u0e38\u0e07\u0e40\u0e17\u0e1e\u0e21\u0e2b\u0e32\u0e19\u0e04\u0e23, \u0e40\u0e02\u0e15\u0e23\u0e32\u0e29\u0e0e\u0e23\u0e4c\u0e1a\u0e39\u0e23\u0e13\u0e30, \u0e01\u0e23\u0e38\u0e07\u0e40\u0e17\u0e1e\u0e21\u0e2b\u0e32\u0e19\u0e04\u0e23, 10140, \u0e1b\u0e23\u0e30\u0e40\u0e17\u0e28\u0e44\u0e17\u0e22", "lat": "13.65450525", "lng": "100.49423171", "type": "edu", "country": "Thailand"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.01810.pdf"], "doi": []}, {"id": "ad6dedc3f56b1ef2c083cb13c2638eddf208d49b", "title": "An object based graph representation for video comparison", "addresses": [{"name": "Chongqing University of Technology", "source_name": "Chongqing University of Technology, China", "street_adddress": "69 Hongguang Ave, Banan Qu, Chongqing Shi, China", "lat": "29.45832600", "lng": "106.52994700", "type": "edu", "country": "China"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8296742", "http://doi.org/10.1109/ICIP.2017.8296742"]}, {"id": "cdabc1f190e8841ec6cd5f7cb4a3cd3016d292de", "title": "Stroke Controllable Fast Style Transfer with Adaptive Receptive Fields", "addresses": [{"name": "Zhejiang University", "source_name": "Zhejiang University", "street_adddress": "\u6d59\u6c5f\u5927\u5b66\u4e4b\u6c5f\u6821\u533a, \u4e4b\u6c5f\u8def, \u8f6c\u5858\u8857\u9053, \u897f\u6e56\u533a (Xihu), \u676d\u5dde\u5e02 Hangzhou, \u6d59\u6c5f\u7701, 310008, \u4e2d\u56fd", "lat": "30.19331415", "lng": "120.11930822", "type": "edu", "country": "China"}, {"name": "Arizona State University", "source_name": "Arizona State University", "street_adddress": "Arizona State University Polytechnic campus, East Texas Avenue, Mesa, Maricopa County, Arizona, 85212, USA", "lat": "33.30715065", "lng": "-111.67653157", "type": "edu", "country": "United States"}, {"name": "University of Sydney", "source_name": "University of Sydney", "street_adddress": "USyd, Fisher Road, Camperdown, Sydney, NSW, 2006, Australia", "lat": "-33.88890695", "lng": "151.18943366", "type": "edu", "country": "Australia"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.07101.pdf"], "doi": []}, {"id": "d9aca4cfe6bf49056c4bc6796414355a59cf5fb5", "title": "3D-SSD: Learning Hierarchical Features from RGB-D Images for Amodal 3D Object Detection", "addresses": [{"name": "Zhejiang University", "source_name": "Zhejiang University", "street_adddress": "\u6d59\u6c5f\u5927\u5b66\u4e4b\u6c5f\u6821\u533a, \u4e4b\u6c5f\u8def, \u8f6c\u5858\u8857\u9053, \u897f\u6e56\u533a (Xihu), \u676d\u5dde\u5e02 Hangzhou, \u6d59\u6c5f\u7701, 310008, \u4e2d\u56fd", "lat": "30.19331415", "lng": "120.11930822", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1711.00238.pdf"], "doi": []}, {"id": "11f515ead5b4a7259668f2620e808fa8ba5ea65c", "title": "Phrase Localization and Visual Relationship Detection with Comprehensive Image-Language Cues", "addresses": [{"name": "University of Illinois, Urbana-Champaign", "source_name": "University of Illinois, Urbana-Champaign", "street_adddress": "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1611.06641.pdf"], "doi": []}, {"id": "d0593359627cd0744740ea50731d2b98ff6b1937", "title": "Short-term memory with read-only unit in neural image caption generator", "addresses": [{"name": "Institute for Informatics and Automation Problems of NAS RA, Yerevan, Armenia", "source_name": "Institute for Informatics and Automation Problems of NAS RA, Yerevan, Armenia", "street_adddress": "62/1 Paruyr Sevak St, Yerevan, Armenia", "lat": "40.21254620", "lng": "44.53266140", "type": "edu", "country": "Armenia"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8312163"]}, {"id": "85e283564fca1d1cf4d142647561901a26f144c6", "title": "On the Origin of Deep Learning On the Origin of Deep Learning", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/85e2/83564fca1d1cf4d142647561901a26f144c6.pdf"], "doi": []}, {"id": "3e198f28343fccf502bc20191660dd090ba5356d", "title": "Accurate License Plate Recognition and Super-Resolution Using a Generative Adversarial Networks on Traffic Surveillance Video", "addresses": [{"name": "Gwangju Institute of Science and Technology", "source_name": "Gwangju Institute of Science and Technology", "street_adddress": "123 Cheomdangwagi-ro, Oryong-dong, Buk-gu, Kwangju, South Korea", "lat": "35.22652880", "lng": "126.83998700", "type": "edu", "country": "South Korea"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8552121", "http://doi.org/10.1109/icce-asia.2018.8552121"]}, {"id": "bc1d609520290e0460c49b685675eb5a57fa5935", "title": "An efficient framework for learning sentence representations", "addresses": [{"name": "University of Michigan", "source_name": "University of Michigan", "street_adddress": "University of Michigan, 500, Hayward Street, Ann Arbor, Washtenaw County, Michigan, 48109, USA", "lat": "42.29421420", "lng": "-83.71003894", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.02893.pdf"], "doi": []}, {"id": "704b46c9c255cd22b4712dcc6bc417d6fefc1e18", "title": "Learning RoI Transformer for Detecting Oriented Objects in Aerial Images", "addresses": [{"name": "Wuhan University of Technology", "source_name": "Wuhan University of Technology", "street_adddress": "\u6b66\u6c49\u7406\u5de5\u5927\u5b66-\u4f59\u5bb6\u5934\u6821\u533a, \u4ea4\u901a\u4e8c\u8def, \u6768\u56ed\u8857\u9053, \u6b66\u660c\u533a (Wuchang), \u6b66\u6c49\u5e02, \u6e56\u5317\u7701, 430062, \u4e2d\u56fd", "lat": "30.60903415", "lng": "114.35142840", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.00155.pdf"], "doi": []}, {"id": "7f1d7688c4923cab09bf0a548e6f1fc1dd916b51", "title": "Boundary aware image segmentation with unsupervised mixture models", "addresses": [{"name": "Technical University Dortmund", "source_name": "Image Analysis Group, Technical University Dortmund, Otto-Hahn-Str. 4, 44227 Dortmund, Germany", "street_adddress": "Emil-Figge-Stra\u00dfe 50, 44227 Dortmund, Germany", "lat": "51.49219020", "lng": "7.41413620", "type": "edu", "country": "Germany"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8296898", "http://doi.org/10.1109/ICIP.2017.8296898"]}, {"id": "0730d5f4408ab3c3bcc316ecbbfdc61cdbf7d813", "title": "Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Video", "addresses": [{"name": "University of Bucharest", "source_name": "University of Bucharest, 14 Academiei Street, Bucharest, Romania", "street_adddress": "Strada Academiei 14, Bucure\u0219ti 010014, Romania", "lat": "44.43546330", "lng": "26.09968830", "type": "edu", "country": "Romania"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.04960.pdf"], "doi": []}, {"id": "3d22f972448a2336677ae6ff2877fae010c7dfa2", "title": "What is the Role of Recurrent Neural Networks (RNNs) in an Image Caption Generator?", "addresses": [{"name": "University of Malta", "source_name": "University of Malta", "street_adddress": "University of Malta, Ring Road, Japanese Garden, L-Imsida, Malta, MSD 9027, Malta", "lat": "35.90232260", "lng": "14.48341890", "type": "edu", "country": "Malta"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.02043.pdf"], "doi": []}, {"id": "c0ef854f4119a74b37211aa4cc36b8c1addd9057", "title": "Training object class detectors with click supervision Dim", "addresses": [{"name": "University of Edinburgh", "source_name": "University of Edinburgh", "street_adddress": "New College, New College Courtyard, The Mound, Old Town, Edinburgh, City of Edinburgh, Scotland, EH1 2LX, UK", "lat": "55.94951105", "lng": "-3.19534913", "type": "edu", "country": "United Kingdom"}], "year": "", "pdf": ["https://pdfs.semanticscholar.org/c0ef/854f4119a74b37211aa4cc36b8c1addd9057.pdf"], "doi": []}, {"id": "0e23229289b1fbea14bc425718bc0a227d100b8e", "title": "Survey of Recent Advances in Visual Question Answering", "addresses": [{"name": "Hyderabad, India", "source_name": "Hyderabad, India", "street_adddress": "Hyderabad, Telangana, India", "lat": "17.38504400", "lng": "78.48667100", "type": "edu", "country": "India"}, {"name": "Adobe Systems", "source_name": "Adobe Systems", "street_adddress": "343 Preston St, Ottawa, ON K1S 1N4, Canada", "lat": "45.40242130", "lng": "-75.70955410", "type": "edu", "country": "South Korea"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1709.08203.pdf"], "doi": []}, {"id": "6950b44613b7a98e860d800fdbbe1693c6444729", "title": "Bottom-up Pose Estimation of Multiple Person with Bounding Box Constraint", "addresses": [{"name": "Zhejiang University", "source_name": "Zhejiang University", "street_adddress": "\u6d59\u6c5f\u5927\u5b66\u4e4b\u6c5f\u6821\u533a, \u4e4b\u6c5f\u8def, \u8f6c\u5858\u8857\u9053, \u897f\u6e56\u533a (Xihu), \u676d\u5dde\u5e02 Hangzhou, \u6d59\u6c5f\u7701, 310008, \u4e2d\u56fd", "lat": "30.19331415", "lng": "120.11930822", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.09972.pdf"], "doi": []}, {"id": "08ff22f76a567fcbc1afec6bfbf957a560cfadc7", "title": "Exploring Person Context and Local Scene Context for Object Detection.", "addresses": [{"name": "UC Berkeley", "source_name": "UC Berkeley", "street_adddress": "Berkeley, CA, USA", "lat": "37.87189920", "lng": "-122.25853990", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1511.08177.pdf"], "doi": []}, {"id": "828ac57f755db989e2886042a85278ae4823297c", "title": "Uncovering the Temporal Context for Video Question Answering", "addresses": [{"name": "University of Technology Sydney", "source_name": "University of Technology Sydney", "street_adddress": "University of Technology Sydney, Omnibus Lane, Ultimo, Sydney, NSW, 2007, Australia", "lat": "-33.88096510", "lng": "151.20107299", "type": "edu", "country": "Australia"}, {"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "2017", "pdf": [], "doi": ["http://doi.org/10.1007/s11263-017-1033-7"]}, {"id": "45e7ddd5248977ba8ec61be111db912a4387d62f", "title": "Adversarial Learning of Structure-Aware Fully Convolutional Networks for Landmark Localization", "addresses": [{"name": "Adelaide University", "source_name": "Adelaide University, Australia", "street_adddress": "Adelaide SA 5005, Australia", "lat": "-34.92060300", "lng": "138.60622770", "type": "edu", "country": "Australia"}, {"name": "Nanjing University", "source_name": "Nanjing University", "street_adddress": "NJU, \u4e09\u6c5f\u8def, \u9f13\u697c\u533a, \u5357\u4eac\u5e02, \u6c5f\u82cf\u7701, 210093, \u4e2d\u56fd", "lat": "32.05659570", "lng": "118.77408833", "type": "edu", "country": "China"}, {"name": "Nanjing University of Science & Technology", "source_name": "Nanjing University of Science & Technology, Nanjing, People\u2019s Republic of China", "street_adddress": "China, Jiangsu, Nanjing, Xuanwu, \u4e2d\u5c71\u95e8\u5916\u5927\u8857", "lat": "32.03522500", "lng": "118.85531700", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1711.00253.pdf"], "doi": []}, {"id": "69c22f1f72de76dfd4f5b90621dad4969674da1e", "title": "Convolution Neural Networks With Two Pathways for Image Style Recognition", "addresses": [{"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}, {"name": "Nanjing University", "source_name": "Nanjing University", "street_adddress": "NJU, \u4e09\u6c5f\u8def, \u9f13\u697c\u533a, \u5357\u4eac\u5e02, \u6c5f\u82cf\u7701, 210093, \u4e2d\u56fd", "lat": "32.05659570", "lng": "118.77408833", "type": "edu", "country": "China"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7945535", "http://doi.org/10.1109/TIP.2017.2710631", "https://www.ncbi.nlm.nih.gov/pubmed/28613168", "https://www.wikidata.org/entity/Q38726144"]}, {"id": "5820ba4c09695ce677a5aca6b0628c024303e60b", "title": "Semantic Correspondence: A Hierarchical Approach", "addresses": [{"name": "Queensland University of Technology", "source_name": "Queensland University of Technology", "street_adddress": "Queensland University of Technology, Macgregor Lane, Merthyr, South Brisbane, Brisbane, QLD, 4000, Australia", "lat": "-27.47715625", "lng": "153.02841004", "type": "edu", "country": "Australia"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.03560.pdf"], "doi": []}, {"id": "2d3d4883350a48708cdc0c260479110e5eed965a", "title": "Leveraging Visual Question Answering for Image-Caption Ranking", "addresses": [{"name": "Virginia Tech", "source_name": "Virginia Tech", "street_adddress": "Blacksburg, VA 24061, USA", "lat": "37.22838430", "lng": "-80.42341670", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1605.01379.pdf"], "doi": []}, {"id": "7a82d83f818cdc4ac714e468446bc2499ff9caa7", "title": "Object Referring in Videos with Language and Human Gaze", "addresses": [{"name": "ETH Zurich", "source_name": "ETH Zurich", "street_adddress": "R\u00e4mistrasse 101, 8092 Z\u00fcrich, Switzerland", "lat": "47.37631300", "lng": "8.54766990", "type": "edu", "country": "Switzerland"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1801.01582.pdf"], "doi": []}, {"id": "1cfbaa9af05f0eea03ac7c28cc0e588687cd8343", "title": "Self-view Grounding Given a Narrated 360{\\deg} Video", "addresses": [{"name": "National Tsing Hua University", "source_name": "National Tsing Hua University", "street_adddress": "\u570b\u7acb\u6e05\u83ef\u5927\u5b78, 101, \u514b\u606d\u6a4b, \u5149\u660e\u91cc, \u8d64\u571f\u5d0e, \u6771\u5340, \u65b0\u7af9\u5e02, 30013, \u81fa\u7063", "lat": "24.79254840", "lng": "120.99511830", "type": "edu", "country": "Taiwan"}, {"name": "Microsoft Research Asia", "source_name": "Microsoft Research Asia", "street_adddress": "1 Memorial Dr, Cambridge, MA 02142, USA", "lat": "42.36142560", "lng": "-71.08120920", "type": "company", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1711.08664.pdf"], "doi": []}, {"id": "a678b68abd4047d5342f64725f57a04647a47711", "title": "From Known to the Unknown: Transferring Knowledge to Answer Questions about Novel Visual and Semantic Concepts", "addresses": [{"name": "Australian National University", "source_name": "Australian National University", "street_adddress": "Canberra ACT 0200, Australia", "lat": "-35.27769990", "lng": "149.11852700", "type": "edu", "country": "Australia"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.12772.pdf"], "doi": []}, {"id": "19d1855e021561d6da9d0200bb18e47f51cddda6", "title": "Visual Storytelling", "addresses": [{"name": "Microsoft", "source_name": "Microsoft Corporation, Redmond, WA, USA", "street_adddress": "One Microsoft Way, Redmond, WA 98052, USA", "lat": "47.64233180", "lng": "-122.13693020", "type": "company", "country": "United States"}, {"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}, {"name": "Virginia Tech", "source_name": "Virginia Tech", "street_adddress": "Blacksburg, VA 24061, USA", "lat": "37.22838430", "lng": "-80.42341670", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1604.03968.pdf"], "doi": []}, {"id": "eecd9a070ed333077a066bfdcf776c51c2c74406", "title": "Deep image representations using caption generators", "addresses": [{"name": "Indian Institute of Science Bangalore", "source_name": "Indian Institute of Science Bangalore", "street_adddress": "IISc, Gulmohar Marg, RMV Stage II - 1st Block, Aramane Nagara Ward, West Zone, Bengaluru, Bangalore Urban, Karnataka, 560012, India", "lat": "13.02223470", "lng": "77.56718325", "type": "edu", "country": "India"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.09142.pdf"], "doi": []}, {"id": "b9566216ec1e5dcd02e3a222987f1934e44c773e", "title": "Neuron-level Selective Context Aggregation for Scene Segmentation", "addresses": [{"name": "Hebrew University of Jerusalem", "source_name": "The Hebrew University of Jerusalem", "street_adddress": "\u05d4\u05d0\u05d5\u05e0\u05d9\u05d1\u05e8\u05e1\u05d9\u05d8\u05d4 \u05d4\u05e2\u05d1\u05e8\u05d9\u05ea \u05d1\u05d9\u05e8\u05d5\u05e9\u05dc\u05d9\u05dd, Reagan Plaza, \u05e7\u05e8\u05d9\u05ea \u05de\u05e0\u05d7\u05dd \u05d1\u05d2\u05d9\u05df, \u05d4\u05e8 \u05d4\u05e6\u05d5\u05e4\u05d9\u05dd, \u05d9\u05e8\u05d5\u05e9\u05dc\u05d9\u05dd, \u05de\u05d7\u05d5\u05d6 \u05d9\u05e8\u05d5\u05e9\u05dc\u05d9\u05dd, NO, \u05d9\u05e9\u05e8\u05d0\u05dc", "lat": "31.79185550", "lng": "35.24472300", "type": "edu", "country": "Israel"}, {"name": "Shandong University", "source_name": "Shandong University", "street_adddress": "\u5c71\u4e1c\u5927\u5b66, \u6cf0\u5b89\u8857, \u9ccc\u5c71\u536b\u8857\u9053, \u5373\u58a8\u533a, \u9752\u5c9b\u5e02, \u5c71\u4e1c\u7701, 266200, \u4e2d\u56fd", "lat": "36.36934730", "lng": "120.67381800", "type": "edu", "country": "China"}, {"name": "Tel Aviv University", "source_name": "Tel Aviv University", "street_adddress": "\u05d0\u05d5\u05e0\u05d9\u05d1\u05e8\u05e1\u05d9\u05d8\u05ea \u05ea\u05dc \u05d0\u05d1\u05d9\u05d1, \u05db\u05d9\u05db\u05e8 \u05de\u05e0\u05d3\u05dc, \u05ea\u05dc \u05d0\u05d1\u05d9\u05d1 - \u05d9\u05e4\u05d5, \u05d0\u05e4\u05e7\u05d4, \u05ea\u05dc \u05d0\u05d1\u05d9\u05d1-\u05d9\u05e4\u05d5, \u05de\u05d7\u05d5\u05d6 \u05ea\u05dc \u05d0\u05d1\u05d9\u05d1, NO, \u05d9\u05e9\u05e8\u05d0\u05dc", "lat": "32.11198890", "lng": "34.80459702", "type": "edu", "country": "Israel"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1711.08278.pdf"], "doi": []}, {"id": "8c3cf0c579a28890e21428fcad7f09175e65e43d", "title": "Adding object detection skills to visual dialogue agents", "addresses": [{"name": "University of Amsterdam", "source_name": "University of Amsterdam", "street_adddress": "Institute for Logic, Language and Computation (ILLC), 107, Science Park, Oost-Watergraafsmeer, Amsterdam, Oost, Amsterdam, Noord-Holland, Nederland, 1098XG, Nederland", "lat": "52.35536550", "lng": "4.95016440", "type": "edu", "country": "Netherlands"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/8c3c/f0c579a28890e21428fcad7f09175e65e43d.pdf"], "doi": []}, {"id": "e559630c5710afb0d5eb8f95141e451393bbcbd9", "title": "Factors Influencing The Performance of Image Captioning Model: An Evaluation", "addresses": [{"name": "National University of Singapore", "source_name": "National University of Singapore", "street_adddress": "NUS, Former 1936 British Outpost, Nepal Hill, Clementi, Southwest, 117542, Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu", "country": "Singapore"}, {"name": "Hanoi University of Science and Technology", "source_name": "Hanoi University of Science and Technology", "street_adddress": "HUST, Tr\u1ea7n \u0110\u1ea1i Ngh\u0129a, Hai B\u00e0 Tr\u01b0ng, H\u00e0 N\u1ed9i, 10999, Vietnam", "lat": "21.00395200", "lng": "105.84360183", "type": "edu", "country": "Vietnam"}], "year": "2016", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3007136"]}, {"id": "e6d8ebfd88ee333deccce32b09ee41d271af6dc4", "title": "Grasp2Vec: Learning Object Representations from Self-Supervised Grasping", "addresses": [{"name": "UC Berkeley", "source_name": "UC Berkeley", "street_adddress": "Berkeley, CA, USA", "lat": "37.87189920", "lng": "-122.25853990", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.06964.pdf"], "doi": []}, {"id": "aea6dfb43df75b176ff209f5510a0f17256a4d0a", "title": "Learning 3 D Scene Synthesis from Annotated RGB-D Images", "addresses": [{"name": "Simon Fraser University", "source_name": "Simon Fraser University", "street_adddress": "SFU Burnaby, South Campus Road, Barnet, Burnaby, Metro Vancouver, British Columbia, V5A 4X6, Canada", "lat": "49.27674540", "lng": "-122.91777375", "type": "edu", "country": "Canada"}, {"name": "Zhejiang University", "source_name": "Zhejiang University", "street_adddress": "\u6d59\u6c5f\u5927\u5b66\u4e4b\u6c5f\u6821\u533a, \u4e4b\u6c5f\u8def, \u8f6c\u5858\u8857\u9053, \u897f\u6e56\u533a (Xihu), \u676d\u5dde\u5e02 Hangzhou, \u6d59\u6c5f\u7701, 310008, \u4e2d\u56fd", "lat": "30.19331415", "lng": "120.11930822", "type": "edu", "country": "China"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/aea6/dfb43df75b176ff209f5510a0f17256a4d0a.pdf"], "doi": []}, {"id": "b7407b2ea67b8c82246f013f4966c4cac1507e60", "title": "Object Detection via End-to-End Integration of Aspect Ratio and Context Aware Part-based Models and Fully Convolutional Networks", "addresses": [{"name": "Jilin University", "source_name": "Jilin University", "street_adddress": "\u5409\u6797\u5927\u5b66\u73e0\u6d77\u6821\u533a, \u4e39\u6842\u8def, \u5723\u5802\u6751, \u91d1\u6e7e\u533a, \u73e0\u6d77\u5e02, \u5e7f\u4e1c\u7701, \u4e2d\u56fd", "lat": "22.05356500", "lng": "113.39913285", "type": "edu", "country": "China"}, {"name": "North Carolina State University", "source_name": "North Carolina State University", "street_adddress": "North Carolina State University, Oval Drive, West Raleigh, Raleigh, Wake County, North Carolina, 27695, USA", "lat": "35.77184965", "lng": "-78.67408695", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/b740/7b2ea67b8c82246f013f4966c4cac1507e60.pdf"], "doi": []}, {"id": "079495c84b68623d9b1d4d48809cc24c1eee0a7e", "title": "Natural Language Object Retrieval", "addresses": [{"name": "University of California, Berkeley", "source_name": "University of California, Berkeley", "street_adddress": "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "lat": "37.86871260", "lng": "-122.25586815", "type": "edu", "country": "United States"}, {"name": "National University of Singapore", "source_name": "National University of Singapore", "street_adddress": "NUS, Former 1936 British Outpost, Nepal Hill, Clementi, Southwest, 117542, Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu", "country": "Singapore"}, {"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}, {"name": "University of Massachusetts", "source_name": "University of Massachusetts", "street_adddress": "University of Massachusetts, Hicks Way, Amherst, Hampshire, Massachusetts, 01003, USA", "lat": "42.38897850", "lng": "-72.52869870", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1511.04164.pdf"], "doi": []}, {"id": "e4b9c14951cea6259dd9d522586ba2c5bb1fbcce", "title": "Social Image Captioning: Exploring Visual Attention and User Attention", "addresses": [{"name": "China University of Petroleum (East China)", "source_name": "College of Information and Control Engineering, China University of Petroleum (East China), #66 Changjiang West Road, Qingdao Economic & Technological Development Zone, 266580 China", "street_adddress": "Jinan Rd, Dongying Qu, Dongying Shi, Shandong Sheng, China, 257000", "lat": "37.46230770", "lng": "118.50053220", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/e4b9/c14951cea6259dd9d522586ba2c5bb1fbcce.pdf"], "doi": []}, {"id": "cf98c333c8d7d5870c1ce5538bb0c3de3de16657", "title": "Panoptic Segmentation", "addresses": [{"name": "Heidelberg University", "source_name": "Institute of Psychology, Heidelberg University, Heidelberg, Germany", "street_adddress": "Hauptstra\u00dfe 47-51, 69117 Heidelberg, Germany", "lat": "49.41092660", "lng": "8.69795290", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1801.00868.pdf"], "doi": []}, {"id": "75cea964884a6f5c35e2954e56fc787ed8f9662c", "title": "Beyond Domain Adaptation: Unseen Domain Encapsulation via Universal Non-volume Preserving Models", "addresses": [{"name": "University of Science, Vietnam", "source_name": "University of Science, Vietnam", "street_adddress": "227 \u0110\u01b0\u1eddng Nguy\u1ec5n V\u0103n C\u1eeb, Ph\u01b0\u1eddng 4, Qu\u1eadn 5, H\u1ed3 Ch\u00ed Minh, Vietnam", "lat": "10.76291300", "lng": "106.68217170", "type": "edu", "country": "Vietnam"}, {"name": "Concordia University", "source_name": "Concordia University", "street_adddress": "Concordia University, 2811, Northeast Holman Street, Concordia, Portland, Multnomah County, Oregon, 97211, USA", "lat": "45.57022705", "lng": "-122.63709346", "type": "edu", "country": "United States"}, {"name": "University of Arkansas", "source_name": "University of Arkansas", "street_adddress": "Fayetteville, AR 72701, USA", "lat": "36.06783240", "lng": "-94.17365510", "type": "edu", "country": "United States"}, {"name": "University of Illinois", "source_name": "Advanced Digital Sciences Center (ADSC) of the University of Illinois, Singapore, Singapore", "street_adddress": "1 Create Way, 14-02 Create Tower, Singapore 138602", "lat": "1.30372570", "lng": "103.77377630", "type": "edu", "country": "Singapore"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.03407.pdf"], "doi": []}, {"id": "ad8fc03b492590a4282df52fe998d713995d0a0c", "title": "Exploring confusing scene classes for the places dataset: Insights and solutions", "addresses": [{"name": "University of Southern California", "source_name": "University of Southern California", "street_adddress": "University of Southern California, Watt Way, Saint James Park, LA, Los Angeles County, California, 90089, USA", "lat": "34.02241490", "lng": "-118.28634407", "type": "edu", "country": "United States"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8282094", "http://doi.org/10.1109/APSIPA.2017.8282094"]}, {"id": "943c372336ced4b28e15e02fe8db1f4b23bf6835", "title": "Advanced Deep-Learning Techniques for Salient and Category-Specific Object Detection: A Survey", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}, {"name": "University of Sydney", "source_name": "University of Sydney", "street_adddress": "USyd, Fisher Road, Camperdown, Sydney, NSW, 2006, Australia", "lat": "-33.88890695", "lng": "151.18943366", "type": "edu", "country": "Australia"}, {"name": "Northwestern Polytechnical University", "source_name": "Northwestern Polytechnical University", "street_adddress": "\u897f\u5317\u5de5\u4e1a\u5927\u5b66 \u53cb\u8c0a\u6821\u533a, 127\u53f7, \u53cb\u8c0a\u897f\u8def, \u957f\u5b89\u8def, \u7891\u6797\u533a (Beilin), \u897f\u5b89\u5e02, \u9655\u897f\u7701, 710072, \u4e2d\u56fd", "lat": "34.24691520", "lng": "108.91061982", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8253582", "http://doi.org/10.1109/MSP.2017.2749125"]}, {"id": "4923c6bc3ab501651763f6814a8384745f3d9a4d", "title": "Visual attribute transfer through deep image analogy", "addresses": [{"name": "Microsoft", "source_name": "Microsoft Corporation, Redmond, WA, USA", "street_adddress": "One Microsoft Way, Redmond, WA 98052, USA", "lat": "47.64233180", "lng": "-122.13693020", "type": "company", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.01088.pdf"], "doi": []}, {"id": "0013fae7390cbd34aade7959b4476512d8ab9aa3", "title": "Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions", "addresses": [{"name": "University of Modena and Reggio Emilia", "source_name": "University of Modena and Reggio Emilia 41125, Modena, Italy", "street_adddress": "Via Universit\u00e0, 4, 41121 Modena MO, Italy", "lat": "44.64510460", "lng": "10.92792680", "type": "edu", "country": "Italy"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.10652.pdf"], "doi": []}, {"id": "00ca28c1c8005ae8d06c7afd0284f67c67710c43", "title": "Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments", "addresses": [{"name": "Cornell University", "source_name": "Cornell University", "street_adddress": "Cornell University, Forest Home Drive, Forest Home, Tompkins County, New York, 14853, USA", "lat": "42.45055070", "lng": "-76.47835130", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.12354.pdf"], "doi": []}, {"id": "a88f86093e6f2d14761d4b8cbdcadfeff496c948", "title": "Adversarial Ranking for Language Generation", "addresses": [{"name": "University of Washington", "source_name": "University of Washington", "street_adddress": "University of Washington, Rainier Vista, Montlake, University District, Seattle, King County, Washington, 98195, USA", "lat": "47.65432380", "lng": "-122.30800894", "type": "edu", "country": "United States"}, {"name": "Microsoft", "source_name": "Microsoft Corporation, Redmond, WA, USA", "street_adddress": "One Microsoft Way, Redmond, WA 98052, USA", "lat": "47.64233180", "lng": "-122.13693020", "type": "company", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.11001.pdf"], "doi": []}, {"id": "30f33cffe390dfcc03d8df28593aebba6afafd59", "title": "Video Predictive Object Detector", "addresses": [{"name": "Queen's University", "source_name": "Queen's University, Belfast, UK", "street_adddress": "University Rd, Belfast BT7 1NN, UK", "lat": "54.58440870", "lng": "-5.93404930", "type": "edu", "country": "United Kingdom"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8615054"]}, {"id": "e69b1314cd65a115c98082a5863b92daa4dcf9f0", "title": "Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks", "addresses": [{"name": "Hong Kong Polytechnic University", "source_name": "Hong Kong Polytechnic University", "street_adddress": "hong kong, 11, \u80b2\u624d\u9053 Yuk Choi Road, \u5c16\u6c99\u5480 Tsim Sha Tsui, \u6cb9\u5c16\u65fa\u5340 Yau Tsim Mong District, \u4e5d\u9f8d Kowloon, HK, 00000, \u4e2d\u56fd", "lat": "22.30457200", "lng": "114.17976285", "type": "edu", "country": "China"}, {"name": "Chinese University of Hong Kong", "source_name": "Chinese University of Hong Kong", "street_adddress": "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "lat": "22.41626320", "lng": "114.21093180", "type": "edu", "country": "China"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7792699", "http://doi.org/10.1109/TMI.2016.2642839", "https://www.ncbi.nlm.nih.gov/pubmed/28026754", "https://www.wikidata.org/entity/Q39062626"]}, {"id": "fe8431a3b4313737183510d8f01003d48870d277", "title": "Superpixel Filtering for Mean Field Inference in CRFs Integrated with Convolutional Neural Networks", "addresses": [{"name": "University of Oxford", "source_name": "University of Oxford", "street_adddress": "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "lat": "51.75345380", "lng": "-1.25400997", "type": "edu", "country": "United Kingdom"}], "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/fe84/31a3b4313737183510d8f01003d48870d277.pdf"], "doi": []}, {"id": "99ef290d0eca8cfe8dc086bb1c4571e88eb876e4", "title": "Multi-label image classification with recurrently learning semantic dependencies", "addresses": [{"name": "Hefei University of Technology", "source_name": "Hefei University of Technology", "street_adddress": "\u5408\u80a5\u5de5\u4e1a\u5927\u5b66\uff08\u5c6f\u6eaa\u8def\u6821\u533a\uff09, 193\u53f7, \u5357\u4e00\u73af\u8def, \u822a\u8fd0\u5357\u6751, \u5305\u516c\u8857\u9053, \u5408\u80a5\u5e02\u533a, \u5408\u80a5\u5e02, \u5b89\u5fbd\u7701, 230009, \u4e2d\u56fd", "lat": "31.84691800", "lng": "117.29053367", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://doi.org/10.1007/s00371-018-01615-0"]}, {"id": "2e0f1c89c4e099b14c4d77bd406be9f7b78d6f6d", "title": "GLA: Global\u2013Local Attention for Image Description", "addresses": [{"name": "University of Texas at San Antonio", "source_name": "University of Texas at San Antonio", "street_adddress": "UTSA, Paseo Principal, San Antonio, Bexar County, Texas, 78249-1620, USA", "lat": "29.58333105", "lng": "-98.61944505", "type": "edu", "country": "United States"}, {"name": "Chinese Academy of Sciences", "source_name": "Chinese Academy of Sciences", "street_adddress": "\u4e2d\u56fd\u79d1\u5b66\u9662\u5fc3\u7406\u7814\u7a76\u6240, 16, \u6797\u8403\u8def, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100101, \u4e2d\u56fd", "lat": "40.00447950", "lng": "116.37023800", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8031355", "http://doi.org/10.1109/TMM.2017.2751140"]}, {"id": "5983b0c92f2a619157e2bedf15abb97ed1b0b98f", "title": "Computer Vision and Deep Learning for Automated Surveillance Technology", "addresses": [{"name": "Stanford University", "source_name": "Stanford University", "street_adddress": "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/5983/b0c92f2a619157e2bedf15abb97ed1b0b98f.pdf"], "doi": []}, {"id": "8d0fb60adc54c168587bce2cf5b1c46ba2ac36e3", "title": "Exploiting Saliency for Object Segmentation from Image Level Labels", "addresses": [{"name": "Max Planck Institute for Informatics", "source_name": "Max Planck Institute for Informatics", "street_adddress": "MPII, E1 4, Campus, Universit\u00e4t, Sankt Johann, Bezirk Mitte, Saarbr\u00fccken, Regionalverband Saarbr\u00fccken, Saarland, 66123, Deutschland", "lat": "49.25795660", "lng": "7.04577417", "type": "edu", "country": "Germany"}, {"name": "University of Amsterdam", "source_name": "University of Amsterdam", "street_adddress": "Institute for Logic, Language and Computation (ILLC), 107, Science Park, Oost-Watergraafsmeer, Amsterdam, Oost, Amsterdam, Noord-Holland, Nederland, 1098XG, Nederland", "lat": "52.35536550", "lng": "4.95016440", "type": "edu", "country": "Netherlands"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1701.08261.pdf"], "doi": []}, {"id": "55b9b1c1c5487f5f62b44340104a9c4cc2ed7c96", "title": "The Color of the Cat is Gray: 1 Million Full-Sentences Visual Question Answering (FSVQA).", "addresses": [{"name": "University of Tokyo", "source_name": "University of Tokyo", "street_adddress": "\u6771\u4eac\u5927\u5b66 \u67cf\u30ad\u30e3\u30f3\u30d1\u30b9, \u5b66\u878d\u5408\u306e\u9053, \u67cf\u5e02, \u5343\u8449\u770c, \u95a2\u6771\u5730\u65b9, 277-8583, \u65e5\u672c", "lat": "35.90204480", "lng": "139.93622009", "type": "edu", "country": "Japan"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1609.06657.pdf"], "doi": []}, {"id": "0d57ba12a6d958e178d83be4c84513f7e42b24e5", "title": "Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour.", "addresses": [{"name": "Facebook", "source_name": "Facebook", "street_adddress": "250 Bryant St, Mountain View, CA 94041, USA", "lat": "37.39367170", "lng": "-122.08072620", "type": "company", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1706.02677.pdf"], "doi": []}, {"id": "030646f4fc694ffea5d4f77203cbbc5d02aae797", "title": "Cognitive Deep Machine Can Train Itself", "addresses": [{"name": "E\u00f6tv\u00f6s Lor\u00e1nd University", "source_name": "Faculty of Informatics, E\u00f6tv\u00f6s Lor\u00e1nd University, P\u00e1zm\u00e1ny P\u00e9ter s\u00e9t\u00e1ny 1/C, Budapest H-1117, Hungary", "street_adddress": "Budapest, P\u00e1zm\u00e1ny P\u00e9ter stny. 1/C., 1117 Hungary", "lat": "47.47228960", "lng": "19.06235910", "type": "edu", "country": "Hungary"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1612.00745.pdf"], "doi": []}, {"id": "0744143542ffcb45b1ad83078c23efa9d3ec2be4", "title": "Multispectral Pedestrian Detection via Simultaneous Detection and Segmentation", "addresses": [{"name": "Zhejiang University", "source_name": "Zhejiang University", "street_adddress": "\u6d59\u6c5f\u5927\u5b66\u4e4b\u6c5f\u6821\u533a, \u4e4b\u6c5f\u8def, \u8f6c\u5858\u8857\u9053, \u897f\u6e56\u533a (Xihu), \u676d\u5dde\u5e02 Hangzhou, \u6d59\u6c5f\u7701, 310008, \u4e2d\u56fd", "lat": "30.19331415", "lng": "120.11930822", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.04818.pdf"], "doi": []}, {"id": "ee5b4fc5fafa7e883d751557b5c7863503cd92d2", "title": "Findings of the Second Shared Task on Multimodal Machine Translation and Multilingual Image Description", "addresses": [{"name": "University of Edinburgh", "source_name": "University of Edinburgh", "street_adddress": "New College, New College Courtyard, The Mound, Old Town, Edinburgh, City of Edinburgh, Scotland, EH1 2LX, UK", "lat": "55.94951105", "lng": "-3.19534913", "type": "edu", "country": "United Kingdom"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1710.07177.pdf"], "doi": []}, {"id": "3f15c35d4c5ed41de9f57e06849f750e43fe80b3", "title": "JointFlow : Temporal Flow Fields for Multi Person Pose Tracking", "addresses": [{"name": "University of Bonn", "source_name": "University of Bonn", "street_adddress": "Rheinische Friedrich-Wilhelms-Universit\u00e4t Bonn, Arkadenhof, Bonn-Zentrum, Stadtbezirk Bonn, Bonn, Regierungsbezirk K\u00f6ln, Nordrhein-Westfalen, 53113, Deutschland", "lat": "50.73381240", "lng": "7.10224650", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/3f15/c35d4c5ed41de9f57e06849f750e43fe80b3.pdf"], "doi": []}, {"id": "d0e20aa3d61b77d17f005a1d24d7cf47600836ef", "title": "Rethinking Atrous Convolution for Semantic Image Segmentation", "addresses": [{"name": "Google", "source_name": "Google, Inc.", "street_adddress": "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "lat": "37.42199990", "lng": "-122.08405750", "type": "company", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1706.05587.pdf"], "doi": []}, {"id": "4fa6a688f350831503d158f8f618c58d1e06bc5d", "title": "A Semi-supervised Framework for Image Captioning", "addresses": [{"name": "ETH Zurich", "source_name": "ETH Zurich", "street_adddress": "R\u00e4mistrasse 101, 8092 Z\u00fcrich, Switzerland", "lat": "47.37631300", "lng": "8.54766990", "type": "edu", "country": "Switzerland"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1611.05321.pdf"], "doi": []}, {"id": "7d8c2d29deb80ceed3c8568100376195ce0914cb", "title": "Identity-Aware Textual-Visual Matching with Latent Co-attention", "addresses": [{"name": "Chinese University of Hong Kong", "source_name": "Chinese University of Hong Kong", "street_adddress": "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "lat": "22.41626320", "lng": "114.21093180", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.01988.pdf"], "doi": []}, {"id": "3f607dd67b456e3dfb136c70a3dae369945a6076", "title": "Improved Selective Refinement Network for Face Detection", "addresses": [{"name": "Chinese Academy of Sciences", "source_name": "Chinese Academy of Sciences", "street_adddress": "\u4e2d\u56fd\u79d1\u5b66\u9662\u5fc3\u7406\u7814\u7a76\u6240, 16, \u6797\u8403\u8def, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100101, \u4e2d\u56fd", "lat": "40.00447950", "lng": "116.37023800", "type": "edu", "country": "China"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.06651.pdf"], "doi": []}, {"id": "357df3ee0f0c30d5c8abc5a1bdf70122322d6fbd", "title": "O BJECT DETECTORS EMERGE IN D EEP S CENE CNN S", "addresses": [{"name": "MIT", "source_name": "Massachusetts Institute", "street_adddress": "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/08c7/a85c443935468450a162ddeccd2b945660e3.pdf"], "doi": []}, {"id": "ef12de45bd47e03451cde586697601cd7e36c3b9", "title": "Aligning Text and Document Illustrations: Towards Visually Explainable Digital Humanities", "addresses": [{"name": "University of of Modena and Reggio Emilia", "source_name": "University of of Modena and Reggio Emilia", "street_adddress": "Via Universit\u00e0, 4, 41121 Modena MO, Italy", "lat": "44.64510460", "lng": "10.92792680", "type": "edu", "country": "Italy"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8545064", "http://doi.ieeecomputersociety.org/10.1109/ICPR.2018.8545064", "http://doi.org/10.1109/ICPR.2018.8545064"]}, {"id": "6cc46899b415ebef4a70068b2cbd8a50e955aeb6", "title": "Where to put the Image in an Image Caption Generator", "addresses": [{"name": "University of Malta", "source_name": "University of Malta", "street_adddress": "University of Malta, Ring Road, Japanese Garden, L-Imsida, Malta, MSD 9027, Malta", "lat": "35.90232260", "lng": "14.48341890", "type": "edu", "country": "Malta"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1703.09137.pdf"], "doi": []}, {"id": "3d732ba534081326eb9de70f2e370a31940c2990", "title": "Semantic image segmentation using fully convolutional neural networks with multi-scale images and multi-scale dilated convolutions", "addresses": [{"name": "Gachon University", "source_name": "Gachon University, Gyeonggi-do, South Korea", "street_adddress": "1342 Seongnam-daero, Bokjeong-dong, Sujeong-gu, Seongnam-si, Gyeonggi-do, South Korea", "lat": "37.45074520", "lng": "127.12884740", "type": "edu", "country": "South Korea"}], "year": "2018", "pdf": [], "doi": ["http://doi.org/10.1007/s11042-018-5653-x"]}, {"id": "5ffa8cfea2f5bea0ec7cecfdf76f9478ca87df89", "title": "Context-Aware Captions from Context-Agnostic Supervision", "addresses": [{"name": "Virginia Tech", "source_name": "Virginia Tech", "street_adddress": "Blacksburg, VA 24061, USA", "lat": "37.22838430", "lng": "-80.42341670", "type": "edu", "country": "United States"}, {"name": "Georgia Institute of Technology", "source_name": "Georgia Institute of Technology", "street_adddress": "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu", "country": "United States"}, {"name": "Google", "source_name": "Google, Inc.", "street_adddress": "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "lat": "37.42199990", "lng": "-122.08405750", "type": "company", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1701.02870.pdf"], "doi": []}, {"id": "b9146b314812231d09587e3a9f622dda65d3cc40", "title": "A survey on social image understanding", "addresses": [{"name": "Nanjing Normal University Nanjing", "source_name": "Honors College, Nanjing Normal University Nanjing, Jiangsu, 210023, China", "street_adddress": "122 Ninghai Rd, Gulou Qu, Nanjing Shi, Jiangsu Sheng, China, 210097", "lat": "32.05494300", "lng": "118.76494700", "type": "edu", "country": "China"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8256394", "http://doi.org/10.1109/BESC.2017.8256394"]}, {"id": "9d0c3adbee8098d47c7c0704e0841fa7daf8d161", "title": "The price of debiasing automatic metrics in natural language evalaution", "addresses": [{"name": "Stanford University", "source_name": "Stanford University", "street_adddress": "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.02202.pdf"], "doi": []}, {"id": "6e97a99b2879634ecae962ddb8af7c1a0a653a82", "title": "Towards Context-aware Interaction Recognition", "addresses": [{"name": "University of Adelaide", "source_name": "University of Adelaide", "street_adddress": "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu", "country": "Australia"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.06246.pdf"], "doi": []}, {"id": "4cc2dc6e6b1f4575e86217a13b591f605a12b825", "title": "Consistent Optimization for Single-Shot Object Detection", "addresses": [{"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.06563.pdf"], "doi": []}, {"id": "9ac253caa50f7d94eead17ac12499226c0f05e87", "title": "Analysing object detectors from the perspective of co-occurring object categories", "addresses": [{"name": "Nokia Bell Labs, Budapest, Hungary", "source_name": "Nokia Bell Labs, Budapest, Hungary", "street_adddress": "Budapest, Hungary", "lat": "47.49791200", "lng": "19.04023500", "type": "company", "country": "Hungary"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8639888"]}, {"id": "102e7bd7660357e1814c821c7f697f2eccececa4", "title": "Predicting Motivations of Actions by Leveraging Text", "addresses": [{"name": "MIT", "source_name": "Massachusetts Institute", "street_adddress": "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu", "country": "United States"}, {"name": "University of Maryland", "source_name": "University of Maryland", "street_adddress": "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1406.5472.pdf"], "doi": []}, {"id": "c2f1aa6395941438501653ea262df63c812e8f71", "title": "Non-parametric human segmentation using support vector machine", "addresses": [{"name": "Yonsei University", "source_name": "Yonsei University", "street_adddress": "\uc5f0\uc138\ub300, \uc5f0\uc138\ub85c, \uc2e0\ucd0c\ub3d9, \ucc3d\ucc9c\ub3d9, \uc11c\ub300\ubb38\uad6c, \uc11c\uc6b8\ud2b9\ubcc4\uc2dc, 03789, \ub300\ud55c\ubbfc\uad6d", "lat": "37.56004060", "lng": "126.93692480", "type": "edu", "country": "South Korea"}], "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7514714", "http://doi.org/10.1109/ICCE.2016.7430551"]}, {"id": "819d1dcea397e6e671acf74adccdef5750550873", "title": "Representations for Visually Guided Actions", "addresses": [{"name": "University of California at Berkeley", "source_name": "International Computer Science Institute, University of California at Berkeley, Berkeley, USA", "street_adddress": "1947 Center St, Berkeley, CA 94704, USA", "lat": "37.87015430", "lng": "-122.27123120", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/819d/1dcea397e6e671acf74adccdef5750550873.pdf"], "doi": []}, {"id": "c1de9803bd0072f017a97c0503308a7b9b4f211b", "title": "Analysis of Spatial, Temporal, and Content Characteristics of Videos in the YFCC100M Dataset", "addresses": [{"name": "Yonsei University", "source_name": "Yonsei University", "street_adddress": "\uc5f0\uc138\ub300, \uc5f0\uc138\ub85c, \uc2e0\ucd0c\ub3d9, \ucc3d\ucc9c\ub3d9, \uc11c\ub300\ubb38\uad6c, \uc11c\uc6b8\ud2b9\ubcc4\uc2dc, 03789, \ub300\ud55c\ubbfc\uad6d", "lat": "37.56004060", "lng": "126.93692480", "type": "edu", "country": "South Korea"}], "year": "2016", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=2983559"]}, {"id": "2298a1e437b4f8f2f2f016f1a98c027bf2f7f5bb", "title": "Top-Down Neural Attention by Excitation Backprop", "addresses": [{"name": "Boston University", "source_name": "Boston University", "street_adddress": "BU, Bay State Road, Fenway, Boston, Suffolk County, Massachusetts, 02215, USA", "lat": "42.35042530", "lng": "-71.10056114", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1608.00507.pdf"], "doi": []}, {"id": "afa073e5ec712423e300f21bcb2c3f17a69fa9d1", "title": "Style Transfer at 100+ FPS Via Sub-Pixel Super-Resolution", "addresses": [{"name": "South China University of Technology", "source_name": "South China University of Technology", "street_adddress": "\u534e\u5357\u7406\u5de5\u5927\u5b66, \u5927\u5b66\u57ce\u4e2d\u73af\u4e1c\u8def, \u5e7f\u5dde\u5927\u5b66\u57ce, \u65b0\u9020, \u756a\u79ba\u533a (Panyu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510006, \u4e2d\u56fd", "lat": "23.05020420", "lng": "113.39880323", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8551538", "http://doi.ieeecomputersociety.org/10.1109/ICMEW.2018.8551538", "http://doi.org/10.1109/ICMEW.2018.8551538"]}, {"id": "19317c6aa7f88c79abe03b146aa5d340a11fde3f", "title": "Object Proposal Generation With Fully Convolutional Networks", "addresses": [{"name": "National University of Singapore", "source_name": "National University of Singapore", "street_adddress": "NUS, Former 1936 British Outpost, Nepal Hill, Clementi, Southwest, 117542, Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu", "country": "Singapore"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7484700", "http://doi.org/10.1109/TCSVT.2016.2576759"]}, {"id": "6a75ef6b36489cb59c61f21f3cd09c50ad5b2995", "title": "MVTec D2S: Densely Segmented Supermarket Dataset", "addresses": [{"name": "Technical University of Munich", "source_name": "Computer Aided Medical Procedures, Technical University of Munich, Garching, Germany", "street_adddress": "Boltzmannstra\u00dfe 3, 85748 Garching bei M\u00fcnchen, Germany", "lat": "48.26301100", "lng": "11.66685700", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.08292.pdf"], "doi": []}, {"id": "02d6fb270c82c390476faffc6015b3116ddbb60c", "title": "Image Captioning with Sentiment Terms via Weakly-Supervised Sentiment Dataset", "addresses": [{"name": "University of Tokyo", "source_name": "University of Tokyo", "street_adddress": "\u6771\u4eac\u5927\u5b66 \u67cf\u30ad\u30e3\u30f3\u30d1\u30b9, \u5b66\u878d\u5408\u306e\u9053, \u67cf\u5e02, \u5343\u8449\u770c, \u95a2\u6771\u5730\u65b9, 277-8583, \u65e5\u672c", "lat": "35.90204480", "lng": "139.93622009", "type": "edu", "country": "Japan"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/bd4a/bb49151220b389d9df1f19fecc3d92e0bff4.pdf"], "doi": []}, {"id": "11d256be1eb3da7789c0c9672f467079917baada", "title": "Action Classification via Concepts and Attributes", "addresses": [{"name": "York University", "source_name": "York University", "street_adddress": "York University, Keele Campus, Campus Walk, North York, Toronto, Ontario, M3J 2S5, Canada", "lat": "43.77439110", "lng": "-79.50481085", "type": "edu", "country": "Canada"}, {"name": "Weizmann Institute of Science", "source_name": "Weizmann Institute of Science", "street_adddress": "\u05de\u05db\u05d5\u05df \u05d5\u05d9\u05e6\u05de\u05df \u05dc\u05de\u05d3\u05e2, \u05e9\u05d3\u05e8\u05ea \u05de\u05e8\u05db\u05d5\u05e1 \u05d6\u05d9\u05d5, \u05de\u05e2\u05d5\u05e0\u05d5\u05ea \u05e9\u05d9\u05d9\u05df, \u05d0\u05d7\u05d5\u05d6\u05d5\u05ea \u05d4\u05e0\u05e9\u05d9\u05d0, \u05e8\u05d7\u05d5\u05d1\u05d5\u05ea, \u05de\u05d7\u05d5\u05d6 \u05d4\u05de\u05e8\u05db\u05d6, NO, \u05d9\u05e9\u05e8\u05d0\u05dc", "lat": "31.90784990", "lng": "34.81334092", "type": "edu", "country": "Israel"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1605.07824.pdf"], "doi": []}, {"id": "549d55a06c5402696e063ce36b411f341a64f8a9", "title": "Learning Deep Structure-Preserving Image-Text Embeddings", "addresses": [{"name": "University of Illinois, Urbana-Champaign", "source_name": "University of Illinois, Urbana-Champaign", "street_adddress": "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu", "country": "United States"}, {"name": "Georgia Institute of Technology", "source_name": "Georgia Institute of Technology", "street_adddress": "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1511.06078.pdf"], "doi": []}, {"id": "3f5b20c35f55417823f0201862d85af1f31e9348", "title": "Salience Biased Loss for Object Detection in Aerial Images", "addresses": [{"name": "University of Missouri-Columbia", "source_name": "University of Missouri-Columbia, USA", "street_adddress": "Columbia, MO 65211, USA", "lat": "38.94038080", "lng": "-92.32773750", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.08103.pdf"], "doi": []}, {"id": "cbe6739ecdb23d61f2ff74481c6b538ef953eb10", "title": "Learning to Learn: Model Regression Networks for Easy Small Sample Learning", "addresses": [{"name": "Robotics Institute", "source_name": "Robotics Institute", "street_adddress": "Institute for Field Robotics, \u0e1b\u0e23\u0e30\u0e0a\u0e32\u0e2d\u0e38\u0e17\u0e34\u0e28, \u0e01\u0e23\u0e38\u0e07\u0e40\u0e17\u0e1e\u0e21\u0e2b\u0e32\u0e19\u0e04\u0e23, \u0e40\u0e02\u0e15\u0e23\u0e32\u0e29\u0e0e\u0e23\u0e4c\u0e1a\u0e39\u0e23\u0e13\u0e30, \u0e01\u0e23\u0e38\u0e07\u0e40\u0e17\u0e1e\u0e21\u0e2b\u0e32\u0e19\u0e04\u0e23, 10140, \u0e1b\u0e23\u0e30\u0e40\u0e17\u0e28\u0e44\u0e17\u0e22", "lat": "13.65450525", "lng": "100.49423171", "type": "edu", "country": "Thailand"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/cbe6/739ecdb23d61f2ff74481c6b538ef953eb10.pdf"], "doi": []}, {"id": "a4e1a95c32e9477aa1b09073a1fd3ca129aacadc", "title": "Driver Identification System Using Convolutional Neural Network with Background Removal-based Infrared Data Augmentation", "addresses": [{"name": "Sogang University", "source_name": "Sogang University, Seoul, Republic of Korea", "street_adddress": "35 Baekbeom-ro, Sinsu-dong, Mapo-gu, Seoul, South Korea", "lat": "37.55094420", "lng": "126.94100230", "type": "edu", "country": "South Korea"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8500364", "http://doi.org/10.1109/IVS.2018.8500364"]}, {"id": "3e4d8bd8cb917db9bad1ed4382ccb266ab5fa411", "title": "Toward Efficient Simultaneous Detection and Segmentation", "addresses": [{"name": "Beijing Information Science and Technology University", "source_name": "Beijing Information Science and Technology University, Beijing, China", "street_adddress": "China, Beijing, Haidian, \u6e05\u6cb3\u56db\u62d4\u5b50", "lat": "40.04332040", "lng": "116.34181090", "type": "edu", "country": "China"}, {"name": "Beijing Institute of Technology", "source_name": "Beijing Institute of Technology University", "street_adddress": "\u5317\u4eac\u7406\u5de5\u5927\u5b66, 5, \u4e2d\u5173\u6751\u5357\u5927\u8857, \u4e2d\u5173\u6751, \u7a3b\u9999\u56ed\u5357\u793e\u533a, \u6d77\u6dc0\u533a, \u5317\u4eac\u5e02, 100872, \u4e2d\u56fd", "lat": "39.95866520", "lng": "116.30971281", "type": "edu", "country": "China"}, {"name": "Peking University", "source_name": "Peking University", "street_adddress": "\u5317\u4eac\u5927\u5b66, 5\u53f7, \u9890\u548c\u56ed\u8def, \u7a3b\u9999\u56ed\u5357\u793e\u533a, \u6d77\u6dc0\u533a, \u5317\u4eac\u5e02, 100871, \u4e2d\u56fd", "lat": "39.99223790", "lng": "116.30393816", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8499154", "http://doi.ieeecomputersociety.org/10.1109/BigMM.2018.8499154", "http://doi.org/10.1109/BigMM.2018.8499154"]}, {"id": "4f0b8f730273e9f11b2bfad2415485414b96299f", "title": "BDD100K: A Diverse Driving Video Database with Scalable Annotation Tooling", "addresses": [{"name": "UC Berkeley", "source_name": "UC Berkeley", "street_adddress": "Berkeley, CA, USA", "lat": "37.87189920", "lng": "-122.25853990", "type": "edu", "country": "United States"}, {"name": "Georgia Institute of Technology", "source_name": "Georgia Institute of Technology", "street_adddress": "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu", "country": "United States"}, {"name": "Peking University", "source_name": "Peking University", "street_adddress": "\u5317\u4eac\u5927\u5b66, 5\u53f7, \u9890\u548c\u56ed\u8def, \u7a3b\u9999\u56ed\u5357\u793e\u533a, \u6d77\u6dc0\u533a, \u5317\u4eac\u5e02, 100871, \u4e2d\u56fd", "lat": "39.99223790", "lng": "116.30393816", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.04687.pdf"], "doi": []}, {"id": "4f9beb035a3d196f653e8528303fdf9ded998e22", "title": "Can You See the (Linguistic) Difference? Exploring Mass/Count Distinction in Vision", "addresses": [{"name": "University of Trento", "source_name": "University of Trento", "street_adddress": "University of Trento, Via Giuseppe Verdi, Piedicastello, Trento, Territorio Val d'Adige, TN, TAA, 38122, Italia", "lat": "46.06588360", "lng": "11.11598940", "type": "edu", "country": "Italy"}, {"name": "University of Padova", "source_name": "University of Padova", "street_adddress": "Via Giovanni Gradenigo, 6, 35131 Padova PD, Italy", "lat": "45.40811720", "lng": "11.89437860", "type": "edu", "country": "Italy"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/4f9b/eb035a3d196f653e8528303fdf9ded998e22.pdf"], "doi": []}, {"id": "87e1ae939f3632f26a9878fe32674e338cb18094", "title": "C4Synth: Cross-Caption Cycle-Consistent Text-to-Image Synthesis", "addresses": [{"name": "IIT Hyderabad, India", "source_name": "IIT Hyderabad, Kandi, Telangana, 502285, India", "street_adddress": "IITH Main Road, Near NH-65, Sangareddy, Kandi, Telangana 502285, India", "lat": "17.59470330", "lng": "78.12310540", "type": "edu", "country": "India"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.10238.pdf"], "doi": []}, {"id": "7277fdf51bb3fc38f254a5546c53caa4169653c9", "title": "Domain Adaptation for Neural Networks by Parameter Augmentation", "addresses": [{"name": "University of Tokyo", "source_name": "University of Tokyo", "street_adddress": "\u6771\u4eac\u5927\u5b66 \u67cf\u30ad\u30e3\u30f3\u30d1\u30b9, \u5b66\u878d\u5408\u306e\u9053, \u67cf\u5e02, \u5343\u8449\u770c, \u95a2\u6771\u5730\u65b9, 277-8583, \u65e5\u672c", "lat": "35.90204480", "lng": "139.93622009", "type": "edu", "country": "Japan"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1607.00410.pdf"], "doi": []}, {"id": "32812f35efab1fc5bdbcc17d67f27bba31c720c6", "title": "Dropout during inference as a model for neurological degeneration in an image captioning network", "addresses": [{"name": "University of Toronto", "source_name": "University of Toronto", "street_adddress": "University of Toronto, St. George Street, Bloor Street Culture Corridor, Old Toronto, Toronto, Ontario, M5S 1A5, Canada", "lat": "43.66333345", "lng": "-79.39769975", "type": "edu", "country": "Canada"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.03747.pdf"], "doi": []}, {"id": "9534a04de5e99a44df76ea30140f66a62e83fdaa", "title": "Iteratively Trained Interactive Segmentation", "addresses": [{"name": "RWTH Aachen University", "source_name": "RWTH Aachen University", "street_adddress": "RWTH Aachen, Mies-van-der-Rohe-Stra\u00dfe, K\u00f6nigsh\u00fcgel, Aachen-Mitte, Aachen, St\u00e4dteregion Aachen, Regierungsbezirk K\u00f6ln, Nordrhein-Westfalen, 52074, Deutschland", "lat": "50.77917030", "lng": "6.06728733", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.04398.pdf"], "doi": []}, {"id": "3349fab3a5e2b7c5194289bdc839f87f556ea3ef", "title": "Social Image Tags as a Source of Word Embeddings: A Task-oriented Evaluation", "addresses": [{"name": "Waseda University", "source_name": "Waseda University", "street_adddress": "\u65e9\u7a32\u7530\u5927\u5b66 \u5317\u4e5d\u5dde\u30ad\u30e3\u30f3\u30d1\u30b9, 2-2, \u6709\u6bdb\u5f15\u91ce\u7dda, \u516b\u5e61\u897f\u533a, \u5317\u4e5d\u5dde\u5e02, \u798f\u5ca1\u770c, \u4e5d\u5dde\u5730\u65b9, 808-0135, \u65e5\u672c", "lat": "33.88987280", "lng": "130.70856205", "type": "edu", "country": "Japan"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/3349/fab3a5e2b7c5194289bdc839f87f556ea3ef.pdf"], "doi": []}, {"id": "eb7e0dfc61f3f9993a39316ccaaa263059b3a108", "title": "Spatially Adaptive Computation Time for Residual Networks", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}, {"name": "Google", "source_name": "Google, Inc.", "street_adddress": "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "lat": "37.42199990", "lng": "-122.08405750", "type": "company", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1612.02297.pdf"], "doi": []}, {"id": "16beefb2f8d0d61e536bf20766e485499906c2e0", "title": "Image Surveillance Assistant", "addresses": [{"name": "Naval Research Laboratory", "source_name": "Naval Research Laboratory", "street_adddress": "Naval Research Laboratory Post Office, 4555, Overlook Avenue Southwest, Washington, D.C., 20375, USA", "lat": "38.82313810", "lng": "-77.01789020", "type": "mil", "country": "United States"}], "year": "2016", "pdf": ["http://cs.umd.edu/~maynord/Image_Surveillance_Assistant.pdf", "https://www.nrl.navy.mil/itd/aic/sites/www.nrl.navy.mil.itd.aic/files/pdfs/(Maynord+%20WACV-16%20WS)%20Intelligent%20Surveillance%20Assistant.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7470119", "http://doi.ieeecomputersociety.org/10.1109/WACVW.2016.7470119", "http://doi.org/10.1109/WACVW.2016.7470119"]}, {"id": "0bbb40e5b9e546a3f4e7340b2980059065c99203", "title": "Learning Object Detectors from Scratch with Gated Recurrent Feature Pyramids", "addresses": [{"name": "Beckman Institute", "source_name": "Beckman Institute", "street_adddress": "Beckman Institute, The Presidents' Walk, Urbana, Champaign County, Illinois, 61801-2341, USA", "lat": "40.11571585", "lng": "-88.22750772", "type": "edu", "country": "United States"}, {"name": "Fudan University", "source_name": "Fudan University", "street_adddress": "\u590d\u65e6\u5927\u5b66, 220, \u90af\u90f8\u8def, \u4e94\u89d2\u573a\u8857\u9053, \u6768\u6d66\u533a, \u4e0a\u6d77\u5e02, 200433, \u4e2d\u56fd", "lat": "31.30104395", "lng": "121.50045497", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1712.00886.pdf"], "doi": []}, {"id": "edafa697ba68874d608015b521c43d04e3584992", "title": "Gated Recurrent Capsules for Visual Word Embeddings", "addresses": [{"name": "EURECOM", "source_name": "EURECOM", "street_adddress": "Campus SophiaTech, 450 Route des Chappes, 06410 Biot, France", "lat": "43.61438600", "lng": "7.07112500", "type": "edu", "country": "France"}], "year": "2019", "pdf": ["https://pdfs.semanticscholar.org/edaf/a697ba68874d608015b521c43d04e3584992.pdf"], "doi": []}, {"id": "6e09a291d61f0e26ce3522a1b0fce952fb811090", "title": "Generative Attention Model with Adversarial Self-learning for Visual Question Answering", "addresses": [{"name": "National University of Singapore", "source_name": "National University of Singapore", "street_adddress": "NUS, Former 1936 British Outpost, Nepal Hill, Clementi, Southwest, 117542, Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu", "country": "Singapore"}], "year": "2017", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3126695"]}, {"id": "46253ab8721ced8c9b94234f3a2401efde1e3f2a", "title": "Language Models for Image Captioning: The Quirks and What Works", "addresses": [{"name": "Microsoft", "source_name": "Microsoft Corporation, Redmond, WA, USA", "street_adddress": "One Microsoft Way, Redmond, WA 98052, USA", "lat": "47.64233180", "lng": "-122.13693020", "type": "company", "country": "United States"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1505.01809.pdf"], "doi": []}, {"id": "402324c77b7b4040810480d6947c7db92d491308", "title": "Socratic Learning: Augmenting Generative Models to Incorporate Latent Subsets in Training Data", "addresses": [{"name": "Stanford University", "source_name": "Stanford University", "street_adddress": "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1610.08123.pdf"], "doi": []}, {"id": "64e2ea4ca45cbf1a6ef35f3448c5799354e2f603", "title": "Visual and Semantic Knowledge Transfer for Large Scale Semi-Supervised Object Detection", "addresses": [{"name": "University of Sheffield", "source_name": "The University of Sheffield", "street_adddress": "University of Sheffield, Portobello, Port Mahon, Saint George's, Sheffield, Yorkshire and the Humber, England, S1 4DP, UK", "lat": "53.38152480", "lng": "-1.48068143", "type": "edu", "country": "United Kingdom"}, {"name": "National Institutes of Health (NIH) Clinical Center, Bethesda, MD", "source_name": "National Institutes of Health (NIH) Clinical Center, Bethesda, MD", "street_adddress": "10 Center Dr, Bethesda, MD 20814, USA", "lat": "39.00252720", "lng": "-77.10437890", "type": "edu", "country": "United States"}, {"name": "\u00c9cole Centrale de Lyon", "source_name": "Laboratoire LIRIS", "street_adddress": "40 Avenue Guy de Collongue, 69130 \u00c9cully, France", "lat": "45.78359660", "lng": "4.76789480", "type": "edu", "country": "France"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8103045"]}, {"id": "14c2321851fb5ae580a19726dd2753a525d6ad76", "title": "Grounding of Textual Phrases in Images by Reconstruction", "addresses": [{"name": "Max Planck Institute for Informatics", "source_name": "Max Planck Institute for Informatics", "street_adddress": "MPII, E1 4, Campus, Universit\u00e4t, Sankt Johann, Bezirk Mitte, Saarbr\u00fccken, Regionalverband Saarbr\u00fccken, Saarland, 66123, Deutschland", "lat": "49.25795660", "lng": "7.04577417", "type": "edu", "country": "Germany"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1511.03745.pdf"], "doi": []}, {"id": "8176e3aea16595b3fe6afdb6c745c9eca98ece06", "title": "The Helping Hand: An Assistive Manipulation Framework Using Augmented Reality and Tongue-Drive Interfaces", "addresses": [{"name": "Georgia Institute of Technology", "source_name": "Georgia Institute of Technology", "street_adddress": "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu", "country": "United States"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8512668", "http://doi.org/10.1109/EMBC.2018.8512668", "https://www.ncbi.nlm.nih.gov/pubmed/30440831"]}, {"id": "2bc70a13426c79c192c5e57f8a0041d8ecf628a8", "title": "Image Labeling with Markov Random Fields and Conditional Random Fields", "addresses": [{"name": "Robotics Institute", "source_name": "Robotics Institute", "street_adddress": "Institute for Field Robotics, \u0e1b\u0e23\u0e30\u0e0a\u0e32\u0e2d\u0e38\u0e17\u0e34\u0e28, \u0e01\u0e23\u0e38\u0e07\u0e40\u0e17\u0e1e\u0e21\u0e2b\u0e32\u0e19\u0e04\u0e23, \u0e40\u0e02\u0e15\u0e23\u0e32\u0e29\u0e0e\u0e23\u0e4c\u0e1a\u0e39\u0e23\u0e13\u0e30, \u0e01\u0e23\u0e38\u0e07\u0e40\u0e17\u0e1e\u0e21\u0e2b\u0e32\u0e19\u0e04\u0e23, 10140, \u0e1b\u0e23\u0e30\u0e40\u0e17\u0e28\u0e44\u0e17\u0e22", "lat": "13.65450525", "lng": "100.49423171", "type": "edu", "country": "Thailand"}, {"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.11323.pdf"], "doi": []}, {"id": "af55a25cdd3a2c138e755d5206b35457c1f5760b", "title": "DistInit: Learning Video Representations without a Single Labeled Video", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.09244.pdf"], "doi": []}, {"id": "9a7784eea6bfa62bf2834ee0b87a3cdda46006f2", "title": "Digital Comics Image Indexing Based on Deep Learning", "addresses": [{"name": "University of La Rochelle", "source_name": "Laboratoire MIA, University of La Rochelle, La Rochelle, France", "street_adddress": "23 Avenue Albert Einstein, 17000 La Rochelle, France", "lat": "46.14764610", "lng": "-1.15494150", "type": "edu", "country": "France"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/9a77/84eea6bfa62bf2834ee0b87a3cdda46006f2.pdf"], "doi": []}, {"id": "719969807953d7ea8bda0397b1aadbaa6e205718", "title": "Automatic Dataset Augmentation", "addresses": [{"name": "Harbin Institute of Technology", "source_name": "Harbin Institute of Technology", "street_adddress": "\u54c8\u5c14\u6ee8\u5de5\u4e1a\u5927\u5b66, \u53f8\u4ee4\u8857, \u5357\u5c97\u533a, \u54c8\u5c14\u6ee8\u5e02 / Harbin, \u9ed1\u9f99\u6c5f\u7701, 150000, \u4e2d\u56fd", "lat": "45.74139210", "lng": "126.62552755", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.08201.pdf"], "doi": []}, {"id": "8de065f412a7d739dff40044212c8506b5c52bf7", "title": "Multi-Person Pose Estimation for PoseTrack with Enhanced Part Affinity Fields", "addresses": [{"name": "Beijing, China", "source_name": "Beijing, China", "street_adddress": "Beijing, China", "lat": "39.90419990", "lng": "116.40739630", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/8de0/65f412a7d739dff40044212c8506b5c52bf7.pdf"], "doi": []}, {"id": "80ef252a17d343ac7b12485c117d6df4a409dee5", "title": "Image Caption with Endogenous\u2013Exogenous Attention", "addresses": [{"name": "Sun Yat-Sen University", "source_name": "Sun Yat-Sen University", "street_adddress": "\u4e2d\u5927, \u65b0\u6e2f\u897f\u8def, \u9f99\u8239\u6ed8, \u5eb7\u4e50, \u6d77\u73e0\u533a (Haizhu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510105, \u4e2d\u56fd", "lat": "23.09461185", "lng": "113.28788994", "type": "edu", "country": "China"}], "year": "2019", "pdf": [], "doi": ["http://doi.org/10.1007/s11063-019-09979-7"]}, {"id": "bd2a3ad4f28757791c9335033f39ac31cb84b8c7", "title": "ScaleNet: Guiding Object Proposal Generation in Supermarkets and Beyond", "addresses": [{"name": "Johns Hopkins University", "source_name": "Johns Hopkins University", "street_adddress": "Baltimore, MD 21218, USA", "lat": "39.32990130", "lng": "-76.62051770", "type": "edu", "country": "United States"}, {"name": "Shanghai University", "source_name": "Shanghai University", "street_adddress": "\u4e0a\u6d77\u5927\u5b66, \u9526\u79cb\u8def, \u5927\u573a\u9547, \u5b9d\u5c71\u533a (Baoshan), \u4e0a\u6d77\u5e02, 201906, \u4e2d\u56fd", "lat": "31.32235655", "lng": "121.38400941", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.06752.pdf"], "doi": []}, {"id": "8a1f46d56ef6dfa34412986a802b5affe2512000", "title": "Aided Action Recognition Using Single Images", "addresses": [{"name": "Lehigh University", "source_name": "Lehigh University", "street_adddress": "Lehigh University, Library Drive, Sayre Park, Bethlehem, Northampton County, Pennsylvania, 18015, USA", "lat": "40.60680280", "lng": "-75.37824880", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/8a1f/46d56ef6dfa34412986a802b5affe2512000.pdf"], "doi": []}, {"id": "6d3d61ef9b5ff6d41badbc3d40ea23acbbc9c3fe", "title": "Learning to Evaluate Image Captioning", "addresses": [{"name": "Cornell University", "source_name": "Cornell University", "street_adddress": "Cornell University, Forest Home Drive, Forest Home, Tompkins County, New York, 14853, USA", "lat": "42.45055070", "lng": "-76.47835130", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.06422.pdf"], "doi": []}, {"id": "2df1688afdb470a9d9eee95e41fc34ebd0c9036b", "title": "Deep Multimodal Learning: An Effective Method for Video Classification", "addresses": [{"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.12563.pdf"], "doi": []}, {"id": "ed605dc1e69dccabf47044499e7ec26e30b72b58", "title": "Pre-gen Metrics: Predicting Caption Quality Metrics Without Generating Captions", "addresses": [{"name": "University of Malta", "source_name": "University of Malta", "street_adddress": "University of Malta, Ring Road, Japanese Garden, L-Imsida, Malta, MSD 9027, Malta", "lat": "35.90232260", "lng": "14.48341890", "type": "edu", "country": "Malta"}], "year": "2018", "pdf": [], "doi": ["http://doi.org/10.1007/978-3-030-11018-5_10"]}, {"id": "c0d0ef94dd3c53c3130b5b8ce38d981929b7adb2", "title": "Weakly- and Semi-supervised Panoptic Segmentation", "addresses": [{"name": "University of Oxford", "source_name": "University of Oxford", "street_adddress": "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "lat": "51.75345380", "lng": "-1.25400997", "type": "edu", "country": "United Kingdom"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.03575.pdf"], "doi": []}, {"id": "31b05f65405534a696a847dd19c621b7b8588263", "title": "UMDFaces: An annotated face dataset for training deep networks", "addresses": [{"name": "University of Maryland", "source_name": "University of Maryland", "street_adddress": "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu", "country": "United States"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8272731"]}, {"id": "43eee49e372e5299608a79f8491fcf40998028df", "title": "Complex event processing for content-based text, image, and video retrieval", "addresses": [{"name": "Army Research Laboratory, Computational and Information Sciences Directorate", "source_name": "Army Research Laboratory, Computational and Information Sciences Directorate", "street_adddress": "2800 Powder Mill Rd, Adelphi, MD 20783, USA", "lat": "39.02985870", "lng": "-76.96380270", "type": "mil", "country": "United States"}, {"name": "Army Research Laboratory, Sensors and Electron Devices Directorate", "source_name": "Army Research Laboratory, Sensors and Electron Devices Directorate", "street_adddress": "2800 Powder Mill Rd, Adelphi, MD 20783, USA", "lat": "39.02985870", "lng": "-76.96380270", "type": "mil", "country": "United States"}, {"name": "Atos Turkey, Ankara, Turkey", "source_name": "Atos Turkey, Ankara, Turkey", "street_adddress": "No: 21, \u00dcniversiteler Mh., Teknokent Silikon Bloklar, 06800 \u00c7ankaya/Ankara, Turkey", "lat": "39.89961620", "lng": "32.77396810", "type": "edu", "country": "Turkey"}, {"name": "Defence Research and Development Canada, Toronto, Ontario", "source_name": "Defence Research and Development Canada, Toronto, Ontario", "street_adddress": "1133 Sheppard Ave W, North York, ON M3K 2C9, Canada", "lat": "43.75107650", "lng": "-79.46945700", "type": "mil", "country": "Canada"}, {"name": "Defence Research and Development Canada, Valcartier, Quebec", "source_name": "Defence Research and Development Canada, Valcartier, Quebec", "street_adddress": "400 Cumberland St, Ottawa, ON K1N 1J8, Canada", "lat": "45.42826030", "lng": "-75.68804370", "type": "mil", "country": "Canada"}, {"name": "TNO, The Hague, Netherlands", "source_name": "TNO, The Hague, Netherlands", "street_adddress": "Anna van Buerenplein 1, 2595 DA Den Haag, Netherlands", "lat": "52.08227700", "lng": "4.32580700", "type": "edu", "country": "Netherlands"}, {"name": "UK Defence Science and Technology Laboratory, Porton, Salisbury, UK", "source_name": "UK Defence Science and Technology Laboratory, Porton, Salisbury, UK", "street_adddress": "Porton Down, Salisbury SP4 0JQ, UK", "lat": "51.13122970", "lng": "-1.70368420", "type": "mil", "country": "United Kingdom"}, {"name": "United States Air Force Research Laboratory, Dayton, OH", "source_name": "United States Air Force Research Laboratory, Dayton, OH", "street_adddress": "1864 4th St, Wright-Patterson AFB, OH 45433, USA", "lat": "39.79084110", "lng": "-84.09897580", "type": "mil", "country": "United States"}], "year": "2016", "pdf": ["http://www.dtic.mil/dtic/tr/fulltext/u2/1011094.pdf", "https://apps.dtic.mil/dtic/tr/fulltext/u2/1011094.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7496546"]}, {"id": "f43012db4836cf671a2a095413ba5ec6725e4a41", "title": "Deep TripletQuantization", "addresses": [{"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}, {"name": "Microsoft Research Asia", "source_name": "Microsoft Research Asia", "street_adddress": "1 Memorial Dr, Cambridge, MA 02142, USA", "lat": "42.36142560", "lng": "-71.08120920", "type": "company", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/f430/12db4836cf671a2a095413ba5ec6725e4a41.pdf"], "doi": []}, {"id": "ebe7eda4fd10caa326d57b93e8a1e2a13e09a403", "title": "TSCSet: A Crowdsourced Time-Sync Comment Dataset for Exploration of User Experience Improvement", "addresses": [{"name": "Rutgers University", "source_name": "Rutgers University", "street_adddress": "Rutgers Cook Campus - North, Biel Road, New Brunswick, Middlesex County, New Jersey, 08901, USA", "lat": "40.47913175", "lng": "-74.43168868", "type": "edu", "country": "United States"}, {"name": "Tongji University", "source_name": "Tongji University", "street_adddress": "\u540c\u6d4e\u5927\u5b66, 1239, \u56db\u5e73\u8def, \u6c5f\u6e7e, \u8679\u53e3\u533a, \u4e0a\u6d77\u5e02, 200092, \u4e2d\u56fd", "lat": "31.28473925", "lng": "121.49694909", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3172966"]}, {"id": "5ba8bb7d204e7a5a29a043792546577500e2e5c1", "title": "Background Appearance Modeling with Applications to Visual Object Detection in an Open-Pit Mine", "addresses": [{"name": "Queensland University of Technology", "source_name": "Queensland University of Technology", "street_adddress": "Queensland University of Technology, Macgregor Lane, Merthyr, South Brisbane, Brisbane, QLD, 4000, Australia", "lat": "-27.47715625", "lng": "153.02841004", "type": "edu", "country": "Australia"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/5ba8/bb7d204e7a5a29a043792546577500e2e5c1.pdf"], "doi": []}, {"id": "48320a4be9cc741fdb28ad72f359c449e41309cc", "title": "Manga109 dataset and creation of metadata", "addresses": [{"name": "University of Tokyo", "source_name": "University of Tokyo", "street_adddress": "\u6771\u4eac\u5927\u5b66 \u67cf\u30ad\u30e3\u30f3\u30d1\u30b9, \u5b66\u878d\u5408\u306e\u9053, \u67cf\u5e02, \u5343\u8449\u770c, \u95a2\u6771\u5730\u65b9, 277-8583, \u65e5\u672c", "lat": "35.90204480", "lng": "139.93622009", "type": "edu", "country": "Japan"}], "year": "2016", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3011551"]}, {"id": "6701efa7f715b3c296843b8ff5414a6610711cf9", "title": "Semi-automatic image and video annotation system for generating ground truth information", "addresses": [{"name": "Korea Electronics Technology Institute", "source_name": "Korea Electronics Technology Institute", "street_adddress": "South Korea, Gyeonggi-do, Seongnam-si, Bundang-gu, \uc0c8\ub098\ub9ac\ub85c 25 (\uc57c\ud0d1\ub3d9) KETI \uc804\uc790\ubd80\ud488\uc5f0\uad6c\uc6d0", "lat": "37.40391700", "lng": "127.15978600", "type": "edu", "country": "South Korea"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8343233", "http://doi.ieeecomputersociety.org/10.1109/ICOIN.2018.8343233", "http://doi.org/10.1109/ICOIN.2018.8343233"]}, {"id": "1334d274bca9c94fed724ecfac7e36d3789aea38", "title": "ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detector", "addresses": [{"name": "Georgia Institute of Technology", "source_name": "Georgia Institute of Technology", "street_adddress": "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu", "country": "United States"}, {"name": "Intel Corporation, Hillsboro, OR, USA", "source_name": "Intel Corporation, Hillsboro, OR, USA", "street_adddress": "6397 NE Evergreen Pkwy, Hillsboro, OR 97124, USA", "lat": "45.55236000", "lng": "-122.91429880", "type": "company", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.05810.pdf"], "doi": []}, {"id": "632fa986bed53862d83918c2b71ab953fd70d6cc", "title": "What Face and Body Shapes Can Tell About Height", "addresses": [{"name": "EPFL", "source_name": "EPFL", "street_adddress": "Route Cantonale, 1015 Lausanne, Switzerland", "lat": "46.51905570", "lng": "6.56675760", "type": "edu", "country": "Switzerland"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.10355.pdf"], "doi": []}, {"id": "2bf41bf420c8d86dd1bffbacd28c70fa8b12b6dd", "title": "Counting the uncountable: deep semantic density estimation from Space", "addresses": [{"name": "ETH Zurich", "source_name": "ETH Zurich", "street_adddress": "R\u00e4mistrasse 101, 8092 Z\u00fcrich, Switzerland", "lat": "47.37631300", "lng": "8.54766990", "type": "edu", "country": "Switzerland"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.07091.pdf"], "doi": []}, {"id": "e4845fb1e624965d4f036d7fd32e8dcdd2408148", "title": "YOLOv3: An Incremental Improvement", "addresses": [{"name": "University of Washington", "source_name": "University of Washington", "street_adddress": "University of Washington, Rainier Vista, Montlake, University District, Seattle, King County, Washington, 98195, USA", "lat": "47.65432380", "lng": "-122.30800894", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.02767.pdf"], "doi": []}, {"id": "663617c728b18e333acb5279e9b1095eeda9287e", "title": "The 2018 DAVIS Challenge on Video Object Segmentation-CVPR 2018 Workshops", "addresses": [{"name": "KTH Royal Institute of Technology, Stockholm", "source_name": "KTH   Royal Institute of Technology, Stockholm", "street_adddress": "KTH, Teknikringen, L\u00e4rkstaden, Norra Djurg\u00e5rden, \u00d6stermalms stadsdelsomr\u00e5de, Sthlm, Stockholm, Stockholms l\u00e4n, Svealand, 114 28, Sverige", "lat": "59.34986645", "lng": "18.07063213", "type": "edu", "country": "Sweden"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/bd1c/72de32b9dafc2c8b392ed26a9977af62fe58.pdf"], "doi": []}, {"id": "fb0bbbc159dad0113f5d01ac736945feeced1247", "title": "Appearance and Gait-Based Progressive Person Re-Identification for Surveillance Systems", "addresses": [{"name": "Beijing University of Posts and Telecommunications", "source_name": "Beijing University of Posts and Telecommunications", "street_adddress": "\u5317\u4eac\u90ae\u7535\u5927\u5b66, \u897f\u571f\u57ce\u8def, \u6d77\u6dc0\u533a, \u5317\u4eac\u5e02, 100082, \u4e2d\u56fd", "lat": "39.96014880", "lng": "116.35193921", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8499460", "http://doi.org/10.1109/BigMM.2018.8499460"]}, {"id": "15147ca5866dc5fbcfa0d91259798599004d051d", "title": "CO-FILTERING HUMAN INTERACTION AND OBJECT SEGMENTATION A Degree Thesis Submitted to the Faculty of the Escola Te\u0300cnica d'Enginyeria de Telecomunicacio\u0301 de Barcelona", "addresses": [{"name": "Universitat Polit\u00e8cnica de Catalunya", "source_name": "Universitat Polit\u00e8cnica de Catalunya", "street_adddress": "Campus Nord, Carrer de Jordi Girona, 1, 3, 08034 Barcelona, Spain", "lat": "41.38800400", "lng": "2.11328040", "type": "edu", "country": "Spain"}], "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/1514/7ca5866dc5fbcfa0d91259798599004d051d.pdf"], "doi": []}, {"id": "6d880f543e583cf1ba4333be7f3845de4dcbda64", "title": "Recursive Visual Attention in Visual Dialog", "addresses": [{"name": "Renmin University of China", "source_name": "Beijing Key Laboratory of Big Data Management and Analysis Methods, Renmin University of China, Beijing, 100872, China", "street_adddress": "59 Zhongguancun St, Haidian Qu, China, 100872", "lat": "39.96960620", "lng": "116.31881450", "type": "edu", "country": "China"}, {"name": "Nanyang Technological University", "source_name": "Nanyang Technological University", "street_adddress": "NTU, Faculty Avenue, Jurong West, Southwest, 637460, Singapore", "lat": "1.34841040", "lng": "103.68297965", "type": "edu", "country": "Singapore"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.02664.pdf"], "doi": []}, {"id": "cba8b9949e71ff485a4ecba33128e2f206651cac", "title": "An RGBD segmentation model for robot vision learned from synthetic data", "addresses": [{"name": "Georgia Institute of Technology", "source_name": "Georgia Institute of Technology", "street_adddress": "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/cba8/b9949e71ff485a4ecba33128e2f206651cac.pdf"], "doi": []}, {"id": "b93cd1e6f1aee81f4f94452c0091d11ee0cb8af3", "title": "Real-world Mapping of Gaze Fixations Using Instance Segmentation for Road Construction Safety Applications", "addresses": [{"name": "North Carolina State University", "source_name": "North Carolina State University", "street_adddress": "North Carolina State University, Oval Drive, West Raleigh, Raleigh, Wake County, North Carolina, 27695, USA", "lat": "35.77184965", "lng": "-78.67408695", "type": "edu", "country": "United States"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.11078.pdf"], "doi": []}, {"id": "4c33746fc5688da61059daa93978ac887f04cce8", "title": "Trainable performance upper bounds for image and video captioning", "addresses": [{"name": "New York University", "source_name": "New York University", "street_adddress": "NYU, West 4th Street, NoHo Historic District, NoHo, Manhattan, Manhattan Community Board 2, New York County, NYC, New York, 10012, USA", "lat": "40.72925325", "lng": "-73.99625394", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/e97f/10c2a4d7edac33597692e6dc243bd86adf10.pdf"], "doi": []}, {"id": "c682ff7a573082c5b69880c4bf84cdd464b70ae5", "title": "Dial2Desc: End-to-end Dialogue Description Generation", "addresses": [{"name": "Zhejiang University", "source_name": "Zhejiang University", "street_adddress": "\u6d59\u6c5f\u5927\u5b66\u4e4b\u6c5f\u6821\u533a, \u4e4b\u6c5f\u8def, \u8f6c\u5858\u8857\u9053, \u897f\u6e56\u533a (Xihu), \u676d\u5dde\u5e02 Hangzhou, \u6d59\u6c5f\u7701, 310008, \u4e2d\u56fd", "lat": "30.19331415", "lng": "120.11930822", "type": "edu", "country": "China"}, {"name": "University of Southern California", "source_name": "University of Southern California", "street_adddress": "University of Southern California, Watt Way, Saint James Park, LA, Los Angeles County, California, 90089, USA", "lat": "34.02241490", "lng": "-118.28634407", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.00185.pdf"], "doi": []}, {"id": "3899b49ca98a134fb9d33feab458f2092da32096", "title": "Faster Bounding Box Annotation for Object Detection in Indoor Scenes", "addresses": [{"name": "Sandvik Mining and Construction Oyj, Tampere, Finland", "source_name": "Sandvik Mining and Construction Oyj, Tampere, Finland", "street_adddress": "Pihtisulunkatu 9, 33330 Tampere, Finland", "lat": "61.50907030", "lng": "23.57149070", "type": "company", "country": "Finland"}, {"name": "Tampere University of Technology", "source_name": "Tampere University of Technology", "street_adddress": "TTY, 10, Korkeakoulunkatu, Finninm\u00e4ki, Hervanta, Tampere, Tampereen seutukunta, Pirkanmaa, L\u00e4nsi- ja Sis\u00e4-Suomen aluehallintovirasto, L\u00e4nsi-Suomi, Manner-Suomi, 33720, Suomi", "lat": "61.44964205", "lng": "23.85877462", "type": "edu", "country": "Finland"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8611732"]}, {"id": "2dda7f46bbb8684a3a497dd40aabd4d759a62386", "title": "YouCookII Dataset", "addresses": [{"name": "Robotics Institute", "source_name": "Robotics Institute", "street_adddress": "Institute for Field Robotics, \u0e1b\u0e23\u0e30\u0e0a\u0e32\u0e2d\u0e38\u0e17\u0e34\u0e28, \u0e01\u0e23\u0e38\u0e07\u0e40\u0e17\u0e1e\u0e21\u0e2b\u0e32\u0e19\u0e04\u0e23, \u0e40\u0e02\u0e15\u0e23\u0e32\u0e29\u0e0e\u0e23\u0e4c\u0e1a\u0e39\u0e23\u0e13\u0e30, \u0e01\u0e23\u0e38\u0e07\u0e40\u0e17\u0e1e\u0e21\u0e2b\u0e32\u0e19\u0e04\u0e23, 10140, \u0e1b\u0e23\u0e30\u0e40\u0e17\u0e28\u0e44\u0e17\u0e22", "lat": "13.65450525", "lng": "100.49423171", "type": "edu", "country": "Thailand"}, {"name": "University of Michigan", "source_name": "University of Michigan", "street_adddress": "University of Michigan, 500, Hayward Street, Ann Arbor, Washtenaw County, Michigan, 48109, USA", "lat": "42.29421420", "lng": "-83.71003894", "type": "edu", "country": "United States"}, {"name": "University of Rochester", "source_name": "University of Rochester", "street_adddress": "Memorial Art Gallery, 500, University Avenue, East End, Rochester, Monroe County, New York, 14607, USA", "lat": "43.15769690", "lng": "-77.58829158", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/2dda/7f46bbb8684a3a497dd40aabd4d759a62386.pdf"], "doi": []}, {"id": "93b689145277f7594e4bc0af2ffec5d3a31cc1fa", "title": "Leveraging Convolutional Pose Machines for Fast and Accurate Head Pose Estimation", "addresses": [{"name": "IDIAP Research Institute", "source_name": "IDIAP Research Institute", "street_adddress": "Idiap Research Institute, Parking Centre du parc, Martigny, Valais/Wallis, 1920, Schweiz/Suisse/Svizzera/Svizra", "lat": "46.10923700", "lng": "7.08453549", "type": "edu", "country": "Switzerland"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8594223"]}, {"id": "14198efb1ea9d1c621dcac44e9c5aad349c0d69f", "title": "Learning to Segment Human by Watching YouTube", "addresses": [{"name": "Adobe Research, San Jose, CA", "source_name": "Adobe Research, San Jose, CA 95110, USA", "street_adddress": "345 Park Ave, San Jose, CA 95110, USA", "lat": "37.33093070", "lng": "-121.89404850", "type": "company", "country": "United States"}, {"name": "National University of Singapore", "source_name": "National University of Singapore", "street_adddress": "NUS, Former 1936 British Outpost, Nepal Hill, Clementi, Southwest, 117542, Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu", "country": "Singapore"}, {"name": "SnapChat Inc., Venice, CA", "source_name": "SnapChat Inc., Venice, CA", "street_adddress": "2772 Donald Douglas Loop N, Santa Monica, CA 90405, USA", "lat": "34.01629660", "lng": "-118.45349590", "type": "company", "country": "United States"}, {"name": "Sun Yat-Sen University", "source_name": "Sun Yat-Sen University", "street_adddress": "\u4e2d\u5927, \u65b0\u6e2f\u897f\u8def, \u9f99\u8239\u6ed8, \u5eb7\u4e50, \u6d77\u73e0\u533a (Haizhu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510105, \u4e2d\u56fd", "lat": "23.09461185", "lng": "113.28788994", "type": "edu", "country": "China"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7534869"]}, {"id": "72976d066d38d3d378d75dcf1467b0a295acad6b", "title": "iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection", "addresses": [{"name": "Virginia Tech", "source_name": "Virginia Tech", "street_adddress": "Blacksburg, VA 24061, USA", "lat": "37.22838430", "lng": "-80.42341670", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.10437.pdf"], "doi": []}, {"id": "7fda1edac608bc67e55ac3d7c9dc5a542d8f8aee", "title": "Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding", "addresses": [{"name": "Max Planck Institute for Informatics", "source_name": "Max Planck Institute for Informatics", "street_adddress": "MPII, E1 4, Campus, Universit\u00e4t, Sankt Johann, Bezirk Mitte, Saarbr\u00fccken, Regionalverband Saarbr\u00fccken, Saarland, 66123, Deutschland", "lat": "49.25795660", "lng": "7.04577417", "type": "edu", "country": "Germany"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1606.01847.pdf"], "doi": []}, {"id": "54830a1cf8606a5183561357b4004088718e4141", "title": "Deep Watershed Detector for Music Object Recognition", "addresses": [{"name": "ZHAW Datalab", "source_name": "ZHAW Datalab", "street_adddress": "Gertrudstrasse 15, 8400 Winterthur, Switzerland", "lat": "47.49991300", "lng": "8.72052200", "type": "edu", "country": "Switzerland"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.10548.pdf"], "doi": []}, {"id": "e772c6ea8a30ec21c3ede6c8abfd540621174fc2", "title": "Semi- and weakly-supervised human pose estimation", "addresses": [{"name": "Toyota Technological Institute", "source_name": "Toyota Technological Institute", "street_adddress": "6045 S Kenwood Ave, Chicago, IL 60637, USA", "lat": "41.78469820", "lng": "-87.59258480", "type": "edu", "country": "United States"}, {"name": "Nara Institute of Science and Technology, Japan", "source_name": "Nara Institute of Science and Technology, Japan", "street_adddress": "8916\u756a\u5730\u2212\uff15 Takayamacho, Ikoma, Nara Prefecture 630-0192, Japan", "lat": "34.73211210", "lng": "135.73285850", "type": "edu", "country": "Japan"}], "year": "2018", "pdf": ["https://www.toyota-ti.ac.jp/Lab/Denshi/iim/ukita/MyPapers/CVIU2018_Pose_preprint.pdf"], "doi": ["http://doi.org/10.1016/j.cviu.2018.02.003"]}, {"id": "94d177db3f198a3571576e562b4d3d9e816eb3cf", "title": "Dynamic Object Scanning: Object-Based Elastic Timeline for Quickly Browsing First-Person Videos", "addresses": [{"name": "University of Tokyo", "source_name": "University of Tokyo", "street_adddress": "\u6771\u4eac\u5927\u5b66 \u67cf\u30ad\u30e3\u30f3\u30d1\u30b9, \u5b66\u878d\u5408\u306e\u9053, \u67cf\u5e02, \u5343\u8449\u770c, \u95a2\u6771\u5730\u65b9, 277-8583, \u65e5\u672c", "lat": "35.90204480", "lng": "139.93622009", "type": "edu", "country": "Japan"}, {"name": "Waseda University", "source_name": "Waseda University", "street_adddress": "\u65e9\u7a32\u7530\u5927\u5b66 \u5317\u4e5d\u5dde\u30ad\u30e3\u30f3\u30d1\u30b9, 2-2, \u6709\u6bdb\u5f15\u91ce\u7dda, \u516b\u5e61\u897f\u533a, \u5317\u4e5d\u5dde\u5e02, \u798f\u5ca1\u770c, \u4e5d\u5dde\u5730\u65b9, 808-0135, \u65e5\u672c", "lat": "33.88987280", "lng": "130.70856205", "type": "edu", "country": "Japan"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3186501"]}, {"id": "4a9831e5fec549edee454709048a51997ef60fb7", "title": "Did the Model Understand the Question?", "addresses": [{"name": "University of Chicago", "source_name": "THE UNIVERSITY OF CHICAGO", "street_adddress": "University of Chicago, South Ellis Avenue, Woodlawn, Chicago, Cook County, Illinois, 60637, USA", "lat": "41.78468745", "lng": "-87.60074933", "type": "edu", "country": "United States"}, {"name": "Google", "source_name": "Google, Inc.", "street_adddress": "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "lat": "37.42199990", "lng": "-122.08405750", "type": "company", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.05492.pdf"], "doi": []}, {"id": "6f71862aa00d61fc8fd7f205de35ee8af458ec0c", "title": "Semi-supervised Learning of Instance-level Recognition from Video", "addresses": [{"name": "Imperial College London", "source_name": "Imperial College London", "street_adddress": "Imperial College London, Exhibition Road, Brompton, Royal Borough of Kensington and Chelsea, London, Greater London, England, SW7 2AZ, UK", "lat": "51.49887085", "lng": "-0.17560797", "type": "edu", "country": "United Kingdom"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/6f71/862aa00d61fc8fd7f205de35ee8af458ec0c.pdf"], "doi": []}, {"id": "c41e483fee61e5040eeb49859a481352f8e3f8ac", "title": "TOWARDS BETTER UNDERSTANDING OF DEEP LEARNING WITH VISUALIZATION by HAIPENG ZENG", "addresses": [{"name": "Hong Kong University of Science and Technology", "source_name": "Hong Kong University of Science and Technology", "street_adddress": "\u9999\u6e2f\u79d1\u6280\u5927\u5b78 Hong Kong University of Science and Technology, \u5927\u5b78\u9053 University Road, \u5927\u57d4\u4ed4 Tai Po Tsai, \u5927\u57d4\u4ed4\u6751 Tai Po Tsai Village, \u65b0\u754c New Territories, HK, DD253 1209, \u4e2d\u56fd", "lat": "22.33863040", "lng": "114.26203370", "type": "edu", "country": "China"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/c41e/483fee61e5040eeb49859a481352f8e3f8ac.pdf"], "doi": []}, {"id": "101d1cff1aa5590a1f79bc485cbfec094a995f74", "title": "Persuasive Faces: Generating Faces in Advertisements (Supplementary Material)", "addresses": [{"name": "University of Pittsburgh", "source_name": "University of Pittsburgh", "street_adddress": "University of Pittsburgh, Sutherland Drive, West Oakland, PGH, Allegheny County, Pennsylvania, 15240, USA", "lat": "40.44415295", "lng": "-79.96243993", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/101d/1cff1aa5590a1f79bc485cbfec094a995f74.pdf"], "doi": []}, {"id": "9a6268d2bc1221ea154097feadea0c58f234d02f", "title": "Co-Attending Free-Form Regions and Detections With Multi-Modal Multiplicative Feature Embedding for Visual Question Answering", "addresses": [{"name": "Chinese University of Hong Kong", "source_name": "Chinese University of Hong Kong", "street_adddress": "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "lat": "22.41626320", "lng": "114.21093180", "type": "edu", "country": "China"}, {"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}, {"name": "East China Normal University", "source_name": "East China Normal University", "street_adddress": "\u534e\u4e1c\u5e08\u8303\u5927\u5b66, 3663, \u4e2d\u5c71\u5317\u8def, \u66f9\u5bb6\u6e21, \u666e\u9640\u533a, \u666e\u9640\u533a (Putuo), \u4e0a\u6d77\u5e02, 200062, \u4e2d\u56fd", "lat": "31.22849230", "lng": "121.40211389", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.06794.pdf"], "doi": []}, {"id": "44674b020e9ce46b16ffb72952a7cacb40d01657", "title": "Depth-aware neural style transfer", "addresses": [{"name": "Cardiff University", "source_name": "Cardiff University", "street_adddress": "Cardiff University, Park Place, Castle, Cardiff, Wales, CF, UK", "lat": "51.48799610", "lng": "-3.17969747", "type": "edu", "country": "United Kingdom"}, {"name": "NanKai University", "source_name": "College of Information Technical Science, NanKai University, CITS, TianJin, China", "street_adddress": "China, Tianjin, Nankai, Lequn N Rd, \u5357\u5f00\u5927\u5b66\u7efc\u5408\u5b9e\u9a8c\u697cA\u533a604", "lat": "39.10335500", "lng": "117.16492700", "type": "edu", "country": "China"}], "year": "2017", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3092924"]}, {"id": "bce963c494ccce1c66757e69993f578c37564f6d", "title": "Can Adversarial Networks Hallucinate Occluded People With a Plausible Aspect?", "addresses": [{"name": "University of Modena and Reggio Emilia", "source_name": "University of Modena and Reggio Emilia 41125, Modena, Italy", "street_adddress": "Via Universit\u00e0, 4, 41121 Modena MO, Italy", "lat": "44.64510460", "lng": "10.92792680", "type": "edu", "country": "Italy"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.08097.pdf"], "doi": []}, {"id": "8dcc95debd07ebab1721c53fa50d846fef265022", "title": "MicroExpNet: An Extremely Small and Fast Model For Expression Recognition From Frontal Face Images", "addresses": [{"name": "Middle East Technical University", "source_name": "Middle East Technical University", "street_adddress": "ODT\u00dc, 1, 1591.sk(315.sk), \u00c7i\u011fdem Mahallesi, Ankara, \u00c7ankaya, Ankara, \u0130\u00e7 Anadolu B\u00f6lgesi, 06800, T\u00fcrkiye", "lat": "39.87549675", "lng": "32.78553506", "type": "edu", "country": "Turkey"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1711.07011.pdf"], "doi": []}, {"id": "3ff40f0760bd8d3c46d72147b0f5b0d4aee2a24f", "title": "AI Challenger : A Large-scale Dataset for Going Deeper in Image Understanding", "addresses": [{"name": "Peking University", "source_name": "Peking University", "street_adddress": "\u5317\u4eac\u5927\u5b66, 5\u53f7, \u9890\u548c\u56ed\u8def, \u7a3b\u9999\u56ed\u5357\u793e\u533a, \u6d77\u6dc0\u533a, \u5317\u4eac\u5e02, 100871, \u4e2d\u56fd", "lat": "39.99223790", "lng": "116.30393816", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1711.06475.pdf"], "doi": []}, {"id": "e7d6fc6daf70a30993b57efff9a259bd418c5c91", "title": "Infrared and Visible Image Fusion with ResNet and zero-phase component analysis", "addresses": [{"name": "University of Strathclyde", "source_name": "Centre for excellence in Signal and Image Processing, University of Strathclyde, Glasgow, UK", "street_adddress": "16 Richmond St, Glasgow G1 1XQ, UK", "lat": "55.86212200", "lng": "-4.24228510", "type": "edu", "country": "United Kingdom"}, {"name": "Jiangnan University", "source_name": "Jiangnan University", "street_adddress": "\u6c5f\u5357\u5927\u5b66\u7ad9, \u8821\u6e56\u5927\u9053, \u6ee8\u6e56\u533a, \u5357\u573a\u6751, \u6ee8\u6e56\u533a (Binhu), \u65e0\u9521\u5e02 / Wuxi, \u6c5f\u82cf\u7701, 214121, \u4e2d\u56fd", "lat": "31.48542550", "lng": "120.27395810", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.07119.pdf"], "doi": []}, {"id": "74875368649f52f74bfc4355689b85a724c3db47", "title": "Object detection by labeling superpixels", "addresses": [{"name": "National Laboratory of Pattern Recognition, Chinese Academy of Sciences", "source_name": "National Laboratory of Pattern Recognition, Institute of Automation of Chinese, Academy of Sciences, Beijing, China", "street_adddress": "China, Beijing, Haidian, \u4e2d\u5173\u6751\u4e1c\u8def95\u53f7", "lat": "39.97920300", "lng": "116.33287000", "type": "edu", "country": "China"}], "year": "2015", "pdf": ["http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/3B_072.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/3B_072_ext.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7299146", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2015.7299146", "http://doi.org/10.1109/CVPR.2015.7299146"]}, {"id": "01cb4071a0a43aeef63e5d568ad5afe1fb8b2411", "title": "Domain Separation Networks", "addresses": [{"name": "Imperial College London", "source_name": "Imperial College London", "street_adddress": "Imperial College London, Exhibition Road, Brompton, Royal Borough of Kensington and Chelsea, London, Greater London, England, SW7 2AZ, UK", "lat": "51.49887085", "lng": "-0.17560797", "type": "edu", "country": "United Kingdom"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/01cb/4071a0a43aeef63e5d568ad5afe1fb8b2411.pdf"], "doi": []}, {"id": "54b5aab87dbe38803935789c4d730bd203d198a1", "title": "3D Human Pose Estimation in RGBD Images for Robotic Task Learning", "addresses": [{"name": "University of Freiburg", "source_name": "Social Robotics Lab, University of Freiburg, Germany", "street_adddress": "Fahnenbergplatz, 79085 Freiburg im Breisgau, Germany", "lat": "47.99354410", "lng": "7.84594960", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8462833"]}, {"id": "09a4f1b7afd8d5f6854b23f0aa9e80b9a0fa6d20", "title": "Seeing Beyond Appearance - Mapping Real Images into Geometrical Domains for Unsupervised CAD-based Recognition", "addresses": [{"name": "University of Passau", "source_name": "Chair of Complex & Intelligent Systems, University of Passau, Passau, Germany", "street_adddress": "Innstra\u00dfe 41, 94032 Passau, Germany", "lat": "48.56704660", "lng": "13.45178350", "type": "edu", "country": "Germany"}, {"name": "Technical University of Munich", "source_name": "Computer Aided Medical Procedures, Technical University of Munich, Garching, Germany", "street_adddress": "Boltzmannstra\u00dfe 3, 85748 Garching bei M\u00fcnchen, Germany", "lat": "48.26301100", "lng": "11.66685700", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.04158.pdf"], "doi": []}, {"id": "f9a14264ca328cfbd817c7458eee5b18592e5d54", "title": "Feature Fusion for Weakly Supervised Object Localization", "addresses": [{"name": "Xi'an Jiaotong University", "source_name": "Xi'an Jiaotong University", "street_adddress": "\u897f\u5b89\u4ea4\u901a\u5927\u5b66\u5174\u5e86\u6821\u533a, \u6587\u6cbb\u8def, \u4e50\u5c45\u573a, \u7891\u6797\u533a (Beilin), \u897f\u5b89\u5e02, \u9655\u897f\u7701, 710048, \u4e2d\u56fd", "lat": "34.24749490", "lng": "108.97898751", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8623227"]}, {"id": "ab0715642330502d5efca948e4753651cb004d84", "title": "Soft-NMS \u2014 Improving Object Detection with One Line of Code", "addresses": [{"name": "University of Maryland", "source_name": "University of Maryland", "street_adddress": "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.04503.pdf"], "doi": []}, {"id": "86c158ef6caaf247d5d14e07c5edded0147df8b7", "title": "Spatial Memory for Context Reasoning in Object Detection", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.04224.pdf"], "doi": []}, {"id": "adc55a30b17060d68b5092dfaba52243e39c68f5", "title": "Meaningful maps with object-oriented semantic mapping", "addresses": [{"name": "Queensland University of Technology (QUT)", "source_name": "Queensland University of Technology (QUT)", "street_adddress": "2 George St, Brisbane City QLD 4000, Australia", "lat": "-27.47735700", "lng": "153.02841500", "type": "edu", "country": "Australia"}, {"name": "University of Adelaide", "source_name": "University of Adelaide", "street_adddress": "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu", "country": "Australia"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8206392"]}, {"id": "3d5575e9ba02128d94c20330f4525fc816411ec2", "title": "Learning Video Object Segmentation from Static Images", "addresses": [{"name": "Disney Research", "source_name": "Disney Research", "street_adddress": "521 Circle 7 Dr, Glendale, CA 91201, USA", "lat": "34.15797420", "lng": "-118.28947290", "type": "company", "country": "United States"}, {"name": "ETH Zurich", "source_name": "ETH Zurich", "street_adddress": "R\u00e4mistrasse 101, 8092 Z\u00fcrich, Switzerland", "lat": "47.37631300", "lng": "8.54766990", "type": "edu", "country": "Switzerland"}, {"name": "Max Planck Institute for Informatics", "source_name": "Max Planck Institute for Informatics", "street_adddress": "MPII, E1 4, Campus, Universit\u00e4t, Sankt Johann, Bezirk Mitte, Saarbr\u00fccken, Regionalverband Saarbr\u00fccken, Saarland, 66123, Deutschland", "lat": "49.25795660", "lng": "7.04577417", "type": "edu", "country": "Germany"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1612.02646.pdf"], "doi": []}, {"id": "089513ca240c6d672c79a46fa94a92cde28bd567", "title": "RNN Fisher Vectors for Action Recognition and Image Annotation", "addresses": [{"name": "Tel Aviv University", "source_name": "Tel Aviv University", "street_adddress": "\u05d0\u05d5\u05e0\u05d9\u05d1\u05e8\u05e1\u05d9\u05d8\u05ea \u05ea\u05dc \u05d0\u05d1\u05d9\u05d1, \u05db\u05d9\u05db\u05e8 \u05de\u05e0\u05d3\u05dc, \u05ea\u05dc \u05d0\u05d1\u05d9\u05d1 - \u05d9\u05e4\u05d5, \u05d0\u05e4\u05e7\u05d4, \u05ea\u05dc \u05d0\u05d1\u05d9\u05d1-\u05d9\u05e4\u05d5, \u05de\u05d7\u05d5\u05d6 \u05ea\u05dc \u05d0\u05d1\u05d9\u05d1, NO, \u05d9\u05e9\u05e8\u05d0\u05dc", "lat": "32.11198890", "lng": "34.80459702", "type": "edu", "country": "Israel"}, {"name": "IBM Research, Haifa, Israel", "source_name": "IBM Research - Haifa, Israel", "street_adddress": "\u05e7\u05de\u05e4\u05d5\u05e1 \u05d0\u05d5\u05e0\u05d9\u05d1\u05e8\u05e1\u05d9\u05d8\u05d4 \u05d7\u05d9\u05e4\u05d4, \u05d7\u05d9\u05e4\u05d4, Israel", "lat": "32.76526220", "lng": "35.01576130", "type": "company", "country": "Israel"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1512.03958.pdf"], "doi": []}, {"id": "8f1fcd6c3007f48eafeddf5f517c1197b2aab9cc", "title": "DPRed: Making Typical Activation and Weight Values Matter In Deep Learning Computing.", "addresses": [{"name": "University of Toronto", "source_name": "University of Toronto", "street_adddress": "University of Toronto, St. George Street, Bloor Street Culture Corridor, Old Toronto, Toronto, Ontario, M5S 1A5, Canada", "lat": "43.66333345", "lng": "-79.39769975", "type": "edu", "country": "Canada"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.06732.pdf"], "doi": []}, {"id": "c0d5fa2e57646f2cc7dbb9633261af7d20f8a51e", "title": "Joint Global and Co-Attentive Representation Learning for Image-Sentence Retrieval", "addresses": [{"name": "Chinese Academy of Sciences & University of Chinese Academy of Sciences", "source_name": "Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China", "street_adddress": "China, Beijing, Haidian, Zhongguancun South 1st Alley, \u4e2d\u5173\u6751\u5357\u4e00\u6761", "lat": "39.98177000", "lng": "116.33008600", "type": "edu", "country": "China"}, {"name": "Chinese Academy of Sciences", "source_name": "Chinese Academy of Sciences", "street_adddress": "\u4e2d\u56fd\u79d1\u5b66\u9662\u5fc3\u7406\u7814\u7a76\u6240, 16, \u6797\u8403\u8def, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100101, \u4e2d\u56fd", "lat": "40.00447950", "lng": "116.37023800", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3240535"]}, {"id": "7ec16949adf6ea78054f6c6512f332a86960b91f", "title": "Computer Vision \u2013 ECCV 2016", "addresses": [{"name": "Czech Technical University", "source_name": "Czech Technical University", "street_adddress": "\u010cesk\u00e9 vysok\u00e9 u\u010den\u00ed technick\u00e9 v Praze, Resslova, Nov\u00e9 M\u011bsto, Praha, okres Hlavn\u00ed m\u011bsto Praha, Hlavn\u00ed m\u011bsto Praha, Praha, 11121, \u010cesko", "lat": "50.07642960", "lng": "14.41802312", "type": "edu", "country": "Czech Republic"}, {"name": "RWTH Aachen, Aachen, Germany", "source_name": "RWTH Aachen, Aachen, Germany", "street_adddress": "Templergraben 55, 52062 Aachen, Germany", "lat": "50.78007780", "lng": "6.06568690", "type": "edu", "country": "Germany"}, {"name": "University of Amsterdam", "source_name": "University of Amsterdam", "street_adddress": "Institute for Logic, Language and Computation (ILLC), 107, Science Park, Oost-Watergraafsmeer, Amsterdam, Oost, Amsterdam, Noord-Holland, Nederland, 1098XG, Nederland", "lat": "52.35536550", "lng": "4.95016440", "type": "edu", "country": "Netherlands"}, {"name": "University of Trento", "source_name": "University of Trento", "street_adddress": "University of Trento, Via Giuseppe Verdi, Piedicastello, Trento, Territorio Val d'Adige, TN, TAA, 38122, Italia", "lat": "46.06588360", "lng": "11.11598940", "type": "edu", "country": "Italy"}], "year": "2016", "pdf": [], "doi": ["http://doi.org/10.1007/978-3-319-46475-6"]}, {"id": "277bfd1bc89044b4a523ef23f48bd053d5560657", "title": "Large-Scale Object Discovery and Detector Adaptation from Unlabeled Video", "addresses": [{"name": "RWTH Aachen University", "source_name": "RWTH Aachen University", "street_adddress": "RWTH Aachen, Mies-van-der-Rohe-Stra\u00dfe, K\u00f6nigsh\u00fcgel, Aachen-Mitte, Aachen, St\u00e4dteregion Aachen, Regierungsbezirk K\u00f6ln, Nordrhein-Westfalen, 52074, Deutschland", "lat": "50.77917030", "lng": "6.06728733", "type": "edu", "country": "Germany"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1712.08832.pdf"], "doi": []}, {"id": "3e6d2e963f9a1b417871327f648d16f2c66a4068", "title": "Fully Convolutional Neural Networks with Full-Scale-Features for Semantic Segmentation", "addresses": [{"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/3e6d/2e963f9a1b417871327f648d16f2c66a4068.pdf"], "doi": []}, {"id": "cda6d9b0cc1509ec61a43e24e9b7a14b18642aca", "title": "Convolutional Neural Networks combined with Runge-Kutta Methods", "addresses": [{"name": "Northeastern University", "source_name": "Northeastern University", "street_adddress": "Snell Library, 360, Huntington Avenue, Roxbury Crossing, Fenway, Boston, Suffolk County, Massachusetts, 02115, USA", "lat": "42.33836680", "lng": "-71.08793524", "type": "edu", "country": "United States"}, {"name": "University of British Columbia", "source_name": "University of British Columbia", "street_adddress": "University of British Columbia, Eagles Drive, Hawthorn Place, University Endowment Lands, Metro Vancouver, British Columbia, V6T, Canada", "lat": "49.25839375", "lng": "-123.24658161", "type": "edu", "country": "Canada"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.08831.pdf"], "doi": []}, {"id": "9a8662189388dd84ce1ec6e90d103959a4132a95", "title": "Analysis and Optimization of Loss Functions for Multiclass, Top-k, and Multilabel Classification", "addresses": [{"name": "Saarbr\u00fccken, Saarland, Germany", "source_name": "Saarbr\u00fccken, Saarland, Germany", "street_adddress": "Saarbr\u00fccken, Germany", "lat": "49.24015720", "lng": "6.99693270", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8036272"]}, {"id": "33bcc97b605f00145098d095be2841a1fa6b9a95", "title": "Order-Embeddings of Images and Language", "addresses": [{"name": "University of Toronto", "source_name": "University of Toronto", "street_adddress": "University of Toronto, St. George Street, Bloor Street Culture Corridor, Old Toronto, Toronto, Ontario, M5S 1A5, Canada", "lat": "43.66333345", "lng": "-79.39769975", "type": "edu", "country": "Canada"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1511.06361.pdf"], "doi": []}, {"id": "126e5a90e12aee34d33e6d301ab9533acf03c199", "title": "Multi-style Generative Network for Real-Time Transfer", "addresses": [{"name": "Rutgers University", "source_name": "Rutgers University", "street_adddress": "Rutgers Cook Campus - North, Biel Road, New Brunswick, Middlesex County, New Jersey, 08901, USA", "lat": "40.47913175", "lng": "-74.43168868", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.06953.pdf"], "doi": []}, {"id": "9c1f5547d98f5390e2389ce40668da83a9830487", "title": "Non-parametric Structured Output Networks", "addresses": [{"name": "Disney Research", "source_name": "Disney Research", "street_adddress": "521 Circle 7 Dr, Glendale, CA 91201, USA", "lat": "34.15797420", "lng": "-118.28947290", "type": "company", "country": "United States"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/9c1f/5547d98f5390e2389ce40668da83a9830487.pdf"], "doi": []}, {"id": "032bde9da87439c781a6c81ba7933985ed95d88e", "title": "What's the point: Semantic segmentation with point supervision", "addresses": [{"name": "Stanford University", "source_name": "Stanford University", "street_adddress": "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu", "country": "United States"}, {"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}, {"name": "University of Edinburgh", "source_name": "University of Edinburgh", "street_adddress": "New College, New College Courtyard, The Mound, Old Town, Edinburgh, City of Edinburgh, Scotland, EH1 2LX, UK", "lat": "55.94951105", "lng": "-3.19534913", "type": "edu", "country": "United Kingdom"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1506.02106.pdf"], "doi": []}, {"id": "414315d44a489d09c6e1933033ffba6396974ee1", "title": "Video Visual Relation Detection", "addresses": [{"name": "Columbia University", "source_name": "Columbia University", "street_adddress": "Columbia University Medical Center, 630, West 168th Street, Washington Heights, Manhattan, Manhattan Community Board 12, New York County, NYC, New York, 10031, USA", "lat": "40.84198360", "lng": "-73.94368971", "type": "edu", "country": "United States"}], "year": "2017", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3123380"]}, {"id": "d182c6d9ac4777b5ad73afdd64b7b68d76037212", "title": "Aligned Image-Word Representations Improve Inductive Transfer Across Vision-Language Tasks", "addresses": [{"name": "University of Illinois, Urbana-Champaign", "source_name": "University of Illinois, Urbana-Champaign", "street_adddress": "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu", "country": "United States"}, {"name": "Google", "source_name": "Google, Inc.", "street_adddress": "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "lat": "37.42199990", "lng": "-122.08405750", "type": "company", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.00260.pdf"], "doi": []}, {"id": "7f33a5fcc5db4625c66972f0e6f06540b64d4f1e", "title": "Image Surveillance Assistant Architecture : Status and Planned Extensions", "addresses": [{"name": "University of Maryland", "source_name": "University of Maryland", "street_adddress": "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu", "country": "United States"}, {"name": "Naval Research Laboratory", "source_name": "Naval Research Laboratory", "street_adddress": "Naval Research Laboratory Post Office, 4555, Overlook Avenue Southwest, Washington, D.C., 20375, USA", "lat": "38.82313810", "lng": "-77.01789020", "type": "mil", "country": "United States"}, {"name": "Fayetteville State University", "source_name": "Fayetteville State University", "street_adddress": "1200 Murchison Rd, Fayetteville, NC 28301, USA", "lat": "35.07422060", "lng": "-78.89248960", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/7f33/a5fcc5db4625c66972f0e6f06540b64d4f1e.pdf"], "doi": []}, {"id": "c0e4b6a993a35ded0d17a5e751bd135b795244ae", "title": "Large-Scale Training of Shadow Detectors with Noisily-Annotated Shadow Examples", "addresses": [{"name": "Stony Brook University", "source_name": "Stony Brook University", "street_adddress": "Stony Brook University, 100, Nicolls Road, Stony Brook, Suffolk County, New York, 11794, USA", "lat": "40.91531960", "lng": "-73.12706260", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["http://www3.cs.stonybrook.edu/~cvl/content/papers/2016/LSS_ECCV16.pdf", "http://www3.cs.stonybrook.edu/~minhhoai/papers/LSS_ECCV16.pdf"], "doi": ["https://doi.org/10.1007/978-3-319-46466-4_49"]}, {"id": "237c0c0749aaab0f73ec0641bef2453714da3099", "title": "An Efficient Hierarchical Convolutional Neural Network for Traffic Object Detection", "addresses": [{"name": "Shanghai Jiao Tong University", "source_name": "Shanghai Jiao Tong University", "street_adddress": "\u4e0a\u6d77\u4ea4\u901a\u5927\u5b66\uff08\u5f90\u6c47\u6821\u533a\uff09, \u6dee\u6d77\u897f\u8def, \u756a\u79ba\u5c0f\u533a, \u5e73\u9634\u6865, \u5f90\u6c47\u533a, \u4e0a\u6d77\u5e02, 200052, \u4e2d\u56fd", "lat": "31.20081505", "lng": "121.42840681", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8500640"]}, {"id": "87697847062e7eefec99a8c3aec888e3eef5e5b9", "title": "Unsupervised Learning of Spoken Language with Visual Context", "addresses": [{"name": "MIT", "source_name": "Massachusetts Institute", "street_adddress": "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/8769/7847062e7eefec99a8c3aec888e3eef5e5b9.pdf"], "doi": []}, {"id": "15908912ce3943fc5ec281c1cbf062722cb114d7", "title": "Dynamic Graph Modules for Modeling Higher-Order Interactions in Activity Recognition", "addresses": [{"name": "University of Rochester", "source_name": "University of Rochester", "street_adddress": "Memorial Art Gallery, 500, University Avenue, East End, Rochester, Monroe County, New York, 14607, USA", "lat": "43.15769690", "lng": "-77.58829158", "type": "edu", "country": "United States"}, {"name": "University of Michigan", "source_name": "University of Michigan", "street_adddress": "University of Michigan, 500, Hayward Street, Ann Arbor, Washtenaw County, Michigan, 48109, USA", "lat": "42.29421420", "lng": "-83.71003894", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.05637.pdf"], "doi": []}, {"id": "60542b1a857024c79db8b5b03db6e79f74ec8f9f", "title": "Learning to Detect Human-Object Interactions", "addresses": [{"name": "University of Michigan", "source_name": "University of Michigan", "street_adddress": "University of Michigan, 500, Hayward Street, Ann Arbor, Washtenaw County, Michigan, 48109, USA", "lat": "42.29421420", "lng": "-83.71003894", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1702.05448.pdf"], "doi": []}, {"id": "41d9719922c81d14f2a39392285c5789f5ea4282", "title": "Head and Body Orientation Estimation Using Convolutional Random Projection Forests", "addresses": [{"name": "Seoul National University", "source_name": "Seoul National University", "street_adddress": "\uc11c\uc6b8\ub300\ud559\uad50, \uc11c\ud638\ub3d9\ub85c, \uc11c\ub454\ub3d9, \uad8c\uc120\uad6c, \uc218\uc6d0\uc2dc, \uacbd\uae30, 16614, \ub300\ud55c\ubbfc\uad6d", "lat": "37.26728000", "lng": "126.98411510", "type": "edu", "country": "South Korea"}], "year": "2019", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8219761"]}, {"id": "6459cf454b87fded65a223a30341e5304519a6aa", "title": "Integrated Object Detection and Tracking with Tracklet-Conditioned Detection", "addresses": [{"name": "Microsoft Research Asia", "source_name": "Microsoft Research Asia", "street_adddress": "1 Memorial Dr, Cambridge, MA 02142, USA", "lat": "42.36142560", "lng": "-71.08120920", "type": "company", "country": "United States"}, {"name": "Beijing Institute of Technology", "source_name": "Beijing Institute of Technology University", "street_adddress": "\u5317\u4eac\u7406\u5de5\u5927\u5b66, 5, \u4e2d\u5173\u6751\u5357\u5927\u8857, \u4e2d\u5173\u6751, \u7a3b\u9999\u56ed\u5357\u793e\u533a, \u6d77\u6dc0\u533a, \u5317\u4eac\u5e02, 100872, \u4e2d\u56fd", "lat": "39.95866520", "lng": "116.30971281", "type": "edu", "country": "China"}, {"name": "University of Science and Technology of China", "source_name": "University of Science and Technology of China", "street_adddress": "\u4e2d\u56fd\u79d1\u5b66\u6280\u672f\u5927\u5b66 \u4e1c\u6821\u533a, 96\u53f7, \u91d1\u5be8\u8def, \u6c5f\u6dee\u5316\u80a5\u5382\u5c0f\u533a, \u829c\u6e56\u8def\u8857\u9053, \u5408\u80a5\u5e02\u533a, \u5408\u80a5\u5e02, \u5b89\u5fbd\u7701, 230026, \u4e2d\u56fd", "lat": "31.83907195", "lng": "117.26420748", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.11167.pdf"], "doi": []}, {"id": "7f836c047bc86d52e3a28098b53311cb2186acaa", "title": "Deep Compositional Question Answering with Neural Module Networks", "addresses": [{"name": "University of California, Berkeley", "source_name": "University of California, Berkeley", "street_adddress": "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "lat": "37.86871260", "lng": "-122.25586815", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/7f83/6c047bc86d52e3a28098b53311cb2186acaa.pdf"], "doi": []}, {"id": "5f5068645a5cebf923093542302c1fa21e387cee", "title": "ChipGAN: A Generative Adversarial Network for Chinese Ink Wash Painting Style Transfer", "addresses": [{"name": "Peking University", "source_name": "Peking University", "street_adddress": "\u5317\u4eac\u5927\u5b66, 5\u53f7, \u9890\u548c\u56ed\u8def, \u7a3b\u9999\u56ed\u5357\u793e\u533a, \u6d77\u6dc0\u533a, \u5317\u4eac\u5e02, 100871, \u4e2d\u56fd", "lat": "39.99223790", "lng": "116.30393816", "type": "edu", "country": "China"}, {"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3240655"]}, {"id": "84ed65bda3de8a17526a0ad06ae3777fbbbeef20", "title": "Adapting Object Detectors from Images to Weakly Labeled Videos", "addresses": [{"name": "University of Manitoba", "source_name": "University of Manitoba", "street_adddress": "University of Manitoba, Gillson Street, Normand Park, Saint Vital, Winnipeg, Manitoba, R3T 2N2, Canada", "lat": "49.80915360", "lng": "-97.13304179", "type": "edu", "country": "Canada"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/84ed/65bda3de8a17526a0ad06ae3777fbbbeef20.pdf"], "doi": []}, {"id": "f85be6a31b74d6da6f490635d314306d77d0b6c7", "title": "Answerer in Questioner's Mind: Information Theoretic Approach to Goal-Oriented Visual Dialog", "addresses": [{"name": "Seoul National University", "source_name": "Seoul National University", "street_adddress": "\uc11c\uc6b8\ub300\ud559\uad50, \uc11c\ud638\ub3d9\ub85c, \uc11c\ub454\ub3d9, \uad8c\uc120\uad6c, \uc218\uc6d0\uc2dc, \uacbd\uae30, 16614, \ub300\ud55c\ubbfc\uad6d", "lat": "37.26728000", "lng": "126.98411510", "type": "edu", "country": "South Korea"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.03881.pdf"], "doi": []}, {"id": "bf8e413869e96afa15ef3ff884cc7739eafa8308", "title": "Deep conditional neural network for image segmentation", "addresses": [{"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}, {"name": "Hong Kong Polytechnic University", "source_name": "Hong Kong Polytechnic University", "street_adddress": "hong kong, 11, \u80b2\u624d\u9053 Yuk Choi Road, \u5c16\u6c99\u5480 Tsim Sha Tsui, \u6cb9\u5c16\u65fa\u5340 Yau Tsim Mong District, \u4e5d\u9f8d Kowloon, HK, 00000, \u4e2d\u56fd", "lat": "22.30457200", "lng": "114.17976285", "type": "edu", "country": "China"}], "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7552924", "http://doi.ieeecomputersociety.org/10.1109/ICME.2016.7552924", "http://doi.org/10.1109/ICME.2016.7552924"]}, {"id": "7dcaf1ef07a593a987f3b529c2ad1e977c0c7196", "title": "Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input", "addresses": [{"name": "MIT", "source_name": "Massachusetts Institute", "street_adddress": "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.01452.pdf"], "doi": []}, {"id": "1bfc74bad04b407d1792a70d73a3f5dc0be0506d", "title": "Cross-Dataset Adaptation for Visual Question Answering", "addresses": [{"name": "U. of Southern California", "source_name": "U. of Southern California", "street_adddress": "Los Angeles, CA 90007, USA", "lat": "34.02235190", "lng": "-118.28511700", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.03726.pdf"], "doi": []}, {"id": "516d57bbd02a6938a99b45691a3d7864c2fdc70a", "title": "DART: Domain-Adversarial Residual-Transfer Networks for Unsupervised Cross-Domain Image Classification", "addresses": [{"name": "Chinese University of Hong Kong", "source_name": "Chinese University of Hong Kong", "street_adddress": "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "lat": "22.41626320", "lng": "114.21093180", "type": "edu", "country": "China"}, {"name": "University of Electronic Science and Technology of China", "source_name": "University of Electronic Science and Technology of China", "street_adddress": "2 Jianshe North Rd 2nd Section, Jianshe Road, Chenghua Qu, Chengdu Shi, Sichuan Sheng, China, 610054", "lat": "30.67272100", "lng": "104.09880600", "type": "edu", "country": "China"}, {"name": "Google", "source_name": "Google, Inc.", "street_adddress": "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "lat": "37.42199990", "lng": "-122.08405750", "type": "company", "country": "United States"}, {"name": "Singapore Management University", "source_name": "Singapore Management University", "street_adddress": "Singapore Management University, Fort Canning Tunnel, Clarke Quay, City Hall, Singapore, Central, 178895, Singapore", "lat": "1.29500195", "lng": "103.84909214", "type": "edu", "country": "Singapore"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.11478.pdf"], "doi": []}, {"id": "d0a934ef5b4edf7ebdc2276048534e4c9acf5a76", "title": "Person Retrieval in Surveillance Video using Height, Color and Gender", "addresses": [{"name": "L. D. College of Engineering, India", "source_name": "L. D. College of Engineering, India", "street_adddress": "120, Circular Road, University Area, Ahmedabad, Gujarat 380015, India", "lat": "23.03380000", "lng": "72.54658400", "type": "edu", "country": "India"}, {"name": "Ahmedabad University", "source_name": "Ahmedabad University", "street_adddress": "School of Science and Technology, University Road, Gurukul, Gulbai tekra, Ahmedabad, Ahmedabad District, Gujarat, 380001, India", "lat": "23.03787430", "lng": "72.55180046", "type": "edu", "country": "India"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8639145"]}, {"id": "ce9287a47f00d06ef75fe3ace9adbd7691b6e844", "title": "Large-Scale Visual Relationship Understanding", "addresses": [{"name": "Rutgers University", "source_name": "Rutgers University", "street_adddress": "Rutgers Cook Campus - North, Biel Road, New Brunswick, Middlesex County, New Jersey, 08901, USA", "lat": "40.47913175", "lng": "-74.43168868", "type": "edu", "country": "United States"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1804.10660.pdf"], "doi": []}, {"id": "c7132da9421bfa06fbc859d6c3d6e621bd7bf472", "title": "Multimodal Deep Embedding via Hierarchical Grounded Compositional Semantics", "addresses": [{"name": "Zhejiang University", "source_name": "Zhejiang University", "street_adddress": "\u6d59\u6c5f\u5927\u5b66\u4e4b\u6c5f\u6821\u533a, \u4e4b\u6c5f\u8def, \u8f6c\u5858\u8857\u9053, \u897f\u6e56\u533a (Xihu), \u676d\u5dde\u5e02 Hangzhou, \u6d59\u6c5f\u7701, 310008, \u4e2d\u56fd", "lat": "30.19331415", "lng": "120.11930822", "type": "edu", "country": "China"}, {"name": "Binghamton University", "source_name": "Binghamton University", "street_adddress": "Binghamton University Downtown Center, Washington Street, Downtown, Binghamton, Broome County, New York, 13901, USA", "lat": "42.09580770", "lng": "-75.91455689", "type": "edu", "country": "United States"}, {"name": "Microsoft Research Asia", "source_name": "Microsoft Research Asia", "street_adddress": "1 Memorial Dr, Cambridge, MA 02142, USA", "lat": "42.36142560", "lng": "-71.08120920", "type": "company", "country": "United States"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7562283"]}, {"id": "c8b592fcf2ed2f75799b94c428d2ccdf1e82c5f7", "title": "RUC-Tencent at ImageCLEF 2015: Concept Detection, Localization and Sentence Generation", "addresses": [{"name": "Renmin University of China", "source_name": "Beijing Key Laboratory of Big Data Management and Analysis Methods, Renmin University of China, Beijing, 100872, China", "street_adddress": "59 Zhongguancun St, Haidian Qu, China, 100872", "lat": "39.96960620", "lng": "116.31881450", "type": "edu", "country": "China"}, {"name": "Tencent", "source_name": "Tencent", "street_adddress": "Ke Ji Zhong Yi Lu, Nanshan Qu, Shenzhen Shi, Guangdong Sheng, China, 518057", "lat": "22.54471540", "lng": "113.93571640", "type": "company", "country": "United States"}], "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/c8b5/92fcf2ed2f75799b94c428d2ccdf1e82c5f7.pdf"], "doi": []}, {"id": "ea8c1ac5a1594d6441d10914e0ccc4bd3e9eadfa", "title": "Anchor Box Optimization for Object Detection", "addresses": [{"name": "University of Illinois, Urbana-Champaign", "source_name": "University of Illinois, Urbana-Champaign", "street_adddress": "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu", "country": "United States"}, {"name": "Microsoft", "source_name": "Microsoft Corporation, Redmond, WA, USA", "street_adddress": "One Microsoft Way, Redmond, WA 98052, USA", "lat": "47.64233180", "lng": "-122.13693020", "type": "company", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.00469.pdf"], "doi": []}, {"id": "d4a7259340ece685b9dacb390eea10c6684a05b3", "title": "Object Detection based on Region Decomposition and Assembly", "addresses": [{"name": "Incheon National University", "source_name": "Incheon National University, Incheon, South Korea", "street_adddress": "119 Academy-ro, Songdo 1(il)-dong, Yeonsu-gu, Incheon, South Korea", "lat": "37.37505480", "lng": "126.63289980", "type": "edu", "country": "South Korea"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.08225.pdf"], "doi": []}, {"id": "c733e4a14b51623120da9b4571b4409bc99ab0cd", "title": "Mainstream: Dynamic Stem-Sharing for Multi-Tenant Video Processing", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/2d64/9992d78efd47b22c9a4dcb52386a951b54ea.pdf"], "doi": []}, {"id": "4328ec9d98eff5d7eb70997f76d81b27849f3220", "title": "Scalable, High-Quality Object Detection", "addresses": [{"name": "Google", "source_name": "Google, Inc.", "street_adddress": "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "lat": "37.42199990", "lng": "-122.08405750", "type": "company", "country": "United States"}, {"name": "University of Michigan", "source_name": "University of Michigan", "street_adddress": "University of Michigan, 500, Hayward Street, Ann Arbor, Washtenaw County, Michigan, 48109, USA", "lat": "42.29421420", "lng": "-83.71003894", "type": "edu", "country": "United States"}], "year": "2014", "pdf": ["https://arxiv.org/pdf/1412.1441.pdf"], "doi": []}, {"id": "e304e516fd4e1499b616f120795600eb688fa93e", "title": "People and Vehicles in Danger - A Fire and Flood Detection System in Social Media", "addresses": [{"name": "CERTH-ITI, Thessaloniki, Greece", "source_name": "CERTH-ITI, Thessaloniki, Greece", "street_adddress": "Thermi 570 01, Greece", "lat": "40.56676110", "lng": "22.99801470", "type": "edu", "country": "Greece"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8448732", "http://doi.org/10.1109/IVMSPW.2018.8448732"]}, {"id": "438d4c181362386590eb703c3b65934a6acbbbdc", "title": "A Multi-Oriented Scene Text Detector with Position-Sensitive Segmentation", "addresses": [{"name": "University of Chinese Academy of Sciences", "source_name": "University of Chinese Academy of Sciences", "street_adddress": "University of Chinese Academy of Sciences, UCAS, Yuquanlu, \u7389\u6cc9\u8def, \u7530\u6751, \u6d77\u6dc0\u533a, 100049, \u4e2d\u56fd", "lat": "39.90828040", "lng": "116.24585270", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3206043"]}, {"id": "29b1a44d1e1ffa05c2bf7f4be931c5045f427718", "title": "ON GENERIC OBJECT RECOGNITION TECHNIQUES : CHALLENGES AND OPPORTUNITIES Prof", "addresses": [{"name": "Nirma University", "source_name": "Student, Computer Engineering, Institute of Technology, Nirma University, Ahmedabad - 382 481, Gujarat, India", "street_adddress": "Sarkhej-Gandhinagar Highway, Gota, Ahmedabad, Gujarat 382481, India", "lat": "23.12838620", "lng": "72.54485080", "type": "edu", "country": "India"}], "year": "", "pdf": ["https://pdfs.semanticscholar.org/29b1/a44d1e1ffa05c2bf7f4be931c5045f427718.pdf"], "doi": []}, {"id": "0005a23c0db792ac9d0f5d408c39240ffe4c1d57", "title": "Understanding Fake Faces", "addresses": [{"name": "Waseda University", "source_name": "Waseda University", "street_adddress": "\u65e9\u7a32\u7530\u5927\u5b66 \u5317\u4e5d\u5dde\u30ad\u30e3\u30f3\u30d1\u30b9, 2-2, \u6709\u6bdb\u5f15\u91ce\u7dda, \u516b\u5e61\u897f\u533a, \u5317\u4e5d\u5dde\u5e02, \u798f\u5ca1\u770c, \u4e5d\u5dde\u5730\u65b9, 808-0135, \u65e5\u672c", "lat": "33.88987280", "lng": "130.70856205", "type": "edu", "country": "Japan"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.08391.pdf"], "doi": []}, {"id": "f660ea723b62f69b9f4c439724a6b73357e1d3c3", "title": "Survey on the attention based RNN model and its applications in computer vision", "addresses": [{"name": "Delft University of Technology", "source_name": "Delft University of Technology", "street_adddress": "TU Delft, Mekelweg, TU-wijk, Delft, Zuid-Holland, Nederland, 2628, Nederland", "lat": "51.99882735", "lng": "4.37396037", "type": "edu", "country": "Netherlands"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1601.06823.pdf"], "doi": []}, {"id": "057d5f66a873ec80f8ae2603f937b671030035e6", "title": "Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images", "addresses": [{"name": "University of Washington", "source_name": "University of Washington", "street_adddress": "University of Washington, Rainier Vista, Montlake, University District, Seattle, King County, Washington, 98195, USA", "lat": "47.65432380", "lng": "-122.30800894", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1511.04048.pdf"], "doi": []}, {"id": "05fa7085663bbbd1057c0d240158091930c59c6a", "title": "MovieQA: Understanding Stories in Movies through Question-Answering", "addresses": [{"name": "Karlsruhe Institute of Technology", "source_name": "Karlsruhe Institute of Technology", "street_adddress": "KIT, Leopoldshafener Allee, Linkenheim, Linkenheim-Hochstetten, Landkreis Karlsruhe, Regierungsbezirk Karlsruhe, Baden-W\u00fcrttemberg, 76351, Deutschland", "lat": "49.10184375", "lng": "8.43312560", "type": "edu", "country": "Germany"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1512.02902.pdf"], "doi": []}, {"id": "2fe87224a5b8db29f72936c1cae17389e1c553ad", "title": "ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation", "addresses": [{"name": "University of Washington", "source_name": "University of Washington", "street_adddress": "University of Washington, Rainier Vista, Montlake, University District, Seattle, King County, Washington, 98195, USA", "lat": "47.65432380", "lng": "-122.30800894", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.06815.pdf"], "doi": []}, {"id": "bb9e418469d018be7f5ac2c4b2435ccac50088a3", "title": "Deep Learning\u2013Based Multimedia Analytics: A Review", "addresses": [{"name": "University of Ottawa", "source_name": "University of Ottawa", "street_adddress": "University of Ottawa, 1, Stewart Street, Byward Market, Lowertown, Rideau-Vanier, Ottawa, Ontario, K1N 6N5, Canada", "lat": "45.42580475", "lng": "-75.68740118", "type": "edu", "country": "Canada"}], "year": "2019", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3279952"]}, {"id": "4634bf44a0c994e2bed89686225f8cef601a0224", "title": "NLM at ImageCLEF 2018 Visual Question Answering in the Medical Domain", "addresses": [{"name": "Lister Hill National Center for Biomedical Communications", "source_name": "Lister Hill National Center for Biomedical Communications, U.S. National Library of Medicine, Bethesda, MD, USA", "street_adddress": "8600 Rockville Pike, Bethesda, MD 20894, USA", "lat": "38.99595080", "lng": "-77.09883230", "type": "gov", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/4634/bf44a0c994e2bed89686225f8cef601a0224.pdf"], "doi": []}, {"id": "59f357015054bab43fb8cbfd3f3dbf17b1d1f881", "title": "Unsupervised Multi-Object Detection for Video Surveillance Using Memory-Based Recurrent Attention Networks", "addresses": [{"name": "National University of Defense Technology, China", "source_name": "National University of Defence Technology, Changsha 410000, China", "street_adddress": "\u56fd\u9632\u79d1\u5b66\u6280\u672f\u5927\u5b66, \u4e09\u4e00\u5927\u9053, \u5f00\u798f\u533a, \u5f00\u798f\u533a (Kaifu), \u957f\u6c99\u5e02 / Changsha, \u6e56\u5357\u7701, 410073, \u4e2d\u56fd", "lat": "28.22902090", "lng": "112.99483204", "type": "mil", "country": "China"}, {"name": "University College London", "source_name": "University College London", "street_adddress": "UCL Institute of Education, 20, Bedford Way, Holborn, Bloomsbury, London Borough of Camden, London, Greater London, England, WC1H 0AL, UK", "lat": "51.52316070", "lng": "-0.12820370", "type": "edu", "country": "United Kingdom"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/59f3/57015054bab43fb8cbfd3f3dbf17b1d1f881.pdf"], "doi": []}, {"id": "1687d0120e937d5efe2022cbeab19b38edba0608", "title": "A 2 A : Attention to Attention Reasoning for Movie Question Answering", "addresses": [{"name": "National Tsing Hua University", "source_name": "National Tsing Hua University", "street_adddress": "\u570b\u7acb\u6e05\u83ef\u5927\u5b78, 101, \u514b\u606d\u6a4b, \u5149\u660e\u91cc, \u8d64\u571f\u5d0e, \u6771\u5340, \u65b0\u7af9\u5e02, 30013, \u81fa\u7063", "lat": "24.79254840", "lng": "120.99511830", "type": "edu", "country": "Taiwan"}, {"name": "Institute of Information Science", "source_name": "Institute of Information Science", "street_adddress": "\u8cc7\u8a0a\u79d1\u5b78\u7814\u7a76\u6240, \u6578\u7406\u5927\u9053, \u4e2d\u7814\u91cc, \u5357\u6e2f\u5b50, \u5357\u6e2f\u5340, \u81fa\u5317\u5e02, 11574, \u81fa\u7063", "lat": "25.04107280", "lng": "121.61475620", "type": "edu", "country": "Taiwan"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/1687/d0120e937d5efe2022cbeab19b38edba0608.pdf"], "doi": []}, {"id": "dbf777403156adda2d551a973379edd3e2bc5aaa", "title": "Interpretable Explanations of Black Boxes by Meaningful Perturbation", "addresses": [{"name": "University of Oxford", "source_name": "University of Oxford", "street_adddress": "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "lat": "51.75345380", "lng": "-1.25400997", "type": "edu", "country": "United Kingdom"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.03296.pdf"], "doi": []}, {"id": "4d925db7c9e3cca2e8fed644f750d218a48cd081", "title": "Automatic Concept Discovery from Parallel Text and Visual Corpora", "addresses": [{"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1509.07225.pdf"], "doi": []}, {"id": "d2b2cb1d5cc1aa30cf5be7bcb0494198934caabb", "title": "A Restricted Visual Turing Test for Deep Scene and Event Understanding", "addresses": [{"name": "UCLA", "source_name": "University of California, Los Angeles", "street_adddress": "Los Angeles, CA 90095, USA", "lat": "34.06892100", "lng": "-118.44518110", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1512.01715.pdf"], "doi": []}, {"id": "07ca470ed3be3a476b6fc1917bbbf4182846d1db", "title": "Transforming sensor data to the image domain for deep learning \u2014 An application to footstep detection", "addresses": [{"name": "University of Fribourg", "source_name": "University of Fribourg", "street_adddress": "Avenue de l'Europe 20, 1700 Fribourg, Switzerland", "lat": "46.80635700", "lng": "7.15200600", "type": "edu", "country": "Switzerland"}, {"name": "TU Kaiserslautern, Germany", "source_name": "TU Kaiserslautern, Germany", "street_adddress": "Erwin-Schr\u00f6dinger-Stra\u00dfe 52, 67663 Kaiserslautern, Germany", "lat": "49.42538910", "lng": "7.75531960", "type": "edu", "country": "Germany"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1701.01077.pdf"], "doi": []}, {"id": "9dde6ed569684356c46217fa53224272b668bae8", "title": "Are You Talking to Me? Reasoned Visual Dialog Generation Through Adversarial Learning", "addresses": [{"name": "University of Adelaide", "source_name": "University of Adelaide", "street_adddress": "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu", "country": "Australia"}, {"name": "Northwestern Polytechnical University", "source_name": "Northwestern Polytechnical University", "street_adddress": "\u897f\u5317\u5de5\u4e1a\u5927\u5b66 \u53cb\u8c0a\u6821\u533a, 127\u53f7, \u53cb\u8c0a\u897f\u8def, \u957f\u5b89\u8def, \u7891\u6797\u533a (Beilin), \u897f\u5b89\u5e02, \u9655\u897f\u7701, 710072, \u4e2d\u56fd", "lat": "34.24691520", "lng": "108.91061982", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.07613.pdf"], "doi": []}, {"id": "eff328e0ecfb9a7a2d6664ee38aa32a61c7b9f42", "title": "Visual Question Reasoning on General Dependency Tree", "addresses": [{"name": "Sun Yat-Sen University", "source_name": "Sun Yat-Sen University", "street_adddress": "\u4e2d\u5927, \u65b0\u6e2f\u897f\u8def, \u9f99\u8239\u6ed8, \u5eb7\u4e50, \u6d77\u73e0\u533a (Haizhu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510105, \u4e2d\u56fd", "lat": "23.09461185", "lng": "113.28788994", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.00105.pdf"], "doi": []}, {"id": "6115445ca062b8f865f0b447c059813088b9dd49", "title": "A Dataset and Exploration of Models for Understanding Video Data through Fill-in-the-Blank Question-Answering", "addresses": [{"name": "Polytechnique Montreal", "source_name": "Polytechnique Montr\u00b4eal", "street_adddress": "2900 Boulevard Edouard-Montpetit, Montr\u00e9al, QC H3T 1J4, Canada", "lat": "45.50438400", "lng": "-73.61288290", "type": "edu", "country": "Canada"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1611.07810.pdf"], "doi": []}, {"id": "c8e1c1a82b76d7bfd69c04ab6ab057bb946e262f", "title": "Towards Deep Cellular Phenotyping in Placental Histology", "addresses": [{"name": "University of Oxford", "source_name": "University of Oxford", "street_adddress": "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "lat": "51.75345380", "lng": "-1.25400997", "type": "edu", "country": "United Kingdom"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.03270.pdf"], "doi": []}, {"id": "1be7ecc7100bb5fdbcff7f5f6191a9b57165fa2c", "title": "Deep Learning for Classification of Colorectal Polyps on Whole-slide Images", "addresses": [{"name": "Dartmouth College", "source_name": "Dartmouth College", "street_adddress": "Dartmouth College, Tuck Mall, Hanover, Grafton County, New Hampshire, 03755, USA", "lat": "43.70479270", "lng": "-72.29259090", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.01550.pdf"], "doi": []}, {"id": "290941887c37547462285152ff82796ad71dd757", "title": "Snuba: Automating Weak Supervision to Label Training Data", "addresses": [{"name": "Stanford University", "source_name": "Stanford University", "street_adddress": "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/df8d/c49f33ac02e2f87aac8343869b2affaf4808.pdf"], "doi": []}, {"id": "71de9b3b8f482863d544da0f26ac2876b4fc210a", "title": "Who Are Raising Their Hands ? Hand-Raiser Seeking Based on Object Detection and Pose Estimation", "addresses": [{"name": "Shanghai Jiao Tong University", "source_name": "Shanghai Jiao Tong University", "street_adddress": "\u4e0a\u6d77\u4ea4\u901a\u5927\u5b66\uff08\u5f90\u6c47\u6821\u533a\uff09, \u6dee\u6d77\u897f\u8def, \u756a\u79ba\u5c0f\u533a, \u5e73\u9634\u6865, \u5f90\u6c47\u533a, \u4e0a\u6d77\u5e02, 200052, \u4e2d\u56fd", "lat": "31.20081505", "lng": "121.42840681", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/71de/9b3b8f482863d544da0f26ac2876b4fc210a.pdf"], "doi": []}, {"id": "cb3e91a4c800c60c3f734dd77a64ced7d81e570e", "title": "Grounded Objects and Interactions for Video Captioning", "addresses": [{"name": "Georgia Institute of Technology", "source_name": "Georgia Institute of Technology", "street_adddress": "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1711.06354.pdf"], "doi": []}, {"id": "4e83df2bf849eb6af24bf919ddc7bb25c7249c39", "title": "Fusion that matters: convolutional fusion networks for visual recognition", "addresses": [{"name": "Leiden University", "source_name": "Leiden University, Leiden, The Netherlands", "street_adddress": "Rapenburg 70, 2311 EZ Leiden, Netherlands", "lat": "52.15714850", "lng": "4.48520900", "type": "edu", "country": "Netherlands"}], "year": "2018", "pdf": [], "doi": ["http://doi.org/10.1007/s11042-018-5691-4"]}, {"id": "0e36ada8cb9c91f07c9dcaf196d036564e117536", "title": "Much Ado About Time: Exhaustive Annotation of Temporal Data", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}, {"name": "INRIA", "source_name": "INRIA Grenoble Rhone-Alpes, Grenoble, France", "street_adddress": "655 Avenue de l'Europe, 38330 Montbonnot-Saint-Martin, France", "lat": "45.21788600", "lng": "5.80736900", "type": "edu", "country": "France"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1607.07429.pdf"], "doi": []}, {"id": "d68a6bf394f8f6440426a84d8494e83d08aa1535", "title": "Automatic Portrait Segmentation for Image Stylization", "addresses": [{"name": "Chinese University of Hong Kong", "source_name": "Chinese University of Hong Kong", "street_adddress": "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "lat": "22.41626320", "lng": "114.21093180", "type": "edu", "country": "China"}], "year": "2016", "pdf": ["http://xiaoyongshen.me/webpage_portrait/papers/portrait_eg16.pdf"], "doi": ["https://doi.org/10.1111/cgf.12814"]}, {"id": "db640eddc51258cf6b11e442745d9a4bd5d6995b", "title": "Simple Baselines for Human Pose Estimation and Tracking", "addresses": [{"name": "Microsoft Research Asia", "source_name": "Microsoft Research Asia", "street_adddress": "1 Memorial Dr, Cambridge, MA 02142, USA", "lat": "42.36142560", "lng": "-71.08120920", "type": "company", "country": "United States"}, {"name": "University of Electronic Science and Technology of China", "source_name": "University of Electronic Science and Technology of China", "street_adddress": "2 Jianshe North Rd 2nd Section, Jianshe Road, Chenghua Qu, Chengdu Shi, Sichuan Sheng, China, 610054", "lat": "30.67272100", "lng": "104.09880600", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.06208.pdf"], "doi": []}, {"id": "e1f041594fa37d407c80b28a13680a9ddc081c49", "title": "Euphrates: Algorithm-SoC Co-Design for Low-Power Mobile Continuous Vision", "addresses": [{"name": "University of Rochester", "source_name": "University of Rochester", "street_adddress": "Memorial Art Gallery, 500, University Avenue, East End, Rochester, Monroe County, New York, 14607, USA", "lat": "43.15769690", "lng": "-77.58829158", "type": "edu", "country": "United States"}, {"name": "Georgia Institute of Technology", "source_name": "Georgia Institute of Technology", "street_adddress": "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.11232.pdf"], "doi": []}, {"id": "bb1dc1e9e9c20d99b55f37b9e635457af86a065f", "title": "Neural Ctrl-F: Segmentation-Free Query-by-String Word Spotting in Handwritten Manuscript Collections", "addresses": [{"name": "Uppsala University", "source_name": "Uppsala University, Uppsala, Sweden", "street_adddress": "Uppsala, 752 36 Uppsala, Sweden", "lat": "59.85090050", "lng": "17.63000930", "type": "edu", "country": "Sweden"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.07645.pdf"], "doi": []}, {"id": "7902309d3c5ab2e1e3a1f08503dc39108e1639dc", "title": "Look into Person: Joint Body Parsing & Pose Estimation Network and A New Benchmark", "addresses": [{"name": "Adobe", "source_name": "Adobe2", "street_adddress": "345 Park Ave, San Jose, CA 95110, USA", "lat": "37.33077030", "lng": "-121.89409510", "type": "company", "country": "United States"}, {"name": "Sun Yat-Sen University", "source_name": "Sun Yat-Sen University", "street_adddress": "\u4e2d\u5927, \u65b0\u6e2f\u897f\u8def, \u9f99\u8239\u6ed8, \u5eb7\u4e50, \u6d77\u73e0\u533a (Haizhu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510105, \u4e2d\u56fd", "lat": "23.09461185", "lng": "113.28788994", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.01984.pdf"], "doi": []}, {"id": "211fe99400bde5116efea3b42719d00a34931dcd", "title": "Multimodal Differential Network for Visual Question Generation", "addresses": [{"name": "Indian Institute of Technology Delhi", "source_name": "IIIT-Delhi, India", "street_adddress": "IIIT-Delhi, Mathura Road, Friends Colony, South East Delhi, Delhi, 110020, India", "lat": "28.54632595", "lng": "77.27325504", "type": "edu", "country": "India"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.03986.pdf"], "doi": []}, {"id": "50ab5859994c76dd69f2ef6c770888408d9ae5d0", "title": "Intention Oriented Image Captions with Guiding Objects", "addresses": [{"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.07662.pdf"], "doi": []}, {"id": "fbe3ba628fa8435bf1ad4ed153c93109624b8dff", "title": "Understanding the Message of Images with Knowledge Base Traversals", "addresses": [{"name": "University of Mannheim", "source_name": "University of Mannheim, Mannheim, Germany", "street_adddress": "68131 Mannheim, Germany", "lat": "49.48371060", "lng": "8.46223330", "type": "edu", "country": "Germany"}], "year": "2016", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=2970414"]}, {"id": "428017f7a6df4d667275c7ac9b3feba39b70e4ae", "title": "CNN-RNN: A Unified Framework for Multi-label Image Classification", "addresses": [{"name": "Horizon Robotics", "source_name": "Horizon Robotics", "street_adddress": "317 3F 1 Zhongguancun Street Haidian District Beijing, 100190 China", "lat": "39.97558000", "lng": "116.31126000", "type": "company", "country": "China"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1604.04573.pdf"], "doi": []}, {"id": "857fb344977e5181bf5a99593ceba09a158d412c", "title": "VCI 2 R at the NTCIR-13 Lifelog-2 Lifelog Semantic Access Task", "addresses": [{"name": "A*STAR", "source_name": "I2R, A*STAR, Singapore", "street_adddress": "1 Fusionopolis Way, #21-01 Connexis, Singapore 138632", "lat": "1.29889260", "lng": "103.78731070", "type": "edu", "country": "Singapore"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/857f/b344977e5181bf5a99593ceba09a158d412c.pdf"], "doi": []}, {"id": "a799babbbd56a047feee85d09e57e2c240c5f50c", "title": "Image describing based on bidirectional LSTM and improved sequence sampling", "addresses": [{"name": "Chongqing University", "source_name": "Chongqing University", "street_adddress": "\u91cd\u5e86\u5de5\u5546\u5927\u5b66, 19, \u7fe0\u6797\u8def, \u91cd\u5e86\u5e02, \u91cd\u5e86\u5e02\u4e2d\u5fc3, \u5357\u5cb8\u533a (Nan'an), \u91cd\u5e86\u5e02, 400067, \u4e2d\u56fd", "lat": "29.50841740", "lng": "106.57858552", "type": "edu", "country": "China"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8078733"]}, {"id": "d4ea0438b6c0479a7d7611130a0dc242a22f93eb", "title": "Pose2Instance: Harnessing Keypoints for Person Instance Segmentation", "addresses": [{"name": "UC San Diego", "source_name": "UC San Diego", "street_adddress": "9500 Gilman Dr, La Jolla, CA 92093, USA", "lat": "32.88006040", "lng": "-117.23401350", "type": "edu", "country": "United States"}, {"name": "Google", "source_name": "Google, Inc.", "street_adddress": "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "lat": "37.42199990", "lng": "-122.08405750", "type": "company", "country": "United States"}, {"name": "Cornell University", "source_name": "Cornell University", "street_adddress": "Cornell University, Forest Home Drive, Forest Home, Tompkins County, New York, 14853, USA", "lat": "42.45055070", "lng": "-76.47835130", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.01152.pdf"], "doi": []}, {"id": "66652367a369d18e1845dd14220dc94a9748c9fd", "title": "Learning Spatial Regularization with Image-Level Supervisions for Multi-label Image Classification", "addresses": [{"name": "Chinese University of Hong Kong", "source_name": "Chinese University of Hong Kong", "street_adddress": "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "lat": "22.41626320", "lng": "114.21093180", "type": "edu", "country": "China"}, {"name": "University of Science and Technology of China", "source_name": "University of Science and Technology of China", "street_adddress": "\u4e2d\u56fd\u79d1\u5b66\u6280\u672f\u5927\u5b66 \u4e1c\u6821\u533a, 96\u53f7, \u91d1\u5be8\u8def, \u6c5f\u6dee\u5316\u80a5\u5382\u5c0f\u533a, \u829c\u6e56\u8def\u8857\u9053, \u5408\u80a5\u5e02\u533a, \u5408\u80a5\u5e02, \u5b89\u5fbd\u7701, 230026, \u4e2d\u56fd", "lat": "31.83907195", "lng": "117.26420748", "type": "edu", "country": "China"}, {"name": "University of Sydney", "source_name": "University of Sydney", "street_adddress": "USyd, Fisher Road, Camperdown, Sydney, NSW, 2006, Australia", "lat": "-33.88890695", "lng": "151.18943366", "type": "edu", "country": "Australia"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1702.05891.pdf"], "doi": []}, {"id": "6f44303f9664a4ceabd0f4bc74cb3886aad5012f", "title": "An Integral Pose Regression System for the ECCV2018 PoseTrack Challenge", "addresses": [{"name": "Microsoft", "source_name": "Microsoft Corporation, Redmond, WA, USA", "street_adddress": "One Microsoft Way, Redmond, WA 98052, USA", "lat": "47.64233180", "lng": "-122.13693020", "type": "company", "country": "United States"}, {"name": "Zhejiang University", "source_name": "Zhejiang University", "street_adddress": "\u6d59\u6c5f\u5927\u5b66\u4e4b\u6c5f\u6821\u533a, \u4e4b\u6c5f\u8def, \u8f6c\u5858\u8857\u9053, \u897f\u6e56\u533a (Xihu), \u676d\u5dde\u5e02 Hangzhou, \u6d59\u6c5f\u7701, 310008, \u4e2d\u56fd", "lat": "30.19331415", "lng": "120.11930822", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.06079.pdf"], "doi": []}, {"id": "d2796a0d1ba7ed9287a9db6f4714585b8508871f", "title": "Human Centred Object Co-Segmentation", "addresses": [{"name": "Cornell University", "source_name": "Cornell University", "street_adddress": "Cornell University, Forest Home Drive, Forest Home, Tompkins County, New York, 14853, USA", "lat": "42.45055070", "lng": "-76.47835130", "type": "edu", "country": "United States"}, {"name": "Stanford University", "source_name": "Stanford University", "street_adddress": "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1606.03774.pdf"], "doi": []}, {"id": "68d96226fb71daad7d1a4ccbda267062244d9bc0", "title": "Aligning Books and Movies: Towards Story-Like Visual Explanations by Watching Movies and Reading Books", "addresses": [{"name": "University of Toronto", "source_name": "University of Toronto", "street_adddress": "University of Toronto, St. George Street, Bloor Street Culture Corridor, Old Toronto, Toronto, Ontario, M5S 1A5, Canada", "lat": "43.66333345", "lng": "-79.39769975", "type": "edu", "country": "Canada"}, {"name": "MIT", "source_name": "Massachusetts Institute", "street_adddress": "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1506.06724.pdf"], "doi": []}, {"id": "f9e3bef2ffec5bd1e62003a3f1d8f735265b4d2f", "title": "ReDMark: Framework for Residual Diffusion Watermarking on Deep Networks", "addresses": [{"name": "University of Michigan", "source_name": "University of Michigan", "street_adddress": "University of Michigan, 500, Hayward Street, Ann Arbor, Washtenaw County, Michigan, 48109, USA", "lat": "42.29421420", "lng": "-83.71003894", "type": "edu", "country": "United States"}, {"name": "University of Queensland", "source_name": "University of Queensland", "street_adddress": "University of Queensland, University Drive, Hill End, St Lucia, Brisbane, QLD, 4072, Australia", "lat": "-27.49741805", "lng": "153.01316956", "type": "edu", "country": "Australia"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.07248.pdf"], "doi": []}, {"id": "5a546cd0e8622b32cfdfd0358041f7d7ab00b5d4", "title": "SuperNeurons: FFT-based Gradient Sparsification in the Distributed Training of Deep Neural Networks", "addresses": [{"name": "Brown University", "source_name": "Brown University", "street_adddress": "Brown University, Waterman Street, College Hill, Providence, Bristol, Rhode Island, 02912, USA", "lat": "41.82686820", "lng": "-71.40123146", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.08596.pdf"], "doi": []}, {"id": "e0ffda149d1d81fff507953377e08cf4f718d8ae", "title": "Image Captioning with both Object and Scene Information", "addresses": [{"name": "Chinese Academy of Sciences", "source_name": "Chinese Academy of Sciences", "street_adddress": "\u4e2d\u56fd\u79d1\u5b66\u9662\u5fc3\u7406\u7814\u7a76\u6240, 16, \u6797\u8403\u8def, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100101, \u4e2d\u56fd", "lat": "40.00447950", "lng": "116.37023800", "type": "edu", "country": "China"}], "year": "2016", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=2984069"]}, {"id": "ee53c9480132fc0d09b1192226cb2c460462fd6d", "title": "Channel Pruning for Accelerating Very Deep Neural Networks", "addresses": [{"name": "Xi\u2019an Jiaotong University", "source_name": "Institute of Information and System Sciences, Faculty of Mathematics and Statistics, Xi\u2019an Jiaotong University, Xi\u2019an, China", "street_adddress": "28 Xianning W Rd, JiaoDa ShangYe JieQu, Beilin Qu, Xian Shi, Shaanxi Sheng, China", "lat": "34.25080300", "lng": "108.98369300", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.06168.pdf"], "doi": []}, {"id": "2453dd38cde21f3248b55d281405f11d58168fa9", "title": "Multi-scale Patch Aggregation (MPA) for Simultaneous Detection and Segmentation", "addresses": [{"name": "Chinese University of Hong Kong", "source_name": "Chinese University of Hong Kong", "street_adddress": "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "lat": "22.41626320", "lng": "114.21093180", "type": "edu", "country": "China"}], "year": "2016", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2016/papers/Liu_Multi-Scale_Patch_Aggregation_CVPR_2016_paper.pdf", "http://www.cse.cuhk.edu.hk/~leojia/papers/mpa_cvpr16.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Liu_Multi-Scale_Patch_Aggregation_CVPR_2016_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780711", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.342", "http://doi.org/10.1109/CVPR.2016.342"]}, {"id": "0abd1a332717f540f1e3297a9eedd9633ad9c3a9", "title": "From UI Design Image to GUI Skeleton: A Neural Machine Translator to Bootstrap Mobile GUI Implementation", "addresses": [{"name": "Australian National University", "source_name": "Australian National University", "street_adddress": "Canberra ACT 0200, Australia", "lat": "-35.27769990", "lng": "149.11852700", "type": "edu", "country": "Australia"}, {"name": "Nanyang Technological University", "source_name": "Nanyang Technological University", "street_adddress": "NTU, Faculty Avenue, Jurong West, Southwest, 637460, Singapore", "lat": "1.34841040", "lng": "103.68297965", "type": "edu", "country": "Singapore"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3180240"]}, {"id": "51a03fe7cbcf5c650b5dbdba0bf14be8a45cbaee", "title": "Deep Triplet Quantization", "addresses": [{"name": "Microsoft Research Asia", "source_name": "Microsoft Research Asia", "street_adddress": "1 Memorial Dr, Cambridge, MA 02142, USA", "lat": "42.36142560", "lng": "-71.08120920", "type": "company", "country": "United States"}, {"name": "Tsinghua University & Beijing National Research Center for Information Science and Technology", "source_name": "Tsinghua University & Beijing National Research Center for Information Science and Technology, Beijing, China", "street_adddress": "30 Shuangqing Rd, Haidian Qu, Beijing Shi, China", "lat": "39.99966740", "lng": "116.32644390", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3240516"]}, {"id": "85a65932f30b05532e259a99bd6a179af20ab267", "title": "HashNet: Deep Learning to Hash by Continuation", "addresses": [{"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}, {"name": "University of Illinois at Chicago", "source_name": "University of Illinois at Chicago", "street_adddress": "University of Illinois at Chicago, West Taylor Street, Greektown, Chicago, Cook County, Illinois, 60607, USA", "lat": "41.86898915", "lng": "-87.64856256", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1702.00758.pdf"], "doi": []}, {"id": "1ed5c62eec52380c285daf2ffa7576d96e4ac150", "title": "Modeling Image Virality with Pairwise Spatial Transformer Networks", "addresses": [{"name": "MIT", "source_name": "Massachusetts Institute", "street_adddress": "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu", "country": "United States"}, {"name": "Indian Institute of Technology Delhi", "source_name": "IIIT-Delhi, India", "street_adddress": "IIIT-Delhi, Mathura Road, Friends Colony, South East Delhi, Delhi, 110020, India", "lat": "28.54632595", "lng": "77.27325504", "type": "edu", "country": "India"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1709.07914.pdf"], "doi": []}, {"id": "6f1c84d5a137ad14e5de9a8728fced8044d05b79", "title": "SketchyScene: Richly-Annotated Scene Sketches", "addresses": [{"name": "University of Maryland", "source_name": "University of Maryland", "street_adddress": "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu", "country": "United States"}, {"name": "Queen Mary University of London", "source_name": "Queen Mary University of London", "street_adddress": "Queen Mary (University of London), Mile End Road, Globe Town, Mile End, London Borough of Tower Hamlets, London, Greater London, England, E1 4NS, UK", "lat": "51.52472720", "lng": "-0.03931035", "type": "edu", "country": "United Kingdom"}, {"name": "Sun Yat-Sen University", "source_name": "Sun Yat-Sen University", "street_adddress": "\u4e2d\u5927, \u65b0\u6e2f\u897f\u8def, \u9f99\u8239\u6ed8, \u5eb7\u4e50, \u6d77\u73e0\u533a (Haizhu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510105, \u4e2d\u56fd", "lat": "23.09461185", "lng": "113.28788994", "type": "edu", "country": "China"}, {"name": "Shandong University", "source_name": "Shandong University", "street_adddress": "\u5c71\u4e1c\u5927\u5b66, \u6cf0\u5b89\u8857, \u9ccc\u5c71\u536b\u8857\u9053, \u5373\u58a8\u533a, \u9752\u5c9b\u5e02, \u5c71\u4e1c\u7701, 266200, \u4e2d\u56fd", "lat": "36.36934730", "lng": "120.67381800", "type": "edu", "country": "China"}, {"name": "Simon Fraser University", "source_name": "Simon Fraser University", "street_adddress": "SFU Burnaby, South Campus Road, Barnet, Burnaby, Metro Vancouver, British Columbia, V5A 4X6, Canada", "lat": "49.27674540", "lng": "-122.91777375", "type": "edu", "country": "Canada"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.02473.pdf"], "doi": []}, {"id": "e8cda2c754670850ec722799640c6cb42dfb8199", "title": "4D Generic Video Object Proposals", "addresses": [{"name": "RWTH Aachen University", "source_name": "RWTH Aachen University", "street_adddress": "RWTH Aachen, Mies-van-der-Rohe-Stra\u00dfe, K\u00f6nigsh\u00fcgel, Aachen-Mitte, Aachen, St\u00e4dteregion Aachen, Regierungsbezirk K\u00f6ln, Nordrhein-Westfalen, 52074, Deutschland", "lat": "50.77917030", "lng": "6.06728733", "type": "edu", "country": "Germany"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.09260.pdf"], "doi": []}, {"id": "5abc8b9ac261f320cae1ce6676a3f05038b93436", "title": "Mixed Supervised Object Detection with Robust Objectness Transfer", "addresses": [{"name": "National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China", "source_name": "National Laboratory of Pattern Recognition (NLPR) of Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China", "street_adddress": "China, Beijing, Haidian, \u4e2d\u5173\u6751\u4e1c\u8def95\u53f7", "lat": "39.97920300", "lng": "116.33287000", "type": "edu", "country": "China"}, {"name": "University of Dundee", "source_name": "University of Dundee", "street_adddress": "University of Dundee, Park Wynd, Law, Dundee, Dundee City, Scotland, DD1 4HN, UK", "lat": "56.45796755", "lng": "-2.98214831", "type": "edu", "country": "United Kingdom"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8304628"]}, {"id": "645f09f4bc2e6a13663564ee9032ca16e35fc52d", "title": "Interactive Demonstration of Probabilistic Predicates", "addresses": [{"name": "Microsoft", "source_name": "Microsoft Corporation, Redmond, WA, USA", "street_adddress": "One Microsoft Way, Redmond, WA 98052, USA", "lat": "47.64233180", "lng": "-122.13693020", "type": "company", "country": "United States"}, {"name": "University of Washington", "source_name": "University of Washington", "street_adddress": "University of Washington, Rainier Vista, Montlake, University District, Seattle, King County, Washington, 98195, USA", "lat": "47.65432380", "lng": "-122.30800894", "type": "edu", "country": "United States"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3193542"]}, {"id": "397085122a5cade71ef6c19f657c609f0a4f7473", "title": "Using Segmentation to Predict the Absence of Occluded Parts", "addresses": [{"name": "UC Irvine", "source_name": "UC Irvine", "street_adddress": "Irvine, CA 92697, USA", "lat": "33.64049520", "lng": "-117.84429620", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/db11/4901d09a07ab66bffa6986bc81303e133ae1.pdf"], "doi": []}, {"id": "60ac4be07ab4b20e1b9d0879e9553f05ec581867", "title": "LabelBank: Revisiting Global Perspectives for Semantic Segmentation", "addresses": [{"name": "University of Southern California", "source_name": "University of Southern California", "street_adddress": "University of Southern California, Watt Way, Saint James Park, LA, Los Angeles County, California, 90089, USA", "lat": "34.02241490", "lng": "-118.28634407", "type": "edu", "country": "United States"}, {"name": "Simon Fraser University", "source_name": "Simon Fraser University", "street_adddress": "SFU Burnaby, South Campus Road, Barnet, Burnaby, Metro Vancouver, British Columbia, V5A 4X6, Canada", "lat": "49.27674540", "lng": "-122.91777375", "type": "edu", "country": "Canada"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.09891.pdf"], "doi": []}, {"id": "0c2cb193274217855000c98a02488885571b55bc", "title": "TrackNet: Simultaneous Object Detection and Tracking and Its Application in Traffic Video Analysis", "addresses": [{"name": "New York University", "source_name": "New York University", "street_adddress": "NYU, West 4th Street, NoHo Historic District, NoHo, Manhattan, Manhattan Community Board 2, New York County, NYC, New York, 10012, USA", "lat": "40.72925325", "lng": "-73.99625394", "type": "edu", "country": "United States"}, {"name": "Chongqing University of Technology", "source_name": "Chongqing University of Technology, China", "street_adddress": "69 Hongguang Ave, Banan Qu, Chongqing Shi, China", "lat": "29.45832600", "lng": "106.52994700", "type": "edu", "country": "China"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1902.01466.pdf"], "doi": []}, {"id": "a98b63516c7d45eadf8cf4045ea114918eb3b636", "title": "Selective Refinement Network for High Performance Face Detection", "addresses": [{"name": "Chinese Academy of Sciences", "source_name": "Chinese Academy of Sciences", "street_adddress": "\u4e2d\u56fd\u79d1\u5b66\u9662\u5fc3\u7406\u7814\u7a76\u6240, 16, \u6797\u8403\u8def, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100101, \u4e2d\u56fd", "lat": "40.00447950", "lng": "116.37023800", "type": "edu", "country": "China"}, {"name": "University of Chinese Academy of Sciences", "source_name": "University of Chinese Academy of Sciences", "street_adddress": "University of Chinese Academy of Sciences, UCAS, Yuquanlu, \u7389\u6cc9\u8def, \u7530\u6751, \u6d77\u6dc0\u533a, 100049, \u4e2d\u56fd", "lat": "39.90828040", "lng": "116.24585270", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.02693.pdf"], "doi": []}, {"id": "6a9c3011b5092daa1d0cacda23f20ca4ae74b902", "title": "Fast and Accurate Person Re-Identification with RMNet.", "addresses": [{"name": "Intel", "source_name": "Intel Corp., 4600 S. Dobson Road, Chandler, AZ 85248", "street_adddress": "4500 S Dobson Rd, Chandler, AZ 85248, USA", "lat": "33.24160080", "lng": "-111.88390830", "type": "company", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.02465.pdf"], "doi": []}, {"id": "3361905a9ff903142e50d5b608f4775f1c5bac1a", "title": "Pathologist-level classification of histologic patterns on resected lung adenocarcinoma slides with deep neural networks", "addresses": [{"name": "Dartmouth College", "source_name": "Dartmouth College", "street_adddress": "Dartmouth College, Tuck Mall, Hanover, Grafton County, New Hampshire, 03755, USA", "lat": "43.70479270", "lng": "-72.29259090", "type": "edu", "country": "United States"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.11489.pdf"], "doi": []}, {"id": "02a5b7a41ffa8518eb3b7cae9914a2bd2bbc886b", "title": "Fast Online Object Tracking and Segmentation: A Unifying Approach", "addresses": [{"name": "University of Oxford", "source_name": "University of Oxford", "street_adddress": "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "lat": "51.75345380", "lng": "-1.25400997", "type": "edu", "country": "United Kingdom"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.05050.pdf"], "doi": []}, {"id": "7e163ae363b62b708566f348da87750284860822", "title": "Weakly-Supervised Spatial Context Networks", "addresses": [{"name": "University of Maryland", "source_name": "University of Maryland", "street_adddress": "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu", "country": "United States"}, {"name": "University of British Columbia", "source_name": "University of British Columbia", "street_adddress": "University of British Columbia, Eagles Drive, Hawthorn Place, University Endowment Lands, Metro Vancouver, British Columbia, V6T, Canada", "lat": "49.25839375", "lng": "-123.24658161", "type": "edu", "country": "Canada"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.02998.pdf"], "doi": []}, {"id": "e4d4346bd415c6fa9187c16a9b7f5c69f48f1ec4", "title": "Towards High Performance Video Object Detection for Mobiles", "addresses": [{"name": "Microsoft Research Asia", "source_name": "Microsoft Research Asia", "street_adddress": "1 Memorial Dr, Cambridge, MA 02142, USA", "lat": "42.36142560", "lng": "-71.08120920", "type": "company", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.05830.pdf"], "doi": []}, {"id": "0ec03a13063e5811ec9461cf7af04f4f3110ccaa", "title": "Visual Question Answering with Question Representation Update (QRU)", "addresses": [{"name": "Chinese University of Hong Kong", "source_name": "Chinese University of Hong Kong", "street_adddress": "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "lat": "22.41626320", "lng": "114.21093180", "type": "edu", "country": "China"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/2695/46925f0fd457b31c13c2870343b0aed761dc.pdf"], "doi": []}, {"id": "0f1c436aa7b1194e8660f7352315497c38ade853", "title": "GANtruth - an unpaired image-to-image translation method for driving scenarios", "addresses": [{"name": "KTH Royal Institute of Technology, Stockholm", "source_name": "KTH   Royal Institute of Technology, Stockholm", "street_adddress": "KTH, Teknikringen, L\u00e4rkstaden, Norra Djurg\u00e5rden, \u00d6stermalms stadsdelsomr\u00e5de, Sthlm, Stockholm, Stockholms l\u00e4n, Svealand, 114 28, Sverige", "lat": "59.34986645", "lng": "18.07063213", "type": "edu", "country": "Sweden"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.01710.pdf"], "doi": []}, {"id": "be22647956f1bc8cf6f936ae3c85f5637492b6b8", "title": "Ambiguity Helps: Classification with Disagreements in Crowdsourced Annotations", "addresses": [{"name": "Harvard University", "source_name": "Harvard University", "street_adddress": "Harvard University, Soldiers Field Road, Allston, Boston, Suffolk County, Massachusetts, 02163, USA", "lat": "42.36782045", "lng": "-71.12666653", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2016/supplemental/Sharmanska_Ambiguity_Helps_Classification_2016_CVPR_supplemental.pdf", "http://sro.sussex.ac.uk/60510/1/Sharmanska_Ambiguity_Helps_Classification_CVPR_2016_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780610", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.241", "http://doi.org/10.1109/CVPR.2016.241"]}, {"id": "fa5ab04ebf64de3bd57bd0729ce9ca3440258acc", "title": "Unprecedented Usage of Pre-trained CNNs on Beauty Product", "addresses": [{"name": "University of Malaya, Kuala Lumpur", "source_name": "University of Malaya", "street_adddress": "UM, Lingkaran Wawasan, Bukit Pantai, Bangsar, KL, 50603, Malaysia", "lat": "3.12267405", "lng": "101.65356103", "type": "edu", "country": "Malaysia"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3266433"]}, {"id": "9c2e5e2ba7c5b3a555c6c72f518e3631aab23c19", "title": "RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation", "addresses": [{"name": "University of Adelaide", "source_name": "University of Adelaide", "street_adddress": "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu", "country": "Australia"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1611.06612.pdf"], "doi": []}, {"id": "1daaeae28270b06962eb6fcf812a368892b5dff4", "title": "Modeling Visual Context Is Key to Augmenting Object Detection Datasets", "addresses": [{"name": "INRIA", "source_name": "INRIA Grenoble Rhone-Alpes, Grenoble, France", "street_adddress": "655 Avenue de l'Europe, 38330 Montbonnot-Saint-Martin, France", "lat": "45.21788600", "lng": "5.80736900", "type": "edu", "country": "France"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.07428.pdf"], "doi": []}, {"id": "3fb4bf38d34f7f7e5b3df36de2413d34da3e174a", "title": "Persuasive Faces: Generating Faces in Advertisements", "addresses": [{"name": "University of Pittsburgh", "source_name": "University of Pittsburgh", "street_adddress": "University of Pittsburgh, Sutherland Drive, West Oakland, PGH, Allegheny County, Pennsylvania, 15240, USA", "lat": "40.44415295", "lng": "-79.96243993", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.09882.pdf"], "doi": []}, {"id": "41aa209e9d294d370357434f310d49b2b0baebeb", "title": "Beyond caption to narrative: Video captioning with multiple sentences", "addresses": [{"name": "University of Tokyo", "source_name": "University of Tokyo", "street_adddress": "\u6771\u4eac\u5927\u5b66 \u67cf\u30ad\u30e3\u30f3\u30d1\u30b9, \u5b66\u878d\u5408\u306e\u9053, \u67cf\u5e02, \u5343\u8449\u770c, \u95a2\u6771\u5730\u65b9, 277-8583, \u65e5\u672c", "lat": "35.90204480", "lng": "139.93622009", "type": "edu", "country": "Japan"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1605.05440.pdf"], "doi": []}, {"id": "21c99706bb26e9012bfb4d8d48009a3d45af59b2", "title": "Neural Module Networks", "addresses": [{"name": "University of California, Berkeley", "source_name": "University of California, Berkeley", "street_adddress": "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "lat": "37.86871260", "lng": "-122.25586815", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1511.02799.pdf"], "doi": []}, {"id": "97ccbe3440e5a574b37753ff49165c7ee97a6eb4", "title": "Efficient Coarse-to-Fine Non-Local Module for the Detection of Small Objects.", "addresses": [{"name": "Weizmann Institute of Science", "source_name": "Weizmann Institute of Science", "street_adddress": "\u05de\u05db\u05d5\u05df \u05d5\u05d9\u05e6\u05de\u05df \u05dc\u05de\u05d3\u05e2, \u05e9\u05d3\u05e8\u05ea \u05de\u05e8\u05db\u05d5\u05e1 \u05d6\u05d9\u05d5, \u05de\u05e2\u05d5\u05e0\u05d5\u05ea \u05e9\u05d9\u05d9\u05df, \u05d0\u05d7\u05d5\u05d6\u05d5\u05ea \u05d4\u05e0\u05e9\u05d9\u05d0, \u05e8\u05d7\u05d5\u05d1\u05d5\u05ea, \u05de\u05d7\u05d5\u05d6 \u05d4\u05de\u05e8\u05db\u05d6, NO, \u05d9\u05e9\u05e8\u05d0\u05dc", "lat": "31.90784990", "lng": "34.81334092", "type": "edu", "country": "Israel"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.12152.pdf"], "doi": []}, {"id": "2a4bf8d096ea9b6a84ebb6cecf98589a76806777", "title": "Evaluation of Segmentation Quality via Adaptive Composition of Reference Segmentations", "addresses": [{"name": "Hong Kong Polytechnic University", "source_name": "Hong Kong Polytechnic University", "street_adddress": "hong kong, 11, \u80b2\u624d\u9053 Yuk Choi Road, \u5c16\u6c99\u5480 Tsim Sha Tsui, \u6cb9\u5c16\u65fa\u5340 Yau Tsim Mong District, \u4e5d\u9f8d Kowloon, HK, 00000, \u4e2d\u56fd", "lat": "22.30457200", "lng": "114.17976285", "type": "edu", "country": "China"}, {"name": "Southwest Jiaotong University", "source_name": "Southwest Jiaotong University", "street_adddress": "\u897f\u5357\u4ea4\u901a\u5927\u5b66 - Xinan Jiaotong University, \u4e8c\u73af\u9ad8\u67b6\u8def, \u6c81\u56ed\u5c0f\u533a, \u91d1\u725b\u533a, \u91d1\u725b\u533a (Jinniu), \u6210\u90fd\u5e02 / Chengdu, \u56db\u5ddd\u7701, 610084, \u4e2d\u56fd", "lat": "30.69784700", "lng": "104.05208110", "type": "edu", "country": "China"}, {"name": "Xi\u2019an Jiaotong University", "source_name": "Institute of Information and System Sciences, Faculty of Mathematics and Statistics, Xi\u2019an Jiaotong University, Xi\u2019an, China", "street_adddress": "28 Xianning W Rd, JiaoDa ShangYe JieQu, Beilin Qu, Xian Shi, Shaanxi Sheng, China", "lat": "34.25080300", "lng": "108.98369300", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["http://faculty.ucmerced.edu/mhyang/papers/pami16_segmentation_evaluation.pdf", "http://faculty.ucmerced.edu/mhyang/papers/pami17_segmentation_evaluation.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7723880", "http://doi.ieeecomputersociety.org/10.1109/TPAMI.2016.2622703", "http://doi.org/10.1109/TPAMI.2016.2622703", "https://www.ncbi.nlm.nih.gov/pubmed/27810800"]}, {"id": "7c4fdcda302b93c0a275420ddd6e249c565173ff", "title": "VISIR: Visual and Semantic Image Label Refinement", "addresses": [{"name": "Max Planck Institute for Informatics", "source_name": "Max Planck Institute for Informatics", "street_adddress": "MPII, E1 4, Campus, Universit\u00e4t, Sankt Johann, Bezirk Mitte, Saarbr\u00fccken, Regionalverband Saarbr\u00fccken, Saarland, 66123, Deutschland", "lat": "49.25795660", "lng": "7.04577417", "type": "edu", "country": "Germany"}, {"name": "University of Warwick", "source_name": "University of Warwick", "street_adddress": "University of Warwick, University Road, Kirby Corner, Cannon Park, Coventry, West Midlands Combined Authority, West Midlands, England, CV4 7AL, UK", "lat": "52.37931310", "lng": "-1.56042520", "type": "edu", "country": "United Kingdom"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3159693"]}, {"id": "a34de6e26cf34257d6c2fdc9a1801aea46c00b08", "title": "Complex Object Classification: A Multi-Modal Multi-Instance Multi-Label Deep Network with Optimal Transport", "addresses": [{"name": "Nanjing University", "source_name": "Nanjing University", "street_adddress": "NJU, \u4e09\u6c5f\u8def, \u9f13\u697c\u533a, \u5357\u4eac\u5e02, \u6c5f\u82cf\u7701, 210093, \u4e2d\u56fd", "lat": "32.05659570", "lng": "118.77408833", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3220012"]}, {"id": "b181ae8ed315ceb8f03332ba02ef0849adbe5b4c", "title": "Multi-modal Capsule Routing for Actor and Action Video Segmentation Conditioned on Natural Language Queries", "addresses": [{"name": "University of Central Florida", "source_name": "University of Central Florida", "street_adddress": "University of Central Florida, Libra Drive, University Park, Orange County, Florida, 32816, USA", "lat": "28.59899755", "lng": "-81.19712501", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.00303.pdf"], "doi": []}, {"id": "a213405441c68a0ce415a4a842bdd6ac62c1667b", "title": "Enhancement of SSD by concatenating feature maps for object detection.", "addresses": [{"name": "Seoul National University", "source_name": "Seoul National University", "street_adddress": "\uc11c\uc6b8\ub300\ud559\uad50, \uc11c\ud638\ub3d9\ub85c, \uc11c\ub454\ub3d9, \uad8c\uc120\uad6c, \uc218\uc6d0\uc2dc, \uacbd\uae30, 16614, \ub300\ud55c\ubbfc\uad6d", "lat": "37.26728000", "lng": "126.98411510", "type": "edu", "country": "South Korea"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.09587.pdf"], "doi": []}, {"id": "0e08cf0b19f0600dadce0f6694420d643ea9828b", "title": "The Middle Child Problem: Revisiting Parametric Min-Cut and Seeds for Object Proposals", "addresses": [{"name": "Georgia Institute of Technology", "source_name": "Georgia Institute of Technology", "street_adddress": "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu", "country": "United States"}, {"name": "Oregon State University", "source_name": "Oregon State University", "street_adddress": "OSU Beaver Store, 538, Southwest 6th Avenue, Portland Downtown, Portland, Multnomah County, Oregon, 97204, USA", "lat": "45.51982890", "lng": "-122.67797964", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["http://openaccess.thecvf.com/content_iccv_2015/papers/Humayun_The_Middle_Child_ICCV_2015_paper.pdf", "http://web.engr.oregonstate.edu/~lif/Middle_Child_ICCV15.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Humayun_The_Middle_Child_ICCV_2015_paper.pdf", "https://smartech.gatech.edu/bitstream/handle/1853/55478/The%20Middle%20Child%20Problem-%20Revisiting%20Parametric%20Min-cut%20and%20Seeds%20for%20Object%20Proposals.pdf?isAllowed=y&sequence=1"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410544", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2015.187", "http://doi.org/10.1109/ICCV.2015.187"]}, {"id": "3e0a1884448bfd7f416c6a45dfcdfc9f2e617268", "title": "Understanding and Controlling User Linkability in Decentralized Learning", "addresses": [{"name": "Max Planck Institute for Informatics", "source_name": "Max Planck Institute for Informatics", "street_adddress": "MPII, E1 4, Campus, Universit\u00e4t, Sankt Johann, Bezirk Mitte, Saarbr\u00fccken, Regionalverband Saarbr\u00fccken, Saarland, 66123, Deutschland", "lat": "49.25795660", "lng": "7.04577417", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.05838.pdf"], "doi": []}, {"id": "5d165ff5b0b389e32809c17838a2afc218a91d62", "title": "Object Detectors Emerge in Deep Scene CNNs", "addresses": [{"name": "MIT", "source_name": "Massachusetts Institute", "street_adddress": "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu", "country": "United States"}], "year": "2014", "pdf": ["https://arxiv.org/pdf/1412.6856.pdf"], "doi": []}, {"id": "dc9b95afcbd972d973f3ae29f05bbc8fa45d6a16", "title": "Learning deep structured network for weakly supervised change detection", "addresses": [{"name": "Australian National University", "source_name": "Australian National University", "street_adddress": "Canberra ACT 0200, Australia", "lat": "-35.27769990", "lng": "149.11852700", "type": "edu", "country": "Australia"}, {"name": "ShanghaiTech University", "source_name": "ShanghaiTech University", "street_adddress": "Yueyang Rd, Xuhui Qu, Shanghai Shi, China", "lat": "31.20254500", "lng": "121.45308600", "type": "edu", "country": "China"}, {"name": "University of Western Australia", "source_name": "University of Western Australia", "street_adddress": "UWA, 35, Underwood Avenue, Daglish, Perth, Western Australia, 6009, Australia", "lat": "-31.95040445", "lng": "115.79790037", "type": "edu", "country": "Australia"}, {"name": "Murdoch University", "source_name": "Murdoch University, Murdoch, WA, Australia", "street_adddress": "90 South St, Murdoch WA 6150, Australia", "lat": "-32.06651350", "lng": "115.83583130", "type": "edu", "country": "Australia"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1606.02009.pdf"], "doi": []}, {"id": "9d62a78b006b09fe8f20eb7cb72e2b542cb5fbad", "title": "ImagineNet : Style Transfer from Fine Art to Graphical User Interfaces", "addresses": [{"name": "Stanford University", "source_name": "Stanford University", "street_adddress": "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/9d62/a78b006b09fe8f20eb7cb72e2b542cb5fbad.pdf"], "doi": []}, {"id": "0ac43cbd4c25994ea2687743c5b666d498831687", "title": "Robust Adversarial Perturbation on Deep Proposal-based Models", "addresses": [{"name": "State University of New York", "source_name": "University at Albany, State University of New York, Albany, USA", "street_adddress": "353 Broadway, Albany, NY 12207, USA", "lat": "42.64805160", "lng": "-73.74957600", "type": "edu", "country": "United States"}, {"name": "GE Global Research Center", "source_name": "GE Global Research Center", "street_adddress": "GE Global Research Center, Aqueduct, Niskayuna, Schenectady County, New York, USA", "lat": "42.82982480", "lng": "-73.87719385", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.05962.pdf"], "doi": []}, {"id": "95f74ce5a69fdcd2abda908724d2ab4977e72100", "title": "Using Syntax to Ground Referring Expressions in Natural Images", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.10547.pdf"], "doi": []}, {"id": "01100c14d0a06376dbb0fae6fe7995f7b3aed8b6", "title": "Active learning for structured probabilistic models with histogram approximation", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}, {"name": "Virginia Tech", "source_name": "Virginia Tech", "street_adddress": "Blacksburg, VA 24061, USA", "lat": "37.22838430", "lng": "-80.42341670", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/2B_030.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/2B_030_ext.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2015/ext/2B_030_ext.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Sun_Active_Learning_for_2015_CVPR_paper.pdf", "https://filebox.ece.vt.edu/~dbatra/papers/slb_cvpr15.pdf", "https://www.cc.gatech.edu/~dbatra/papers/slb_cvpr15.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7298984", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2015.7298984", "http://doi.org/10.1109/CVPR.2015.7298984"]}, {"id": "a1b5b0697e46eecc9657954311828cc9b4113a26", "title": "Semantic Segmentation With Object Clique Potentials", "addresses": [{"name": "Chinese University of Hong Kong", "source_name": "Chinese University of Hong Kong", "street_adddress": "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "lat": "22.41626320", "lng": "114.21093180", "type": "edu", "country": "China"}], "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/fd6c/8c23edc6ce6bc97d44b6c739dcfe81b9dcc4.pdf"], "doi": []}, {"id": "ccd02b5cb6acee7db170c0fb7f4cf0dd64a8499f", "title": "Generation with Recursive Neural Networks", "addresses": [{"name": "Stanford University", "source_name": "Stanford University", "street_adddress": "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/ccd0/2b5cb6acee7db170c0fb7f4cf0dd64a8499f.pdf"], "doi": []}, {"id": "1cc85b17137c4d6d75e4c418976e7dceb3d7559e", "title": "Open Logo Detection Challenge", "addresses": [{"name": "Queen Mary University of London", "source_name": "Queen Mary University of London", "street_adddress": "Queen Mary (University of London), Mile End Road, Globe Town, Mile End, London Borough of Tower Hamlets, London, Greater London, England, E1 4NS, UK", "lat": "51.52472720", "lng": "-0.03931035", "type": "edu", "country": "United Kingdom"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.01964.pdf"], "doi": []}, {"id": "cd7b872365cc5b5114e0ccb833e307e874a5c3aa", "title": "Video Object Segmentation with Language Referring Expressions", "addresses": [{"name": "Max Planck Institute for Informatics", "source_name": "Max Planck Institute for Informatics", "street_adddress": "MPII, E1 4, Campus, Universit\u00e4t, Sankt Johann, Bezirk Mitte, Saarbr\u00fccken, Regionalverband Saarbr\u00fccken, Saarland, 66123, Deutschland", "lat": "49.25795660", "lng": "7.04577417", "type": "edu", "country": "Germany"}, {"name": "University of California, Berkeley", "source_name": "University of California, Berkeley", "street_adddress": "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "lat": "37.86871260", "lng": "-122.25586815", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.08006.pdf"], "doi": []}, {"id": "1c0d70587340adc412c6e2afd71012d563c1e724", "title": "Could we create a training set for image captioning using automatic translation?", "addresses": [{"name": "Bilgisayar M\u00fchendisli\u011fi, Hacettepe \u00dcniversitesi, Ankara, T\u00fcrkiye", "source_name": "Bilgisayar Mühendisliği, Hacettepe Üniversitesi, Ankara, Türkiye", "street_adddress": "\u00dcniversiteler Mh., Hacettepe Beytepe Kamp\u00fcs\u00fc No:21, 06800 \u00c7ankaya/Ankara, Turkey", "lat": "39.87143010", "lng": "32.73636570", "type": "edu", "country": "Turkey"}, {"name": "Bilgisayar M\u00fchendisli\u011fi, Orta Doggu Teknik \u00dcniversitesi, Ankara, T\u00fcrkiye", "source_name": "Bilgisayar Mühendisliği, Orta Doggu Teknik Üniversitesi, Ankara, Türkiye", "street_adddress": "\u00dcniversiteler Mh., 06800 \u00c7ankaya/Ankara, Turkey", "lat": "39.89183900", "lng": "32.78334710", "type": "edu", "country": "Poland"}], "year": "2017", "pdf": ["http://users.metu.edu.tr/snermin/papers/siu2017.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7960638", "http://doi.org/10.1109/SIU.2017.7960638"]}, {"id": "e0821e6bb9efb795b4593229e4eacd6d86cef7d9", "title": "Weakly and Semi Supervised Human Body Part Parsing via Pose-Guided Knowledge Transfer", "addresses": [{"name": "Shanghai Jiao Tong University", "source_name": "Shanghai Jiao Tong University", "street_adddress": "\u4e0a\u6d77\u4ea4\u901a\u5927\u5b66\uff08\u5f90\u6c47\u6821\u533a\uff09, \u6dee\u6d77\u897f\u8def, \u756a\u79ba\u5c0f\u533a, \u5e73\u9634\u6865, \u5f90\u6c47\u533a, \u4e0a\u6d77\u5e02, 200052, \u4e2d\u56fd", "lat": "31.20081505", "lng": "121.42840681", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.04310.pdf"], "doi": []}, {"id": "081307db6d8d709af26f49d24041086bb09abfd1", "title": "A general description generator for human activity images based on deep understanding framework", "addresses": [{"name": "Beijing Institute of Technology", "source_name": "Beijing Institute of Technology University", "street_adddress": "\u5317\u4eac\u7406\u5de5\u5927\u5b66, 5, \u4e2d\u5173\u6751\u5357\u5927\u8857, \u4e2d\u5173\u6751, \u7a3b\u9999\u56ed\u5357\u793e\u533a, \u6d77\u6dc0\u533a, \u5317\u4eac\u5e02, 100872, \u4e2d\u56fd", "lat": "39.95866520", "lng": "116.30971281", "type": "edu", "country": "China"}, {"name": "Guangxi University", "source_name": "Electronics and Information, Guangxi University", "street_adddress": "Chongwen Rd, Xixiangtang Qu, Nanning Shi, Guangxi Zhuangzuzizhiqu, China, 530001", "lat": "22.83760000", "lng": "108.28983900", "type": "edu", "country": "China"}], "year": "2015", "pdf": [], "doi": ["http://doi.org/10.1007/s00521-015-2171-x"]}, {"id": "3b08ef7aa0cf9528da42b2b594b66e4a6f7fdb7f", "title": "Active Learning for Delineation of Curvilinear Structures", "addresses": [{"name": "University of Bern", "source_name": "University of Bern, Neubr\u00fcckstrasse 10, Bern, Switzerland", "street_adddress": "Hochschulstrasse 6, 3012 Bern, Switzerland", "lat": "46.95048960", "lng": "7.43811900", "type": "edu", "country": "Switzerland"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1512.00747.pdf"], "doi": []}, {"id": "0e5d673111e398f6c083623e31c2f498f0bf7b5f", "title": "Resolving References to Objects in Photographs using the Words-As-Classifiers Model", "addresses": [{"name": "Bielefeld University", "source_name": "Bielefeld University", "street_adddress": "Fachhochschule Bielefeld FB Gestaltung, 3, Lampingstra\u00dfe, Mitte, Bielefeld, Regierungsbezirk Detmold, Nordrhein-Westfalen, 33615, Deutschland", "lat": "52.02804210", "lng": "8.51148270", "type": "edu", "country": "Germany"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1510.02125.pdf"], "doi": []}, {"id": "0910a4c470a410fac446f4026f7c8ef512ae7427", "title": "Hierarchical Question-Image Co-Attention for Visual Question Answering", "addresses": [{"name": "Virginia Tech", "source_name": "Virginia Tech", "street_adddress": "Blacksburg, VA 24061, USA", "lat": "37.22838430", "lng": "-80.42341670", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1606.00061.pdf"], "doi": []}, {"id": "431140620ecf6cbb7c4118a65f7f2b8f48089647", "title": "Segment-Phrase Table for Semantic Segmentation, Visual Entailment and Paraphrasing", "addresses": [{"name": "University of Washington", "source_name": "University of Washington", "street_adddress": "University of Washington, Rainier Vista, Montlake, University District, Seattle, King County, Washington, 98195, USA", "lat": "47.65432380", "lng": "-122.30800894", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1509.08075.pdf"], "doi": []}, {"id": "8481d4160bf5a9c760b5c4de60c82f102492317b", "title": "Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation", "addresses": [{"name": "Johns Hopkins University", "source_name": "Johns Hopkins University", "street_adddress": "Baltimore, MD 21218, USA", "lat": "39.32990130", "lng": "-76.62051770", "type": "edu", "country": "United States"}, {"name": "Google", "source_name": "Google, Inc.", "street_adddress": "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "lat": "37.42199990", "lng": "-122.08405750", "type": "company", "country": "United States"}, {"name": "Stanford University", "source_name": "Stanford University", "street_adddress": "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu", "country": "United States"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.02985.pdf"], "doi": []}, {"id": "8b5b8db6a2a2880c14894140ea70ceb5f96c3b9b", "title": "Learning a Text-Video Embedding from Incomplete and Heterogeneous Data", "addresses": [{"name": "INRIA", "source_name": "INRIA Grenoble Rhone-Alpes, Grenoble, France", "street_adddress": "655 Avenue de l'Europe, 38330 Montbonnot-Saint-Martin, France", "lat": "45.21788600", "lng": "5.80736900", "type": "edu", "country": "France"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.02516.pdf"], "doi": []}, {"id": "0c2875bb47db3698dbbb3304aca47066978897a4", "title": "Recurrent Models for Situation Recognition", "addresses": [{"name": "University of Illinois, Urbana-Champaign", "source_name": "University of Illinois, Urbana-Champaign", "street_adddress": "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.06233.pdf"], "doi": []}, {"id": "1eeca84f33079c6d7a95daf8994370b2d7a93443", "title": "Fingertip Detection and Tracking for Recognition of Air-Writing in Videos", "addresses": [{"name": "Indian Institute of Technology Bhubaneswar", "source_name": "Indian Institute of Technology Bhubaneswar, Bhubaneswar, India", "street_adddress": "Argul - Jatni Rd, Kansapada, Odisha 752050, India", "lat": "20.14389950", "lng": "85.67620330", "type": "edu", "country": "India"}, {"name": "Indian Institute of Technology Roorkee", "source_name": "Indian Institute of Technology, Roorkee", "street_adddress": "Indian Institute of Technology (IIT), Roorkee, LBS Jogging Track, Roorkee, Haridwar, Uttarakhand, 247667, India", "lat": "29.86624610", "lng": "77.89587081", "type": "edu", "country": "India"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.03016.pdf"], "doi": []}, {"id": "5a0209515ab62e008efeca31f80fa0a97031cd9d", "title": "Dataset fingerprints: Exploring image collections through data mining", "addresses": [{"name": "Georgia Tech", "source_name": "Georgia Tech, Atlanta, GA, USA", "street_adddress": "North Ave NW, Atlanta, GA 30332, USA", "lat": "33.77561780", "lng": "-84.39628500", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/3B_046.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/3B_046_ext.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2015/ext/3B_046_ext.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Rematas_Dataset_Fingerprints_Exploring_2015_CVPR_paper.pdf", "https://homes.cs.washington.edu/~krematas/Publications/rematasCVPR2015.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7299120", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2015.7299120", "http://doi.org/10.1109/CVPR.2015.7299120"]}, {"id": "84036eb97d011ed2d7c9e4eb14fa346b5347c0ad", "title": "Revisiting Pre-training: An Efficient Training Method for Image Classification", "addresses": [{"name": "Beckman Institute", "source_name": "Beckman Institute", "street_adddress": "Beckman Institute, The Presidents' Walk, Urbana, Champaign County, Illinois, 61801-2341, USA", "lat": "40.11571585", "lng": "-88.22750772", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.09347.pdf"], "doi": []}, {"id": "2b0134725e7400f2211207fbe9bfb402b9fcacf3", "title": "Deep Attribute-preserving Metric Learning for Natural Language Object Retrieval", "addresses": [{"name": "Beijing Institute of Technology", "source_name": "Beijing Institute of Technology University", "street_adddress": "\u5317\u4eac\u7406\u5de5\u5927\u5b66, 5, \u4e2d\u5173\u6751\u5357\u5927\u8857, \u4e2d\u5173\u6751, \u7a3b\u9999\u56ed\u5357\u793e\u533a, \u6d77\u6dc0\u533a, \u5317\u4eac\u5e02, 100872, \u4e2d\u56fd", "lat": "39.95866520", "lng": "116.30971281", "type": "edu", "country": "China"}, {"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}, {"name": "National University of Singapore", "source_name": "National University of Singapore", "street_adddress": "NUS, Former 1936 British Outpost, Nepal Hill, Clementi, Southwest, 117542, Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu", "country": "Singapore"}], "year": "2017", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3123439"]}, {"id": "e959a426d02dd014c1346131ac38ed50114c17b7", "title": "A Focused Dynamic Attention Model for Visual Question Answering", "addresses": [{"name": "National University of Singapore", "source_name": "National University of Singapore", "street_adddress": "NUS, Former 1936 British Outpost, Nepal Hill, Clementi, Southwest, 117542, Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu", "country": "Singapore"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1604.01485.pdf"], "doi": []}, {"id": "5f94e354faeba1d330088b926d1f7886067bc93f", "title": "RefineNet : MultiPath Refinement Networks with Identity Mappings for High-Resolution Semantic Segmentation", "addresses": [{"name": "University of Adelaide", "source_name": "University of Adelaide", "street_adddress": "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu", "country": "Australia"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/5f94/e354faeba1d330088b926d1f7886067bc93f.pdf"], "doi": []}, {"id": "d42142285c46207a16bd4294e437d504e419a9b7", "title": "Varying image description tasks : spoken versus written descriptions", "addresses": [{"name": "Tilburg University", "source_name": "Tilburg center for Cognition and Communication, Tilburg University, Tilburg, The Netherlands", "street_adddress": "Warandelaan 2, 5037 AB Tilburg, Netherlands", "lat": "51.56314060", "lng": "5.04197360", "type": "edu", "country": "Netherlands"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/d421/42285c46207a16bd4294e437d504e419a9b7.pdf"], "doi": []}, {"id": "ccd99008d942b890cecd308a31ba61240eac9e54", "title": "Learning to Segment Every Thing", "addresses": [{"name": "UC Berkeley", "source_name": "UC Berkeley", "street_adddress": "Berkeley, CA, USA", "lat": "37.87189920", "lng": "-122.25853990", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.10370.pdf"], "doi": []}, {"id": "91c184e7fb0c7cce5319b8db85c1488b3861976f", "title": "Visual Question Answer Diversity", "addresses": [{"name": "University of Texas at Austin", "source_name": "University of Texas at Austin", "street_adddress": "University of Texas at Austin, 1, East 23rd Street, The Drag, Austin, Travis County, Texas, 78712, USA", "lat": "30.28415100", "lng": "-97.73195598", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/b357/d44a34cc0f692b09a789802f5a905e12a726.pdf"], "doi": []}, {"id": "31c197a0e30f1aeb1414634968d1649e74cd8d0f", "title": "Deep correlation for matching images and text", "addresses": [{"name": "University of Surrey", "source_name": "University of Surrey", "street_adddress": "University of Surrey, Spine Road, Guildford Park, Guildford, Surrey, South East, England, GU2 7XH, UK", "lat": "51.24303255", "lng": "-0.59001382", "type": "edu", "country": "United Kingdom"}], "year": "2015", "pdf": ["http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/2B_012.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/2B_012_ext.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2015/ext/2B_012_ext.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Yan_Deep_Correlation_for_2015_CVPR_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7298966", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2015.7298966", "http://doi.org/10.1109/CVPR.2015.7298966"]}, {"id": "5b8b27d1339d788eb3e0e96888c3633a7b92dc1e", "title": "Hierarchical Image Segmentation Ensemble for Objectness in RGB-D Images", "addresses": [{"name": "Beihang University", "source_name": "Beihang University", "street_adddress": "\u5317\u4eac\u822a\u7a7a\u822a\u5929\u5927\u5b66, 37, \u5b66\u9662\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100083, \u4e2d\u56fd", "lat": "39.98083330", "lng": "116.34101249", "type": "edu", "country": "China"}, {"name": "South China University of Technology", "source_name": "South China University of Technology", "street_adddress": "\u534e\u5357\u7406\u5de5\u5927\u5b66, \u5927\u5b66\u57ce\u4e2d\u73af\u4e1c\u8def, \u5e7f\u5dde\u5927\u5b66\u57ce, \u65b0\u9020, \u756a\u79ba\u533a (Panyu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510006, \u4e2d\u56fd", "lat": "23.05020420", "lng": "113.39880323", "type": "edu", "country": "China"}], "year": "2019", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8116651"]}, {"id": "da437db062e751d49528914971ecdc868b557648", "title": "Improved Image Captioning via Policy Gradient optimization of SPIDEr", "addresses": [{"name": "University of Oxford", "source_name": "University of Oxford", "street_adddress": "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "lat": "51.75345380", "lng": "-1.25400997", "type": "edu", "country": "United Kingdom"}, {"name": "Google", "source_name": "Google, Inc.", "street_adddress": "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "lat": "37.42199990", "lng": "-122.08405750", "type": "company", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1612.00370.pdf"], "doi": []}, {"id": "ee098ed493af3abe873ce89354599e1f6bdf65be", "title": "Progressively Diffused Networks for Semantic Image Segmentation", "addresses": [{"name": "Sun Yat-Sen University", "source_name": "Sun Yat-Sen University", "street_adddress": "\u4e2d\u5927, \u65b0\u6e2f\u897f\u8def, \u9f99\u8239\u6ed8, \u5eb7\u4e50, \u6d77\u73e0\u533a (Haizhu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510105, \u4e2d\u56fd", "lat": "23.09461185", "lng": "113.28788994", "type": "edu", "country": "China"}, {"name": "Chinese University of Hong Kong", "source_name": "Chinese University of Hong Kong", "street_adddress": "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "lat": "22.41626320", "lng": "114.21093180", "type": "edu", "country": "China"}, {"name": "SenseTime", "source_name": "SenseTime", "street_adddress": "China, Beijing Shi, Haidian Qu, WuDaoKou, Zhongguancun E Rd, 1\u53f7-7", "lat": "39.99300800", "lng": "116.32988200", "type": "company", "country": "China"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1702.05839.pdf"], "doi": []}, {"id": "b1db174463b0bbc54a61fcc83acfb89ad3e3d18f", "title": "Loss Functions for Multiset Prediction", "addresses": [{"name": "New York University", "source_name": "New York University", "street_adddress": "NYU, West 4th Street, NoHo Historic District, NoHo, Manhattan, Manhattan Community Board 2, New York County, NYC, New York, 10012, USA", "lat": "40.72925325", "lng": "-73.99625394", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.05246.pdf"], "doi": []}, {"id": "2ebadff3e2a573c947d49aba987e7917a9285ce5", "title": "Investigating the feature collection for semantic segmentation via single skip connection", "addresses": [{"name": "Ajou University", "source_name": "Ajou University", "street_adddress": "\uc544\uc8fc\ub300\ud559\uad50, \uc131\ud638\ub300\uad50, \uc774\uc758\ub3d9, \uc601\ud1b5\uad6c, \uc218\uc6d0\uc2dc, \uacbd\uae30, 16499, \ub300\ud55c\ubbfc\uad6d", "lat": "37.28300030", "lng": "127.04548469", "type": "edu", "country": "Korea"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1710.08192.pdf"], "doi": []}, {"id": "f6ce7e947f1cfe75abda61f018c3ca7e38fceb20", "title": "NLE@MediaEval'17: Combining Cross-Media Similarity and Embeddings for Retrieving Diverse Social Images", "addresses": [{"name": "Naver Labs Europe, Meylan, France", "source_name": "Naver Labs Europe, Meylan, France", "street_adddress": "6 Chemin de Maupertuis, 38240 Meylan, France", "lat": "45.21739890", "lng": "5.79213490", "type": "edu", "country": "France"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/c352/159a5a280e2f7df34d9e8e1444c789e5b912.pdf"], "doi": []}, {"id": "bb6548b43c737dca642298c46ec4648a403e1b11", "title": "A Fast Multi-Task CNN for Spatial Understanding of Traffic Scenes", "addresses": [{"name": "TU Dortmund University", "source_name": "Institute of Control Theory and Systems Engineering, TU Dortmund University, Otto-Hahn-Str. 8, Dortmund, 44227, Germany", "street_adddress": "Emil-Figge-Stra\u00dfe 50, 44227 Dortmund, Germany", "lat": "51.49219020", "lng": "7.41413620", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8569822", "http://doi.org/10.1109/ITSC.2018.8569822"]}, {"id": "256623ff025f36d343588bcd0b966c1fd26afcf8", "title": "Looking for ELMo's friends: Sentence-Level Pretraining Beyond Language Modeling.", "addresses": [{"name": "New York University", "source_name": "New York University", "street_adddress": "NYU, West 4th Street, NoHo Historic District, NoHo, Manhattan, Manhattan Community Board 2, New York County, NYC, New York, 10012, USA", "lat": "40.72925325", "lng": "-73.99625394", "type": "edu", "country": "United States"}, {"name": "Johns Hopkins University", "source_name": "Johns Hopkins University", "street_adddress": "Baltimore, MD 21218, USA", "lat": "39.32990130", "lng": "-76.62051770", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.10860.pdf"], "doi": []}, {"id": "e762f25f13d6dbb95dc59af5e6fbb2160fcf4d55", "title": "Zero-Shot Detection", "addresses": [{"name": "Boston University", "source_name": "Boston University", "street_adddress": "BU, Bay State Road, Fenway, Boston, Suffolk County, Massachusetts, 02215, USA", "lat": "42.35042530", "lng": "-71.10056114", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.07113.pdf"], "doi": []}, {"id": "a3be1951ddb2fa2682385c7f22c2904f5c22a66d", "title": "Traffic-Sign Detection and Classification in the Wild", "addresses": [{"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}, {"name": "Beijing, China", "source_name": "Beijing, China", "street_adddress": "Beijing, China", "lat": "39.90419990", "lng": "116.40739630", "type": "edu", "country": "China"}, {"name": "Lehigh University", "source_name": "Lehigh University", "street_adddress": "Lehigh University, Library Drive, Sayre Park, Bethlehem, Northampton County, Pennsylvania, 18015, USA", "lat": "40.60680280", "lng": "-75.37824880", "type": "edu", "country": "United States"}, {"name": "Tencent", "source_name": "Tencent", "street_adddress": "Ke Ji Zhong Yi Lu, Nanshan Qu, Shenzhen Shi, Guangdong Sheng, China, 518057", "lat": "22.54471540", "lng": "113.93571640", "type": "company", "country": "United States"}], "year": "2016", "pdf": ["http://cg.cs.tsinghua.edu.cn/traffic-sign/0682.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Zhu_Traffic-Sign_Detection_and_CVPR_2016_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780601", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.232", "http://doi.org/10.1109/CVPR.2016.232"]}, {"id": "012876a5f45da258675add1614ad7608a210141a", "title": "What are the Visual Features Underlying Human Versus Machine Vision?", "addresses": [{"name": "Brown University", "source_name": "Brown University", "street_adddress": "Brown University, Waterman Street, College Hill, Providence, Bristol, Rhode Island, 02912, USA", "lat": "41.82686820", "lng": "-71.40123146", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1701.02704.pdf"], "doi": []}, {"id": "c5f6ed9efc222fe2773135ffb4e5c567d98e64ea", "title": "Image Captioning with Word Level Attention", "addresses": [{"name": "Tongji University", "source_name": "Tongji University", "street_adddress": "\u540c\u6d4e\u5927\u5b66, 1239, \u56db\u5e73\u8def, \u6c5f\u6e7e, \u8679\u53e3\u533a, \u4e0a\u6d77\u5e02, 200092, \u4e2d\u56fd", "lat": "31.28473925", "lng": "121.49694909", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8451558", "http://doi.org/10.1109/ICIP.2018.8451558"]}, {"id": "bb4650130c460f413e97b0328624a485bf094967", "title": "Dynamic Lexicon Generation for Natural Scene Images", "addresses": [{"name": "IIIT Hyderabad", "source_name": "CVIT, IIIT Hyderabad", "street_adddress": "IIIT, Gachibowli, Gachibowli, Hyderabad, Telangana 500032, India", "lat": "17.44509810", "lng": "78.34976780", "type": "edu", "country": "India"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/bb46/50130c460f413e97b0328624a485bf094967.pdf"], "doi": []}, {"id": "2f0486b7770c0a8d9cd37e0d73ea3495562511f3", "title": "Extreme Clicking for Efficient Object Annotation", "addresses": [{"name": "University of Edinburgh", "source_name": "University of Edinburgh", "street_adddress": "New College, New College Courtyard, The Mound, Old Town, Edinburgh, City of Edinburgh, Scotland, EH1 2LX, UK", "lat": "55.94951105", "lng": "-3.19534913", "type": "edu", "country": "United Kingdom"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.02750.pdf"], "doi": []}, {"id": "43cb50f669a0d492256d11c6cc4128ba0ce79a3e", "title": "Per-Pixel Feedback for improving Semantic Segmentation", "addresses": [{"name": "Indian Institute of Technology Roorkee", "source_name": "Indian Institute of Technology, Roorkee", "street_adddress": "Indian Institute of Technology (IIT), Roorkee, LBS Jogging Track, Roorkee, Haridwar, Uttarakhand, 247667, India", "lat": "29.86624610", "lng": "77.89587081", "type": "edu", "country": "India"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1712.02861.pdf"], "doi": []}, {"id": "e7928bd33d09fd00a588617736b102063ca9d070", "title": "A Non-Technical Survey on Deep Convolutional Neural Network Architectures", "addresses": [{"name": "Technical University of Munich", "source_name": "Computer Aided Medical Procedures, Technical University of Munich, Garching, Germany", "street_adddress": "Boltzmannstra\u00dfe 3, 85748 Garching bei M\u00fcnchen, Germany", "lat": "48.26301100", "lng": "11.66685700", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.02129.pdf"], "doi": []}, {"id": "ab6c09ee2e466ceef2492f16472aeb76cd34009a", "title": "Data Augmentation for Cnn-Based People Detection in Aerial Images", "addresses": [{"name": "National Chiao Tung University", "source_name": "National Chiao Tung University", "street_adddress": "NCTU;\u4ea4\u5927;\u4ea4\u901a\u5927\u5b78;\u4ea4\u5927\u5149\u5fa9\u6821\u5340;\u4ea4\u901a\u5927\u5b78\u5149\u5fa9\u6821\u5340, 1001, \u5927\u5b78\u8def, \u5149\u660e\u91cc, \u8d64\u571f\u5d0e, \u6771\u5340, \u65b0\u7af9\u5e02, 30010, \u81fa\u7063", "lat": "24.78676765", "lng": "120.99724412", "type": "edu", "country": "Taiwan"}, {"name": "Feng Chia University", "source_name": "Feng Chia University", "street_adddress": "\u9022\u7532\u5927\u5b78, 100, \u6587\u83ef\u8def, \u897f\u5e73\u91cc, \u897f\u5c6f\u5340, \u81fa\u4e2d\u5e02, 40724, \u81fa\u7063", "lat": "24.18005755", "lng": "120.64836072", "type": "edu", "country": "Taiwan"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8551501", "http://doi.ieeecomputersociety.org/10.1109/ICMEW.2018.8551501", "http://doi.org/10.1109/ICMEW.2018.8551501"]}, {"id": "b1f9657ad8033bca6f25a7aef019a1cb45b75ce2", "title": "High performance and fast object detection in road environments", "addresses": [{"name": "DGIST", "source_name": "DGIST", "street_adddress": "South Korea, Daegu, Dalseong-gun, Yuga-myeon, \ud14c\ud06c\ub178\uc911\uc559\ub300\ub85c 333", "lat": "35.70528600", "lng": "128.45710200", "type": "edu", "country": "South Korea"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8310148", "http://doi.org/10.1109/IPTA.2017.8310148"]}, {"id": "51c765b8d872c206f6dd781ab26bd5a8c2feb81e", "title": "Semantic Image Segmentation via Deep Parsing Network", "addresses": [{"name": "Chinese University of Hong Kong", "source_name": "Chinese University of Hong Kong", "street_adddress": "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "lat": "22.41626320", "lng": "114.21093180", "type": "edu", "country": "China"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1509.02634.pdf"], "doi": []}, {"id": "3fde03e7479f2fbff16f7849a2d038dbd29b1762", "title": "SAVOIAS: A Diverse, Multi-Category Visual Complexity Dataset", "addresses": [{"name": "Boston University", "source_name": "Boston University", "street_adddress": "BU, Bay State Road, Fenway, Boston, Suffolk County, Massachusetts, 02215, USA", "lat": "42.35042530", "lng": "-71.10056114", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.01771.pdf"], "doi": []}, {"id": "2fa45a5b0421578a9a0d5124678dafc689e2bf82", "title": "Fake Sentence Detection as a Training Task for Sentence Encoding", "addresses": [{"name": "Stony Brook University", "source_name": "Stony Brook University", "street_adddress": "Stony Brook University, 100, Nicolls Road, Stony Brook, Suffolk County, New York, 11794, USA", "lat": "40.91531960", "lng": "-73.12706260", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.03840.pdf"], "doi": []}, {"id": "059582bee125512b127296364e7700ebd9f80436", "title": "Action-driven 3D indoor scene evolution", "addresses": [{"name": "Simon Fraser University", "source_name": "Simon Fraser University", "street_adddress": "SFU Burnaby, South Campus Road, Barnet, Burnaby, Metro Vancouver, British Columbia, V5A 4X6, Canada", "lat": "49.27674540", "lng": "-122.91777375", "type": "edu", "country": "Canada"}, {"name": "Shandong University", "source_name": "Shandong University", "street_adddress": "\u5c71\u4e1c\u5927\u5b66, \u6cf0\u5b89\u8857, \u9ccc\u5c71\u536b\u8857\u9053, \u5373\u58a8\u533a, \u9752\u5c9b\u5e02, \u5c71\u4e1c\u7701, 266200, \u4e2d\u56fd", "lat": "36.36934730", "lng": "120.67381800", "type": "edu", "country": "China"}, {"name": "Zhejiang University", "source_name": "Zhejiang University", "street_adddress": "\u6d59\u6c5f\u5927\u5b66\u4e4b\u6c5f\u6821\u533a, \u4e4b\u6c5f\u8def, \u8f6c\u5858\u8857\u9053, \u897f\u6e56\u533a (Xihu), \u676d\u5dde\u5e02 Hangzhou, \u6d59\u6c5f\u7701, 310008, \u4e2d\u56fd", "lat": "30.19331415", "lng": "120.11930822", "type": "edu", "country": "China"}, {"name": "Microsoft", "source_name": "Microsoft Corporation, Redmond, WA, USA", "street_adddress": "One Microsoft Way, Redmond, WA 98052, USA", "lat": "47.64233180", "lng": "-122.13693020", "type": "company", "country": "United States"}], "year": "2016", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=2980223"]}, {"id": "c580b0a8dc655a8831ddbb7954bb929b1f236ebc", "title": "Looking deeper and transferring attention for image captioning", "addresses": [{"name": "Tongji University", "source_name": "Tongji University", "street_adddress": "\u540c\u6d4e\u5927\u5b66, 1239, \u56db\u5e73\u8def, \u6c5f\u6e7e, \u8679\u53e3\u533a, \u4e0a\u6d77\u5e02, 200092, \u4e2d\u56fd", "lat": "31.28473925", "lng": "121.49694909", "type": "edu", "country": "China"}, {"name": "Shanghai Engineering Research Center of Industrial Vision Perception & Intelligent Computing, Shanghai, China", "source_name": "Shanghai Engineering Research Center of Industrial Vision Perception & Intelligent Computing, Shanghai, China", "street_adddress": "Shanghai, China", "lat": "31.23039040", "lng": "121.47370210", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://doi.org/10.1007/s11042-018-6228-6"]}, {"id": "537afabc561a2efa79a903f4859ca63e6592f340", "title": "Algorithms for Semantic Segmentation of Multispectral Remote Sensing Imagery using Deep Learning", "addresses": [{"name": "Rochester Institute of Technology", "source_name": "Rochester Institute of Technology", "street_adddress": "Rochester Institute of Technology (RIT), 1, Lomb Memorial Drive, Bailey, Henrietta Town, Monroe County, New York, 14623, USA", "lat": "43.08250655", "lng": "-77.67121663", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.06452.pdf"], "doi": []}, {"id": "ccd3dcbccae7d903608530bddf6381db8e723a7d", "title": "Unsupervised Domain Adaptation for Semantic Segmentation with GANs", "addresses": [{"name": "University of Maryland", "source_name": "University of Maryland", "street_adddress": "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu", "country": "United States"}, {"name": "GE Global Research", "source_name": "General Electric Global Research, Niskayuna, NY, USA", "street_adddress": "1 Research Cir, Niskayuna, NY 12309, USA", "lat": "42.82715560", "lng": "-73.87804810", "type": "company", "country": "United States"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/ccd3/dcbccae7d903608530bddf6381db8e723a7d.pdf"], "doi": []}, {"id": "dec7bbc3e9eeb940c47214d6ea61e14945ab6e7c", "title": "Prototype GOD: prototype Generic Objects Dataset for an Object Detection System based on Bird\u2019s \u2013Eye View", "addresses": [{"name": "Electronics and Telecommunications Research Institute, Korea", "source_name": "Electronics and Telecommunications Research Institute, Korea", "street_adddress": "1110-6 Oryong-dong, Buk-gu, Kwangju, South Korea", "lat": "35.22537080", "lng": "126.84618340", "type": "edu", "country": "South Korea"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8539407", "http://doi.org/10.1109/ICTC.2018.8539407"]}, {"id": "52d9ad99874f6b76184ad9abe45e824a6568617b", "title": "Large-Scale Active Learning with Approximations of Expected Model Output Changes", "addresses": [{"name": "Friedrich Schiller University Jena", "source_name": "Computer Vision Group, Friedrich Schiller University Jena, Germany", "street_adddress": "Ernst-Abbe-Platz 2, 07743 Jena, Germany", "lat": "50.92776710", "lng": "11.58217290", "type": "edu", "country": "Germany"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/52d9/ad99874f6b76184ad9abe45e824a6568617b.pdf"], "doi": []}, {"id": "1eb4ea011a3122dc7ef3447e10c1dad5b69b0642", "title": "Contextual Visual Recognition from Images and Videos", "addresses": [{"name": "University of California at Berkeley", "source_name": "International Computer Science Institute, University of California at Berkeley, Berkeley, USA", "street_adddress": "1947 Center St, Berkeley, CA 94704, USA", "lat": "37.87015430", "lng": "-122.27123120", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/1eb4/ea011a3122dc7ef3447e10c1dad5b69b0642.pdf"], "doi": []}, {"id": "c5cfeac36fd9fc35de7752cd2c63939920eb1eb3", "title": "Dictionary-Guided Editing Networks for Paraphrase Generation", "addresses": [{"name": "Microsoft Research Asia", "source_name": "Microsoft Research Asia", "street_adddress": "1 Memorial Dr, Cambridge, MA 02142, USA", "lat": "42.36142560", "lng": "-71.08120920", "type": "company", "country": "United States"}, {"name": "Beihang University", "source_name": "Beihang University", "street_adddress": "\u5317\u4eac\u822a\u7a7a\u822a\u5929\u5927\u5b66, 37, \u5b66\u9662\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100083, \u4e2d\u56fd", "lat": "39.98083330", "lng": "116.34101249", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.08077.pdf"], "doi": []}, {"id": "72ff1a1dd7c24b51d40d2be7f337b9075bbb8d58", "title": "Where and Who? Automatic Semantic-Aware Person Composition", "addresses": [{"name": "University of Virginia", "source_name": "University of Virginia", "street_adddress": "University of Virginia, Rotunda Alley, Carr's Hill, Albemarle County, Virginia, 22904-4119, USA", "lat": "38.03536820", "lng": "-78.50353220", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1706.01021.pdf"], "doi": []}, {"id": "a32878e85941b5392d58d28e5248f94e16e25d78", "title": "Quality Classified Image Analysis with Application to Face Detection and Recognition", "addresses": [{"name": "University of Nottingham Ningbo China", "source_name": "University of Nottingham Ningbo China", "street_adddress": "199 Taikang E Rd, Yinzhou Qu, Ningbo Shi, Zhejiang Sheng, China, 315000", "lat": "29.80344900", "lng": "121.56160900", "type": "edu", "country": "China"}, {"name": "Shenzhen University", "source_name": "Shenzhen University", "street_adddress": "\u6df1\u5733\u5927\u5b66, 3688, \u5357\u6d77\u5927\u9053, \u86c7\u53e3, \u540c\u4e50\u6751, \u5357\u5c71\u533a, \u6df1\u5733\u5e02, \u5e7f\u4e1c\u7701, 518060, \u4e2d\u56fd", "lat": "22.53521465", "lng": "113.93159110", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1801.06445.pdf"], "doi": []}, {"id": "3244699e06b145ffa65d0fbddb2ce6e5da889418", "title": "Do You See What I Mean? Visual Resolution of Linguistic Ambiguities", "addresses": [{"name": "Weizmann Institute of Science", "source_name": "Weizmann Institute of Science", "street_adddress": "\u05de\u05db\u05d5\u05df \u05d5\u05d9\u05e6\u05de\u05df \u05dc\u05de\u05d3\u05e2, \u05e9\u05d3\u05e8\u05ea \u05de\u05e8\u05db\u05d5\u05e1 \u05d6\u05d9\u05d5, \u05de\u05e2\u05d5\u05e0\u05d5\u05ea \u05e9\u05d9\u05d9\u05df, \u05d0\u05d7\u05d5\u05d6\u05d5\u05ea \u05d4\u05e0\u05e9\u05d9\u05d0, \u05e8\u05d7\u05d5\u05d1\u05d5\u05ea, \u05de\u05d7\u05d5\u05d6 \u05d4\u05de\u05e8\u05db\u05d6, NO, \u05d9\u05e9\u05e8\u05d0\u05dc", "lat": "31.90784990", "lng": "34.81334092", "type": "edu", "country": "Israel"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1603.08079.pdf"], "doi": []}, {"id": "9e64582b644481a734b018304a22b536886ed024", "title": "ALFA: Agglomerative Late Fusion Algorithm for Object Detection", "addresses": [{"name": "Czech Technical University", "source_name": "Czech Technical University", "street_adddress": "\u010cesk\u00e9 vysok\u00e9 u\u010den\u00ed technick\u00e9 v Praze, Resslova, Nov\u00e9 M\u011bsto, Praha, okres Hlavn\u00ed m\u011bsto Praha, Hlavn\u00ed m\u011bsto Praha, Praha, 11121, \u010cesko", "lat": "50.07642960", "lng": "14.41802312", "type": "edu", "country": "Czech Republic"}, {"name": "Kazan Federal University", "source_name": "Institute of Computational Mathematics and Information Technologies, Kazan Federal University, Russia", "street_adddress": "Kremlyovskaya St, 18, Kazan, Respublika Tatarstan, Russia, 420008", "lat": "55.79044700", "lng": "49.12143490", "type": "edu", "country": "Russia"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8545182", "http://doi.ieeecomputersociety.org/10.1109/ICPR.2018.8545182", "http://doi.org/10.1109/ICPR.2018.8545182"]}, {"id": "c85340a0d428ff0b47f1a4d92fc92157cb7664f0", "title": "Multi-Label Music Genre Classification from Audio, Text and Images Using Deep Features", "addresses": [{"name": "Universitat Pompeu Fabra", "source_name": "Universitat Pompeu Fabra", "street_adddress": "Dip\u00f2sit de les Aig\u00fces, Carrer de Wellington, la Vila Ol\u00edmpica del Poblenou, Ciutat Vella, Barcelona, BCN, CAT, 08071, Espa\u00f1a", "lat": "41.39044285", "lng": "2.18891949", "type": "edu", "country": "Spain"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.04916.pdf"], "doi": []}, {"id": "511fad07b943f088e487ea09ffc6c89114bb3c3e", "title": "Towards an Integrated Method of Detection and Description for Face Authentication System", "addresses": [{"name": "University of Ulsan", "source_name": "University of Ulsan, Korea", "street_adddress": "93 Daehak-ro, Mugeo-dong, Nam-gu, Ulsan, South Korea", "lat": "35.54374110", "lng": "129.25628430", "type": "edu", "country": "South Korea"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8430774", "http://doi.org/10.1109/HSI.2018.8430774"]}, {"id": "6bd1f2782d6c8c3066d4e7d7e3afb995d79fa3dd", "title": "Deep Neural Networks for Semantic Segmentation of Multispectral Remote Sensing Imagery", "addresses": [{"name": "Rochester Institute of Technology", "source_name": "Rochester Institute of Technology", "street_adddress": "Rochester Institute of Technology (RIT), 1, Lomb Memorial Drive, Bailey, Henrietta Town, Monroe County, New York, 14623, USA", "lat": "43.08250655", "lng": "-77.67121663", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/6bd1/f2782d6c8c3066d4e7d7e3afb995d79fa3dd.pdf"], "doi": []}, {"id": "d09a3ec68311af4ebd3cbf7ed906aadffa94a464", "title": "Pedestrian Detection by Feature Selected Self-Similarity Features", "addresses": [{"name": "Shanghai Jiao Tong University", "source_name": "Shanghai Jiao Tong University", "street_adddress": "\u4e0a\u6d77\u4ea4\u901a\u5927\u5b66\uff08\u5f90\u6c47\u6821\u533a\uff09, \u6dee\u6d77\u897f\u8def, \u756a\u79ba\u5c0f\u533a, \u5e73\u9634\u6865, \u5f90\u6c47\u533a, \u4e0a\u6d77\u5e02, 200052, \u4e2d\u56fd", "lat": "31.20081505", "lng": "121.42840681", "type": "edu", "country": "China"}, {"name": "University College London", "source_name": "University College London", "street_adddress": "UCL Institute of Education, 20, Bedford Way, Holborn, Bloomsbury, London Borough of Camden, London, Greater London, England, WC1H 0AL, UK", "lat": "51.52316070", "lng": "-0.12820370", "type": "edu", "country": "United Kingdom"}, {"name": "Sichuan Open University", "source_name": "Engineering and Technology College, Sichuan Open University, Chengdu, China", "street_adddress": "\u4e00 Baiye Rd, Pixian, Chengdu Shi, Sichuan Sheng, China", "lat": "30.72886200", "lng": "103.96638100", "type": "edu", "country": "China"}, {"name": "University of Electronic Science and Technology of China", "source_name": "University of Electronic Science and Technology of China", "street_adddress": "2 Jianshe North Rd 2nd Section, Jianshe Road, Chenghua Qu, Chengdu Shi, Sichuan Sheng, China, 610054", "lat": "30.67272100", "lng": "104.09880600", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8286891", "http://doi.org/10.1109/ACCESS.2018.2803160"]}, {"id": "e096003fc0dad2a09334044ebcc01601fdc0afd6", "title": "Subitizing with Variational Autoencoders", "addresses": [{"name": "University of Amsterdam", "source_name": "University of Amsterdam", "street_adddress": "Institute for Logic, Language and Computation (ILLC), 107, Science Park, Oost-Watergraafsmeer, Amsterdam, Oost, Amsterdam, Noord-Holland, Nederland, 1098XG, Nederland", "lat": "52.35536550", "lng": "4.95016440", "type": "edu", "country": "Netherlands"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.00257.pdf"], "doi": []}, {"id": "43c5be1f64e0135fb3d6e43a9c33caaaa58f7213", "title": "The Emotional Impact of Audio-Visual Stimuli", "addresses": [{"name": "Rochester Institute of Technology", "source_name": "Rochester Institute of Technology", "street_adddress": "Rochester Institute of Technology (RIT), 1, Lomb Memorial Drive, Bailey, Henrietta Town, Monroe County, New York, 14623, USA", "lat": "43.08250655", "lng": "-77.67121663", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/43c5/be1f64e0135fb3d6e43a9c33caaaa58f7213.pdf"], "doi": []}, {"id": "80fc9efde5bb28550d17363d882fd5bc6d805c26", "title": "Question Type Guided Attention in Visual Question Answering", "addresses": [{"name": "University of California, Irvine", "source_name": "University of California, Irvine", "street_adddress": "Irvine, CA 92697, USA", "lat": "33.64049520", "lng": "-117.84429620", "type": "edu", "country": "United States"}, {"name": "University of Southern California", "source_name": "University of Southern California", "street_adddress": "University of Southern California, Watt Way, Saint James Park, LA, Los Angeles County, California, 90089, USA", "lat": "34.02241490", "lng": "-118.28634407", "type": "edu", "country": "United States"}, {"name": "California Institute of Technology", "source_name": "California Institute of Technology", "street_adddress": "California Institute of Technology, San Pasqual Walk, Madison Heights, Pasadena, Los Angeles County, California, 91126, USA", "lat": "34.13710185", "lng": "-118.12527487", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.02088.pdf"], "doi": []}, {"id": "4a9d906935c9de019c61aedc10b77ee10e3aec63", "title": "Cross Modal Distillation for Supervision Transfer", "addresses": [{"name": "University of California, Berkeley", "source_name": "University of California, Berkeley", "street_adddress": "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "lat": "37.86871260", "lng": "-122.25586815", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1507.00448.pdf"], "doi": []}, {"id": "350af77e01e78e8e3534f42b80b5dd35a602e73c", "title": "Hierarchical Recurrent Neural Encoder for Video Representation with Application to Captioning", "addresses": [{"name": "University of Technology Sydney", "source_name": "University of Technology Sydney", "street_adddress": "University of Technology Sydney, Omnibus Lane, Ultimo, Sydney, NSW, 2007, Australia", "lat": "-33.88096510", "lng": "151.20107299", "type": "edu", "country": "Australia"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1511.03476.pdf"], "doi": []}, {"id": "db0a4af734dab1854c2e8dfe499fe0e353226e45", "title": "Hot Anchors: A Heuristic Anchors Sampling Method in RCNN-Based Object Detection", "addresses": [{"name": "Chinese Academy of Sciences", "source_name": "Chinese Academy of Sciences", "street_adddress": "\u4e2d\u56fd\u79d1\u5b66\u9662\u5fc3\u7406\u7814\u7a76\u6240, 16, \u6797\u8403\u8def, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100101, \u4e2d\u56fd", "lat": "40.00447950", "lng": "116.37023800", "type": "edu", "country": "China"}, {"name": "University of Chinese Academy of Sciences", "source_name": "University of Chinese Academy of Sciences", "street_adddress": "University of Chinese Academy of Sciences, UCAS, Yuquanlu, \u7389\u6cc9\u8def, \u7530\u6751, \u6d77\u6dc0\u533a, 100049, \u4e2d\u56fd", "lat": "39.90828040", "lng": "116.24585270", "type": "edu", "country": "China"}, {"name": "Xi\u2019an Jiaotong University", "source_name": "Institute of Information and System Sciences, Faculty of Mathematics and Statistics, Xi\u2019an Jiaotong University, Xi\u2019an, China", "street_adddress": "28 Xianning W Rd, JiaoDa ShangYe JieQu, Beilin Qu, Xian Shi, Shaanxi Sheng, China", "lat": "34.25080300", "lng": "108.98369300", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/db0a/4af734dab1854c2e8dfe499fe0e353226e45.pdf"], "doi": []}, {"id": "0171bdeb1c6e333287be655c667cfba5edb89b76", "title": "Aggregated Residual Transformations for Deep Neural Networks", "addresses": [{"name": "UC San Diego", "source_name": "UC San Diego", "street_adddress": "9500 Gilman Dr, La Jolla, CA 92093, USA", "lat": "32.88006040", "lng": "-117.23401350", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1611.05431.pdf"], "doi": []}, {"id": "6759fd391e3f8a1aea7673d617d3e1b04d069804", "title": "Pose Flow: Efficient Online Pose Tracking", "addresses": [{"name": "Shanghai Jiao Tong University", "source_name": "Shanghai Jiao Tong University", "street_adddress": "\u4e0a\u6d77\u4ea4\u901a\u5927\u5b66\uff08\u5f90\u6c47\u6821\u533a\uff09, \u6dee\u6d77\u897f\u8def, \u756a\u79ba\u5c0f\u533a, \u5e73\u9634\u6865, \u5f90\u6c47\u533a, \u4e0a\u6d77\u5e02, 200052, \u4e2d\u56fd", "lat": "31.20081505", "lng": "121.42840681", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.00977.pdf"], "doi": []}, {"id": "fa93e027e795e98405dc72f123aadebafc5d80d8", "title": "Explaining the Ambiguity of Object Detection and 6D Pose from Visual Data", "addresses": [{"name": "TU Munich", "source_name": "Faculty of Electrical Engineering and Information Technology, Technische Universit\u00e4t M\u00fcnchen, 85290, Germany", "street_adddress": "Mies-van-der-Rohe-Stra\u00dfe 15, 52074 Aachen, Germany", "lat": "50.77892190", "lng": "6.06563870", "type": "edu", "country": "Germany"}, {"name": "University of Oxford", "source_name": "University of Oxford", "street_adddress": "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "lat": "51.75345380", "lng": "-1.25400997", "type": "edu", "country": "United Kingdom"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.00287.pdf"], "doi": []}, {"id": "5fa04523ff13a82b8b6612250a39e1edb5066521", "title": "Dockerface: an easy to install and use Faster R-CNN face detector in a Docker container", "addresses": [{"name": "Georgia Institute of Technology", "source_name": "Georgia Institute of Technology", "street_adddress": "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.04370.pdf"], "doi": []}, {"id": "4443d51f54a9df679efc5ae65115f60f8e58a1a0", "title": "Spott: On-the-Spot e-Commerce for Television Using Deep Learning-Based Video Analysis Techniques", "addresses": [{"name": "Ghent University - imec - MICT", "source_name": "Ghent University - imec - MICT, Korte Meer, Ghent", "street_adddress": "Miriam Makebaplein 1, 9000 Gent, Belgium", "lat": "51.04893030", "lng": "3.72886530", "type": "edu", "country": "Belgium"}, {"name": "Ghent University", "source_name": "Ghent University", "street_adddress": "St. Pietersnieuwstraat 33, 9000 Gent, Belgium", "lat": "51.04656190", "lng": "3.72791810", "type": "edu", "country": "Belgium"}], "year": "2017", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3092834"]}, {"id": "a8fd9be2f7775b123f62094eadd59d18bbbef027", "title": "Peephole: Predicting Network Performance Before Training", "addresses": [{"name": "Beihang University", "source_name": "Beihang University", "street_adddress": "\u5317\u4eac\u822a\u7a7a\u822a\u5929\u5927\u5b66, 37, \u5b66\u9662\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100083, \u4e2d\u56fd", "lat": "39.98083330", "lng": "116.34101249", "type": "edu", "country": "China"}, {"name": "SenseTime", "source_name": "SenseTime", "street_adddress": "China, Beijing Shi, Haidian Qu, WuDaoKou, Zhongguancun E Rd, 1\u53f7-7", "lat": "39.99300800", "lng": "116.32988200", "type": "company", "country": "China"}, {"name": "Chinese University of Hong Kong", "source_name": "Chinese University of Hong Kong", "street_adddress": "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "lat": "22.41626320", "lng": "114.21093180", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1712.03351.pdf"], "doi": []}, {"id": "812e11fc86e5d183337257978e5a0f26b5668218", "title": "Evaluating ResNeXt Model Architecture for Image Classification", "addresses": [{"name": "University of Waterloo", "source_name": "University of Waterloo", "street_adddress": "University of Waterloo, 200, University Avenue West, Northdale, Beechwood, Waterloo, Regional Municipality of Waterloo, Ontario, N2L 3G1, Canada", "lat": "43.47061295", "lng": "-80.54724732", "type": "edu", "country": "Canada"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.08700.pdf"], "doi": []}, {"id": "a71b99357b0952858f98867ed0cbc87738899e1a", "title": "ScratchDet : Training Single-Shot Object Detectors from Scratch", "addresses": [{"name": "University of Chinese Academy of Sciences", "source_name": "University of Chinese Academy of Sciences", "street_adddress": "University of Chinese Academy of Sciences, UCAS, Yuquanlu, \u7389\u6cc9\u8def, \u7530\u6751, \u6d77\u6dc0\u533a, 100049, \u4e2d\u56fd", "lat": "39.90828040", "lng": "116.24585270", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/a71b/99357b0952858f98867ed0cbc87738899e1a.pdf"], "doi": []}, {"id": "faa3b7034b89c9ab7ca5360a14311f2fd36ef7b9", "title": "AutoFocus: Efficient Multi-Scale Inference", "addresses": [{"name": "University of Maryland", "source_name": "University of Maryland", "street_adddress": "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.01600.pdf"], "doi": []}, {"id": "044e0d86e2db70d4c0b767bf0994913e90e105e3", "title": "Answer-Type Prediction for Visual Question Answering", "addresses": [{"name": "Rochester Institute of Technology", "source_name": "Rochester Institute of Technology", "street_adddress": "Rochester Institute of Technology (RIT), 1, Lomb Memorial Drive, Bailey, Henrietta Town, Monroe County, New York, 14623, USA", "lat": "43.08250655", "lng": "-77.67121663", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2016/papers/Kafle_Answer-Type_Prediction_for_CVPR_2016_paper.pdf", "http://www.chriskanan.com/wp-content/uploads/Kafle2016.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Kafle_Answer-Type_Prediction_for_CVPR_2016_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780907", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.538", "http://doi.org/10.1109/CVPR.2016.538", "http://scholarworks.rit.edu/cgi/viewcontent.cgi?article=1919&context=other"]}, {"id": "d5873c4f169227ab002366db3b55d1fede9f473f", "title": "Multi-modal deep feature learning for RGB-D object detection", "addresses": [{"name": "Nanjing University", "source_name": "Nanjing University", "street_adddress": "NJU, \u4e09\u6c5f\u8def, \u9f13\u697c\u533a, \u5357\u4eac\u5e02, \u6c5f\u82cf\u7701, 210093, \u4e2d\u56fd", "lat": "32.05659570", "lng": "118.77408833", "type": "edu", "country": "China"}, {"name": "University of Rochester", "source_name": "University of Rochester", "street_adddress": "Memorial Art Gallery, 500, University Avenue, East End, Rochester, Monroe County, New York, 14607, USA", "lat": "43.15769690", "lng": "-77.58829158", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["http://mcg.nju.edu.cn/publication/2017/xiangyang-2017.pdf"], "doi": ["http://doi.org/10.1016/j.patcog.2017.07.026"]}, {"id": "a89e1fc2681a9a399cc5008ea34b5ec3fe7ca845", "title": "Improving Fast Segmentation With Teacher-Student Learning", "addresses": [{"name": "Sun Yat-Sen University", "source_name": "Sun Yat-Sen University", "street_adddress": "\u4e2d\u5927, \u65b0\u6e2f\u897f\u8def, \u9f99\u8239\u6ed8, \u5eb7\u4e50, \u6d77\u73e0\u533a (Haizhu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510105, \u4e2d\u56fd", "lat": "23.09461185", "lng": "113.28788994", "type": "edu", "country": "China"}, {"name": "Nanyang Technological University", "source_name": "Nanyang Technological University", "street_adddress": "NTU, Faculty Avenue, Jurong West, Southwest, 637460, Singapore", "lat": "1.34841040", "lng": "103.68297965", "type": "edu", "country": "Singapore"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.08476.pdf"], "doi": []}, {"id": "55af092ce75ade8a26d2afe97d57de2191d44b5f", "title": "Unsupervised Ensemble Regression", "addresses": [{"name": "Weizmann Institute of Science", "source_name": "Weizmann Institute of Science", "street_adddress": "\u05de\u05db\u05d5\u05df \u05d5\u05d9\u05e6\u05de\u05df \u05dc\u05de\u05d3\u05e2, \u05e9\u05d3\u05e8\u05ea \u05de\u05e8\u05db\u05d5\u05e1 \u05d6\u05d9\u05d5, \u05de\u05e2\u05d5\u05e0\u05d5\u05ea \u05e9\u05d9\u05d9\u05df, \u05d0\u05d7\u05d5\u05d6\u05d5\u05ea \u05d4\u05e0\u05e9\u05d9\u05d0, \u05e8\u05d7\u05d5\u05d1\u05d5\u05ea, \u05de\u05d7\u05d5\u05d6 \u05d4\u05de\u05e8\u05db\u05d6, NO, \u05d9\u05e9\u05e8\u05d0\u05dc", "lat": "31.90784990", "lng": "34.81334092", "type": "edu", "country": "Israel"}, {"name": "IBM T.J. Watson Research Center", "source_name": "IBM T. J. Watson Research, Center, New York, USA", "street_adddress": "1101 Kitchawan Rd, Yorktown Heights, NY 10598, USA", "lat": "41.20975160", "lng": "-73.80264670", "type": "company", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.02965.pdf"], "doi": []}, {"id": "5f94969b9491db552ffebc5911a45def99026afe", "title": "Multimodal Learning and Reasoning for Visual Question Answering", "addresses": [{"name": "National University of Singapore", "source_name": "National University of Singapore", "street_adddress": "NUS, Former 1936 British Outpost, Nepal Hill, Clementi, Southwest, 117542, Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu", "country": "Singapore"}, {"name": "Electrical and Computer Engineering", "source_name": "Electrical and Computer Engineering", "street_adddress": "Electrical and Computer Engineering, Boston Avenue, South Overton, Lubbock, Lubbock County, Texas, 79409, USA", "lat": "33.58667840", "lng": "-101.87539204", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/5f94/969b9491db552ffebc5911a45def99026afe.pdf"], "doi": []}, {"id": "91a972eadf78f44bdc03cc5ebe27899091bc94e1", "title": "AutoMarkov DNNs for object classification", "addresses": [{"name": "University Politehnica of Bucharest", "source_name": "University Politehnica of Bucharest", "street_adddress": "Universitatea Politehnica din Bucure\u0219ti, Novum Invest, Bucure\u0219ti, Militari, Sector 6, Municipiul Bucure\u0219ti, 060042, Rom\u00e2nia", "lat": "44.43918115", "lng": "26.05044565", "type": "edu", "country": "Romania"}], "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7900168", "http://doi.org/10.1109/ICPR.2016.7900168"]}, {"id": "55d1342900e0abc59495afd44cde0a0052367b42", "title": "Traits & Transferability of Adversarial Examples against Instance Segmentation & Object Detection", "addresses": [{"name": "University of Illinois, Urbana-Champaign", "source_name": "University of Illinois, Urbana-Champaign", "street_adddress": "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.01452.pdf"], "doi": []}, {"id": "267bd60e442d87c44eaae3290610138e63d663ab", "title": "PoseTrack: Joint Multi-person Pose Estimation and Tracking", "addresses": [{"name": "University of Bonn", "source_name": "University of Bonn", "street_adddress": "Rheinische Friedrich-Wilhelms-Universit\u00e4t Bonn, Arkadenhof, Bonn-Zentrum, Stadtbezirk Bonn, Bonn, Regierungsbezirk K\u00f6ln, Nordrhein-Westfalen, 53113, Deutschland", "lat": "50.73381240", "lng": "7.10224650", "type": "edu", "country": "Germany"}, {"name": "University of Adelaide", "source_name": "University of Adelaide", "street_adddress": "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu", "country": "Australia"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1611.07727.pdf"], "doi": []}, {"id": "6583d293734d56c9dd2a34ffa5887c6c323aacf5", "title": "Integrating Local Material Recognition with Large-Scale Perceptual Attribute Discovery", "addresses": [{"name": "Drexel University", "source_name": "Drexel University", "street_adddress": "Drexel University, Arch Street, Powelton Village, Philadelphia, Philadelphia County, Pennsylvania, 19104, USA", "lat": "39.95740000", "lng": "-75.19026706", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1604.01345.pdf"], "doi": []}, {"id": "bfce448a3409d87ba281de53ed696b09119f2ba9", "title": "Object segmentation in depth maps with one user click and a synthetically trained fully convolutional network", "addresses": [{"name": "INRIA", "source_name": "INRIA Grenoble Rhone-Alpes, Grenoble, France", "street_adddress": "655 Avenue de l'Europe, 38330 Montbonnot-Saint-Martin, France", "lat": "45.21788600", "lng": "5.80736900", "type": "edu", "country": "France"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1801.01281.pdf"], "doi": []}, {"id": "66c6aebf10410a11623e32e23295213dfd7c557f", "title": "Fast and Accurate Semantic Mapping through Geometric-based Incremental Segmentation", "addresses": [{"name": "TU Munich", "source_name": "Faculty of Electrical Engineering and Information Technology, Technische Universit\u00e4t M\u00fcnchen, 85290, Germany", "street_adddress": "Mies-van-der-Rohe-Stra\u00dfe 15, 52074 Aachen, Germany", "lat": "50.77892190", "lng": "6.06563870", "type": "edu", "country": "Germany"}, {"name": "Keio University", "source_name": "Keio University", "street_adddress": "\u7db1\u5cf6\u5e02\u6c11\u306e\u68ee, \u3051\u3064\u308f\u308a\u5742, \u6e2f\u5317\u533a, \u6a2a\u6d5c\u5e02, \u795e\u5948\u5ddd\u770c, \u95a2\u6771\u5730\u65b9, 223-0053, \u65e5\u672c", "lat": "35.54169690", "lng": "139.63471840", "type": "edu", "country": "Japan"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8593993"]}, {"id": "267c8798a5c602dae05908b63f031dbdb81fc42b", "title": "Amodal Instance Segmentation", "addresses": [{"name": "University of California, Berkeley", "source_name": "University of California, Berkeley", "street_adddress": "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "lat": "37.86871260", "lng": "-122.25586815", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1604.08202.pdf"], "doi": []}, {"id": "c1d1b1197667facd360196059796ab8cb7b46e96", "title": "PolyMapper: Extracting City Maps using Polygons", "addresses": [{"name": "ETH Z\u00fcrich", "source_name": "ETH Z\u00fcrich", "street_adddress": "ETH Z\u00fcrich, 101, R\u00e4mistrasse, Hochschulen, Altstadt, Z\u00fcrich, Bezirk Z\u00fcrich, Z\u00fcrich, 8092, Schweiz/Suisse/Svizzera/Svizra", "lat": "47.37645340", "lng": "8.54770931", "type": "edu", "country": "Switzerland"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.01497.pdf"], "doi": []}, {"id": "a0a49f50d9b76ad4ba7ce5acd14a3d4b31a520d6", "title": "HiDDeN: Hiding Data With Deep Networks", "addresses": [{"name": "Stanford University", "source_name": "Stanford University", "street_adddress": "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.09937.pdf"], "doi": []}, {"id": "333f083671da1010cbb080c6ce607ed87c19d73d", "title": "Multiple Instance Learning Convolutional Neural Networks for object recognition", "addresses": [{"name": "Electrical and Computer Engineering", "source_name": "Electrical and Computer Engineering", "street_adddress": "Electrical and Computer Engineering, Boston Avenue, South Overton, Lubbock, Lubbock County, Texas, 79409, USA", "lat": "33.58667840", "lng": "-101.87539204", "type": "edu", "country": "United States"}, {"name": "University of Missouri", "source_name": "University of Missouri", "street_adddress": "L1, Maguire Boulevard, Lemone Industrial Park, Columbia, Boone County, Missouri, 65201, USA", "lat": "38.92676100", "lng": "-92.29193783", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1610.03155.pdf"], "doi": []}, {"id": "a2c97ced4981a4505a6aa7f26e1c499df98f525d", "title": "Shape and Pose Estimation for Closely Interacting Persons Using Multi-view Images", "addresses": [{"name": "Tianjin University", "source_name": "Tianjin University", "street_adddress": "\u6cf0\u5c71\u822a\u7a7a\u6e2f/\u5929\u6d25\u5927\u53a6, \u67a3\u884c\u8def, \u67a3\u884c \u9ad8\u738b\u5bfa, \u957f\u57ce\u8def, \u5927\u6cb3, \u5cb1\u5cb3\u533a (Daiyue), \u6cf0\u5b89\u5e02, \u5c71\u4e1c\u7701, 271000, \u4e2d\u56fd", "lat": "36.20304395", "lng": "117.05842113", "type": "edu", "country": "China"}, {"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}, {"name": "Southeast University", "source_name": "Southeast University", "street_adddress": "SEU, \u4f53\u80b2\u9986\u8def, \u65b0\u8857\u53e3, \u6708\u5b63\u56ed, \u7384\u6b66\u533a, \u5357\u4eac\u5e02, \u6c5f\u82cf\u7701, 210008, \u4e2d\u56fd", "lat": "32.05752790", "lng": "118.78682252", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://www.yangangwang.com/papers/LI-SPE-2018-08.pdf"], "doi": ["http://doi.org/10.1111/cgf.13574"]}, {"id": "21819624b83b40586afce41c3c9ae7abf6c9a2ab", "title": "A vision-grounded dataset for predicting typical locations for verbs", "addresses": [{"name": "Max Planck Institute for Informatics", "source_name": "Max Planck Institute for Informatics", "street_adddress": "MPII, E1 4, Campus, Universit\u00e4t, Sankt Johann, Bezirk Mitte, Saarbr\u00fccken, Regionalverband Saarbr\u00fccken, Saarland, 66123, Deutschland", "lat": "49.25795660", "lng": "7.04577417", "type": "edu", "country": "Germany"}, {"name": "Saarland University", "source_name": "Mathematical Image Analysis Group, Faculty of Mathematics and Computer Science, Saarland University, Saarbr\u00fccken, Germany", "street_adddress": "66123 Saarbr\u00fccken, Germany", "lat": "49.25502840", "lng": "7.04097500", "type": "edu", "country": "Germany"}, {"name": "University of California at Berkeley", "source_name": "International Computer Science Institute, University of California at Berkeley, Berkeley, USA", "street_adddress": "1947 Center St, Berkeley, CA 94704, USA", "lat": "37.87015430", "lng": "-122.27123120", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/2181/9624b83b40586afce41c3c9ae7abf6c9a2ab.pdf"], "doi": []}, {"id": "744089e18ef246785cdec2875d2b3872ef1d71b6", "title": "Parallel Attention: A Unified Framework for Visual Object Discovery Through Dialogs and Queries", "addresses": [{"name": "University of Adelaide", "source_name": "University of Adelaide", "street_adddress": "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu", "country": "Australia"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.06370.pdf"], "doi": []}, {"id": "ff772950f66ac6a57f4201ce1f02f0013ccdc1bb", "title": "Receptive Field Block Net for Accurate and Fast Object Detection", "addresses": [{"name": "Beihang University", "source_name": "Beihang University", "street_adddress": "\u5317\u4eac\u822a\u7a7a\u822a\u5929\u5927\u5b66, 37, \u5b66\u9662\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100083, \u4e2d\u56fd", "lat": "39.98083330", "lng": "116.34101249", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.07767.pdf"], "doi": []}, {"id": "658c802890c7133e2ade778b5d88b68bcd0dca9c", "title": "Learning to Segment via Cut-and-Paste", "addresses": [{"name": "Google", "source_name": "Google, Inc.", "street_adddress": "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "lat": "37.42199990", "lng": "-122.08405750", "type": "company", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.06414.pdf"], "doi": []}, {"id": "606cfdcc43203351dbb944a3bb3719695e557e37", "title": "Ex Paucis Plura : Learning Affordance Segmentation from Very Few Examples", "addresses": [{"name": "University of Bonn", "source_name": "University of Bonn", "street_adddress": "Rheinische Friedrich-Wilhelms-Universit\u00e4t Bonn, Arkadenhof, Bonn-Zentrum, Stadtbezirk Bonn, Bonn, Regierungsbezirk K\u00f6ln, Nordrhein-Westfalen, 53113, Deutschland", "lat": "50.73381240", "lng": "7.10224650", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/606c/fdcc43203351dbb944a3bb3719695e557e37.pdf"], "doi": []}, {"id": "1bd9db88bdab930f0dd380942b65c1449383166b", "title": "Robot Classification of Human Interruptibility and a Study of Its Effects", "addresses": [{"name": "Georgia Institute of Technology", "source_name": "Georgia Institute of Technology", "street_adddress": "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu", "country": "United States"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3277902"]}, {"id": "83e5e6fc0f086017b3e099ec063df94f47427d2c", "title": "Fast, Diverse and Accurate Image Captioning Guided By Part-of-Speech", "addresses": [{"name": "University of Illinois, Urbana-Champaign", "source_name": "University of Illinois, Urbana-Champaign", "street_adddress": "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.12589.pdf"], "doi": []}, {"id": "39836fbbcd2a664edb31119e88870c38b83df352", "title": "Adaptively Attending to Visual Attributes and Linguistic Knowledge for Captioning", "addresses": [{"name": "University of Electronic Science and Technology of China", "source_name": "University of Electronic Science and Technology of China", "street_adddress": "2 Jianshe North Rd 2nd Section, Jianshe Road, Chenghua Qu, Chengdu Shi, Sichuan Sheng, China, 610054", "lat": "30.67272100", "lng": "104.09880600", "type": "edu", "country": "China"}, {"name": "University of Queensland", "source_name": "University of Queensland", "street_adddress": "University of Queensland, University Drive, Hill End, St Lucia, Brisbane, QLD, 4072, Australia", "lat": "-27.49741805", "lng": "153.01316956", "type": "edu", "country": "Australia"}], "year": "2017", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3123391"]}, {"id": "c72e6992f44ce75a40f44be4365dc4f264735cfb", "title": "Story Understanding in Video Advertisements", "addresses": [{"name": "University of Pittsburgh", "source_name": "University of Pittsburgh", "street_adddress": "University of Pittsburgh, Sutherland Drive, West Oakland, PGH, Allegheny County, Pennsylvania, 15240, USA", "lat": "40.44415295", "lng": "-79.96243993", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.11122.pdf"], "doi": []}, {"id": "25dba68e4db0ce361032126b91f734f9252cae7c", "title": "DeepSetNet: Predicting Sets with Deep Neural Networks", "addresses": [{"name": "University of Adelaide", "source_name": "University of Adelaide", "street_adddress": "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu", "country": "Australia"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1611.08998.pdf"], "doi": []}, {"id": "3a0f23dcb731762f9cc968d63385183b301eef89", "title": "Towards Segmenting Everything That Moves", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1902.03715.pdf"], "doi": []}, {"id": "8bce31108f598986558e9afb1061eb988ea4f3be", "title": "Automated Image Annotation based on YOLOv3", "addresses": [{"name": "Vilnius Gediminas Technical University", "source_name": "Vilnius Gediminas Technical University, Naugarduko g. 41-413, Vilnius LT-03227, Lithuania", "street_adddress": "Naugarduko g. 41, Vilnius 03227, Lithuania", "lat": "54.67377770", "lng": "25.26622250", "type": "edu", "country": "Lithuania"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8592167"]}, {"id": "fdbe50ca6741ddad66fb289960624627c6869cfc", "title": "Weakly Semi-Supervised Deep Learning for Multi-Label Image Annotation", "addresses": [{"name": "Zhejiang University", "source_name": "Zhejiang University", "street_adddress": "\u6d59\u6c5f\u5927\u5b66\u4e4b\u6c5f\u6821\u533a, \u4e4b\u6c5f\u8def, \u8f6c\u5858\u8857\u9053, \u897f\u6e56\u533a (Xihu), \u676d\u5dde\u5e02 Hangzhou, \u6d59\u6c5f\u7701, 310008, \u4e2d\u56fd", "lat": "30.19331415", "lng": "120.11930822", "type": "edu", "country": "China"}, {"name": "University of Rochester", "source_name": "University of Rochester", "street_adddress": "Memorial Art Gallery, 500, University Avenue, East End, Rochester, Monroe County, New York, 14607, USA", "lat": "43.15769690", "lng": "-77.58829158", "type": "edu", "country": "United States"}, {"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}, {"name": "University of Technology Sydney", "source_name": "University of Technology Sydney", "street_adddress": "University of Technology Sydney, Omnibus Lane, Ultimo, Sydney, NSW, 2007, Australia", "lat": "-33.88096510", "lng": "151.20107299", "type": "edu", "country": "Australia"}], "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7317747"]}, {"id": "1855818c492d5f42dbe14814e4dd9b5733d54790", "title": "Densely Connected Discriminative Correlation Filters for Visual Tracking", "addresses": [{"name": "Shanghai Jiao Tong University", "source_name": "Shanghai Jiao Tong University", "street_adddress": "\u4e0a\u6d77\u4ea4\u901a\u5927\u5b66\uff08\u5f90\u6c47\u6821\u533a\uff09, \u6dee\u6d77\u897f\u8def, \u756a\u79ba\u5c0f\u533a, \u5e73\u9634\u6865, \u5f90\u6c47\u533a, \u4e0a\u6d77\u5e02, 200052, \u4e2d\u56fd", "lat": "31.20081505", "lng": "121.42840681", "type": "edu", "country": "China"}, {"name": "Auckland University of Technology", "source_name": "Computer and Mathematical Sciences, Auckland University of Technology, Auckland, New Zealand", "street_adddress": "31 Symonds St, Auckland, 1010, New Zealand", "lat": "-36.85444260", "lng": "174.76761040", "type": "edu", "country": "New Zealand"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8359334"]}, {"id": "f857cdf601379064bde3d4738f40aed30e266dbf", "title": "Training Very Deep CNNs for General Non-Blind Deconvolution", "addresses": [{"name": "University of Sydney", "source_name": "University of Sydney", "street_adddress": "USyd, Fisher Road, Camperdown, Sydney, NSW, 2006, Australia", "lat": "-33.88890695", "lng": "151.18943366", "type": "edu", "country": "Australia"}, {"name": "Union Visual Innovation Technology Co., Ltd., Shenzhen, China", "source_name": "Union Visual Innovation Technology Co., Ltd., Shenzhen, China", "street_adddress": "Shenzhen, Guangdong, China", "lat": "22.54309600", "lng": "114.05786500", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8315039"]}, {"id": "8d0dffcf36e76ebbb5ff9389750264d9fb77265f", "title": "Comparison of Visual Datasets for Machine Learning", "addresses": [{"name": "Purdue University", "source_name": "Purdue University", "street_adddress": "Purdue University, West Stadium Avenue, West Lafayette, Tippecanoe County, Indiana, 47907, USA", "lat": "40.43197220", "lng": "-86.92389368", "type": "edu", "country": "United States"}, {"name": "University of Miami", "source_name": "University of Miami", "street_adddress": "University of Miami, Theo Dickenson Drive, Coral Gables, Miami-Dade County, Florida, 33124, USA", "lat": "25.71733390", "lng": "-80.27866887", "type": "edu", "country": "United States"}, {"name": "Florida International University", "source_name": "Florida International University", "street_adddress": "FIU, Southwest 14th Street, Sweetwater, University Park, Miami-Dade County, Florida, 33199, USA", "lat": "25.75533775", "lng": "-80.37628897", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["http://rvc.eng.miami.edu/Paper/2017/IRI17_Gauen.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8102956", "http://doi.ieeecomputersociety.org/10.1109/IRI.2017.59", "http://doi.org/10.1109/IRI.2017.59", "http://ecommons.luc.edu/cgi/viewcontent.cgi?article=1148&context=cs_facpubs"]}, {"id": "8c4c723a74fe479c2b8af7d911817377dd6d85c9", "title": "Understanding Neural Networks Through Deep Visualization", "addresses": [{"name": "Cornell University", "source_name": "Cornell University", "street_adddress": "Cornell University, Forest Home Drive, Forest Home, Tompkins County, New York, 14853, USA", "lat": "42.45055070", "lng": "-76.47835130", "type": "edu", "country": "United States"}, {"name": "California Institute of Technology", "source_name": "California Institute of Technology", "street_adddress": "California Institute of Technology, San Pasqual Walk, Madison Heights, Pasadena, Los Angeles County, California, 91126, USA", "lat": "34.13710185", "lng": "-118.12527487", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1506.06579.pdf"], "doi": []}, {"id": "e0c3c1b9744a695cfeab11ceb23069c38844932c", "title": "Non-parametric human segmentation using support vector machine", "addresses": [{"name": "Yonsei University", "source_name": "Yonsei University", "street_adddress": "\uc5f0\uc138\ub300, \uc5f0\uc138\ub85c, \uc2e0\ucd0c\ub3d9, \ucc3d\ucc9c\ub3d9, \uc11c\ub300\ubb38\uad6c, \uc11c\uc6b8\ud2b9\ubcc4\uc2dc, 03789, \ub300\ud55c\ubbfc\uad6d", "lat": "37.56004060", "lng": "126.93692480", "type": "edu", "country": "South Korea"}], "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7430551"]}, {"id": "fe0edc34d9bdf51c1544a3f70e83917e5d917681", "title": "An End-to-End Quadrilateral Regression Network for Comic Panel Extraction", "addresses": [{"name": "Peking University", "source_name": "Peking University", "street_adddress": "\u5317\u4eac\u5927\u5b66, 5\u53f7, \u9890\u548c\u56ed\u8def, \u7a3b\u9999\u56ed\u5357\u793e\u533a, \u6d77\u6dc0\u533a, \u5317\u4eac\u5e02, 100871, \u4e2d\u56fd", "lat": "39.99223790", "lng": "116.30393816", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3240555"]}, {"id": "e431de776590f52a5ae2be2d71900136c91b7136", "title": "Towards a Robust Interactive and Learning Social Robot", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}, {"name": "Karlsruhe Institute of Technology", "source_name": "Karlsruhe Institute of Technology", "street_adddress": "KIT, Leopoldshafener Allee, Linkenheim, Linkenheim-Hochstetten, Landkreis Karlsruhe, Regierungsbezirk Karlsruhe, Baden-W\u00fcrttemberg, 76351, Deutschland", "lat": "49.10184375", "lng": "8.43312560", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/e431/de776590f52a5ae2be2d71900136c91b7136.pdf"], "doi": []}, {"id": "474c8f4e31a51e2cb3c1e9fed83202b4483efb35", "title": "Computer Vision \u2013 ECCV 2018", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}, {"name": "Google Research, Zurich, Switzerland", "source_name": "Google Research, Zurich, Switzerland", "street_adddress": "Brandschenkestrasse 110, 8002 Z\u00fcrich, Switzerland", "lat": "47.36554640", "lng": "8.52483910", "type": "company", "country": "Switzerland"}, {"name": "Hebrew University of Jerusalem", "source_name": "The Hebrew University of Jerusalem", "street_adddress": "\u05d4\u05d0\u05d5\u05e0\u05d9\u05d1\u05e8\u05e1\u05d9\u05d8\u05d4 \u05d4\u05e2\u05d1\u05e8\u05d9\u05ea \u05d1\u05d9\u05e8\u05d5\u05e9\u05dc\u05d9\u05dd, Reagan Plaza, \u05e7\u05e8\u05d9\u05ea \u05de\u05e0\u05d7\u05dd \u05d1\u05d2\u05d9\u05df, \u05d4\u05e8 \u05d4\u05e6\u05d5\u05e4\u05d9\u05dd, \u05d9\u05e8\u05d5\u05e9\u05dc\u05d9\u05dd, \u05de\u05d7\u05d5\u05d6 \u05d9\u05e8\u05d5\u05e9\u05dc\u05d9\u05dd, NO, \u05d9\u05e9\u05e8\u05d0\u05dc", "lat": "31.79185550", "lng": "35.24472300", "type": "edu", "country": "Israel"}], "year": "2018", "pdf": [], "doi": ["http://doi.org/10.1007/978-3-030-01228-1"]}, {"id": "62a6220c8cb5b74e958870e52affd9e7542216fc", "title": "Street object detection / tracking for AI city traffic analysis", "addresses": [{"name": "State University of New York", "source_name": "University at Albany, State University of New York, Albany, USA", "street_adddress": "353 Broadway, Albany, NY 12207, USA", "lat": "42.64805160", "lng": "-73.74957600", "type": "edu", "country": "United States"}, {"name": "University of Chinese Academy of Sciences", "source_name": "University of Chinese Academy of Sciences", "street_adddress": "University of Chinese Academy of Sciences, UCAS, Yuquanlu, \u7389\u6cc9\u8def, \u7530\u6751, \u6d77\u6dc0\u533a, 100049, \u4e2d\u56fd", "lat": "39.90828040", "lng": "116.24585270", "type": "edu", "country": "China"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8397669"]}, {"id": "cdeee5eed68e7c8eb06185f7fcb1a072af784886", "title": "Deep Learning for Object Saliency Detection and Image Segmentation", "addresses": [{"name": "York University", "source_name": "York University", "street_adddress": "York University, Keele Campus, Campus Walk, North York, Toronto, Ontario, M3J 2S5, Canada", "lat": "43.77439110", "lng": "-79.50481085", "type": "edu", "country": "Canada"}, {"name": "Stanford University", "source_name": "Stanford University", "street_adddress": "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1505.01173.pdf"], "doi": []}, {"id": "164f3b9740d9ceb14658237fddede0f86b5e0c47", "title": "Deep Category-Aware Semantic Edge Detection", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "", "pdf": ["https://pdfs.semanticscholar.org/1b61/41d3fbe8b97fd414ec931a47aa1d019347d9.pdf"], "doi": []}, {"id": "30f464c09779c6210397204901d025c0def1fe10", "title": "Deep Reasoning with Knowledge Graph for Social Relationship Understanding", "addresses": [{"name": "Sun Yat-Sen University", "source_name": "Sun Yat-Sen University", "street_adddress": "\u4e2d\u5927, \u65b0\u6e2f\u897f\u8def, \u9f99\u8239\u6ed8, \u5eb7\u4e50, \u6d77\u73e0\u533a (Haizhu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510105, \u4e2d\u56fd", "lat": "23.09461185", "lng": "113.28788994", "type": "edu", "country": "China"}, {"name": "SenseTime", "source_name": "SenseTime", "street_adddress": "China, Beijing Shi, Haidian Qu, WuDaoKou, Zhongguancun E Rd, 1\u53f7-7", "lat": "39.99300800", "lng": "116.32988200", "type": "company", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.00504.pdf"], "doi": []}, {"id": "64a5709d41f4c2ef0383cee9932e89bb58085588", "title": "Surgeon Technical Skill Assessment using Computer Vision based Analysis", "addresses": [{"name": "University of Michigan", "source_name": "University of Michigan", "street_adddress": "University of Michigan, 500, Hayward Street, Ann Arbor, Washtenaw County, Michigan, 48109, USA", "lat": "42.29421420", "lng": "-83.71003894", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/64a5/709d41f4c2ef0383cee9932e89bb58085588.pdf"], "doi": []}, {"id": "0c65245bff0004961a5173709400479addbb9ee1", "title": "SemanticFusion: Dense 3D semantic mapping with convolutional neural networks", "addresses": [{"name": "Imperial College London", "source_name": "Imperial College London", "street_adddress": "Imperial College London, Exhibition Road, Brompton, Royal Borough of Kensington and Chelsea, London, Greater London, England, SW7 2AZ, UK", "lat": "51.49887085", "lng": "-0.17560797", "type": "edu", "country": "United Kingdom"}], "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7989538"]}, {"id": "24e680c5e7f59b72984ebc344dfba0f9573fb38c", "title": "On the difficulty of a distributional semantics of spoken language", "addresses": [{"name": "Tilburg University", "source_name": "Tilburg center for Cognition and Communication, Tilburg University, Tilburg, The Netherlands", "street_adddress": "Warandelaan 2, 5037 AB Tilburg, Netherlands", "lat": "51.56314060", "lng": "5.04197360", "type": "edu", "country": "Netherlands"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.08869.pdf"], "doi": []}, {"id": "2e84deb2fbc518c0ed0ba4158fc063060e5ac1b3", "title": "Real-time Progressive 3D Semantic Segmentation for Indoor Scene", "addresses": [{"name": "Singapore University of Technology and Design", "source_name": "Singapore University of Technology and Design", "street_adddress": "Singapore University of Technology and Design, Simpang Bedok, Changi Business Park, Southeast, 486041, Singapore", "lat": "1.34021600", "lng": "103.96508900", "type": "edu", "country": "Singapore"}, {"name": "Deakin University", "source_name": "Deakin University", "street_adddress": "Deakin University, Pigdons Lane, Waurn Ponds, Geelong, City of Greater Geelong, Barwon South West, Victoria, 3216, Australia", "lat": "-38.19928505", "lng": "144.30365229", "type": "edu", "country": "Australia"}, {"name": "Hong Kong University of Science and Technology", "source_name": "Hong Kong University of Science and Technology", "street_adddress": "\u9999\u6e2f\u79d1\u6280\u5927\u5b78 Hong Kong University of Science and Technology, \u5927\u5b78\u9053 University Road, \u5927\u57d4\u4ed4 Tai Po Tsai, \u5927\u57d4\u4ed4\u6751 Tai Po Tsai Village, \u65b0\u754c New Territories, HK, DD253 1209, \u4e2d\u56fd", "lat": "22.33863040", "lng": "114.26203370", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.00257.pdf"], "doi": []}, {"id": "2d15a7546c16d5821ffa8f769eb7ec18e435e64d", "title": "Recognition in Terra Incognita", "addresses": [{"name": "Caltech", "source_name": "California Inst. of Technol., Pasadena, CA, USA", "street_adddress": "1200 E California Blvd, Pasadena, CA 91125, USA", "lat": "34.13765760", "lng": "-118.12526900", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.04975.pdf"], "doi": []}, {"id": "84a3478cf884b0cbba480c7c36dab565e778094b", "title": "Learning to detect chest radiographs containing lung nodules using visual attention networks", "addresses": [{"name": "King\u2019s College London", "source_name": "Institute of Psychiatry, King\u2019s College London, London, UK", "street_adddress": "16 De Crespigny Park, Camberwell, London SE5 8AF, UK", "lat": "51.47022750", "lng": "-0.09014280", "type": "edu", "country": "United Kingdom"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1712.00996.pdf"], "doi": []}, {"id": "fbace36d9161fbd062eefa0c005362bb210c7097", "title": "VPGNet: Vanishing Point Guided Network for Lane and Road Marking Detection and Recognition", "addresses": [{"name": "KAIST", "source_name": "KAIST", "street_adddress": "291 Daehak-ro, Eoeun-dong, Yuseong-gu, Daejeon, South Korea", "lat": "36.37214270", "lng": "127.36039000", "type": "edu", "country": "South Korea"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1710.06288.pdf"], "doi": []}, {"id": "d012f6d7fd45051adaff8da4ce0860de9f81d445", "title": "A Deep Multi-task Learning Approach to Skin Lesion Classification", "addresses": [{"name": "University of Rochester", "source_name": "University of Rochester", "street_adddress": "Memorial Art Gallery, 500, University Avenue, East End, Rochester, Monroe County, New York, 14607, USA", "lat": "43.15769690", "lng": "-77.58829158", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1812.03527.pdf"], "doi": []}, {"id": "fc027fccb19512a439fc17181c34ee1c3aad51b5", "title": "Joint Multi-person Pose Estimation and Semantic Part Segmentation", "addresses": [{"name": "UCLA", "source_name": "University of California, Los Angeles", "street_adddress": "Los Angeles, CA 90095, USA", "lat": "34.06892100", "lng": "-118.44518110", "type": "edu", "country": "United States"}, {"name": "Johns Hopkins University", "source_name": "Johns Hopkins University", "street_adddress": "Baltimore, MD 21218, USA", "lat": "39.32990130", "lng": "-76.62051770", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.03383.pdf"], "doi": []}, {"id": "50d6dcec7f1fcbde647237d43950fa5ec59d6984", "title": "Panoptic Segmentation with a Joint Semantic and Instance Segmentation Network", "addresses": [{"name": "TU Eindhoven", "source_name": "TU Eindhoven", "street_adddress": "Technische Universiteit Eindhoven, 2, De Rondom, Villapark, Eindhoven, Noord-Brabant, Nederland, 5600 MB, Nederland", "lat": "51.44866020", "lng": "5.49039957", "type": "edu", "country": "Netherlands"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.02110.pdf"], "doi": []}, {"id": "225c318f3143b9b9d6c0f7a87672bd1d9d2901f4", "title": "2 D-Driven 3 D Object Detection in RGB-D Images", "addresses": [{"name": "King Abdullah University of Science and Technology (KAUST)", "source_name": "King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia", "street_adddress": "Thuwal 23955, Saudi Arabia", "lat": "22.30946500", "lng": "39.10469700", "type": "edu", "country": "Saudi Arabia"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/225c/318f3143b9b9d6c0f7a87672bd1d9d2901f4.pdf"], "doi": []}, {"id": "37e1fc37a3ee90f24d85ad6fd3e5c51d3f5ab4fd", "title": "Attentive Explanations: Justifying Decisions and Pointing to the Evidence", "addresses": [{"name": "Max Planck Institute for Informatics", "source_name": "Max Planck Institute for Informatics", "street_adddress": "MPII, E1 4, Campus, Universit\u00e4t, Sankt Johann, Bezirk Mitte, Saarbr\u00fccken, Regionalverband Saarbr\u00fccken, Saarland, 66123, Deutschland", "lat": "49.25795660", "lng": "7.04577417", "type": "edu", "country": "Germany"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1612.04757.pdf"], "doi": []}, {"id": "475e16577be1bfc0dd1f74f67bb651abd6d63524", "title": "DAiSEE: Towards User Engagement Recognition in the Wild", "addresses": [{"name": "Microsoft", "source_name": "Microsoft Corporation, Redmond, WA, USA", "street_adddress": "One Microsoft Way, Redmond, WA 98052, USA", "lat": "47.64233180", "lng": "-122.13693020", "type": "company", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1609.01885.pdf"], "doi": []}, {"id": "503c16d9cb1560f13a7d6baedf8c9f889b22459d", "title": "Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation", "addresses": [{"name": "Google", "source_name": "Google, Inc.", "street_adddress": "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "lat": "37.42199990", "lng": "-122.08405750", "type": "company", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.02611.pdf"], "doi": []}, {"id": "18c57ddc9c0164ee792661f43a5578f7a00d0330", "title": "ChestX-Ray8: Hospital-Scale Chest X-Ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases", "addresses": [{"name": "National Institutes of Health", "source_name": "National Institutes of Health", "street_adddress": "NIH, Pooks Hill, Bethesda, Montgomery County, Maryland, USA", "lat": "39.00041165", "lng": "-77.10327775", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.02315.pdf"], "doi": []}, {"id": "f632790471b2bed7ba7c28b12cda9360ec586a63", "title": "Deep Binaries: Encoding Semantic-Rich Cues for Efficient Textual-Visual Cross Retrieval", "addresses": [{"name": "University of East Anglia", "source_name": "University of East Anglia", "street_adddress": "Arts (Lower Walkway Level), The Square, Westfield View, Earlham, Norwich, Norfolk, East of England, England, NR4 7TJ, UK", "lat": "52.62215710", "lng": "1.24091360", "type": "edu", "country": "United Kingdom"}, {"name": "University of Electronic Science and Technology of China", "source_name": "University of Electronic Science and Technology of China", "street_adddress": "2 Jianshe North Rd 2nd Section, Jianshe Road, Chenghua Qu, Chengdu Shi, Sichuan Sheng, China, 610054", "lat": "30.67272100", "lng": "104.09880600", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.02531.pdf"], "doi": []}, {"id": "197c406b95340dfcdef542db532e0f7a967b9cda", "title": "Softer-NMS: Rethinking Bounding Box Regression for Accurate Object Detection", "addresses": [{"name": "Carnegie Mellon University", "source_name": "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "street_adddress": "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "lat": "40.44416190", "lng": "-79.94272826", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.08545.pdf"], "doi": []}, {"id": "0f54eacd2d9ad031a0b55166399e2f1d0f70b4b5", "title": "Joint Learning of Set Cardinality and State Distribution", "addresses": [{"name": "University of Adelaide", "source_name": "University of Adelaide", "street_adddress": "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu", "country": "Australia"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1709.04093.pdf"], "doi": []}, {"id": "1e54025a6b399bfc210a52a8c3314e8f570c2204", "title": "DenseCap: Fully Convolutional Localization Networks for Dense Captioning", "addresses": [{"name": "Stanford University", "source_name": "Stanford University", "street_adddress": "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1511.07571.pdf"], "doi": []}, {"id": "26203d84466488b168745334935f7ca82294e3e4", "title": "Visual Reasoning by Progressive Module Networks", "addresses": [{"name": "University of Toronto", "source_name": "University of Toronto", "street_adddress": "University of Toronto, St. George Street, Bloor Street Culture Corridor, Old Toronto, Toronto, Ontario, M5S 1A5, Canada", "lat": "43.66333345", "lng": "-79.39769975", "type": "edu", "country": "Canada"}, {"name": "NVIDIA", "source_name": "NVIDIA", "street_adddress": "2788 San Tomas Expy, Santa Clara, CA 95051, USA", "lat": "37.37062540", "lng": "-121.96718940", "type": "company", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.02453.pdf"], "doi": []}, {"id": "8b059a9851c23067afe247b59e54f3167caa9b34", "title": "Modality-Specific Cross-Modal Similarity Measurement With Recurrent Attention Network", "addresses": [{"name": "Peking University", "source_name": "Peking University", "street_adddress": "\u5317\u4eac\u5927\u5b66, 5\u53f7, \u9890\u548c\u56ed\u8def, \u7a3b\u9999\u56ed\u5357\u793e\u533a, \u6d77\u6dc0\u533a, \u5317\u4eac\u5e02, 100871, \u4e2d\u56fd", "lat": "39.99223790", "lng": "116.30393816", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8401908"]}, {"id": "3796fe0e5dd10b01fc9fb486d09e61b28eedf915", "title": "Instance Segmentation of Fibers from Low Resolution CT Scans via 3D Deep Embedding Learning", "addresses": [{"name": "Heidelberg University", "source_name": "Institute of Psychology, Heidelberg University, Heidelberg, Germany", "street_adddress": "Hauptstra\u00dfe 47-51, 69117 Heidelberg, Germany", "lat": "49.41092660", "lng": "8.69795290", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1901.01034.pdf"], "doi": []}, {"id": "11a8cc3fa18ab4f7158447cc1fc8800489e82f9c", "title": "AttResNet: Attention-based ResNet for Image Captioning", "addresses": [{"name": "National University of Defense Technology, China", "source_name": "National University of Defence Technology, Changsha 410000, China", "street_adddress": "\u56fd\u9632\u79d1\u5b66\u6280\u672f\u5927\u5b66, \u4e09\u4e00\u5927\u9053, \u5f00\u798f\u533a, \u5f00\u798f\u533a (Kaifu), \u957f\u6c99\u5e02 / Changsha, \u6e56\u5357\u7701, 410073, \u4e2d\u56fd", "lat": "28.22902090", "lng": "112.99483204", "type": "mil", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3302464"]}, {"id": "2e78e804ddfe86f112719d4a237c882f930a9d3b", "title": "Development of Real-time ADAS Object Detector for Deployment on CPU", "addresses": [{"name": "Intel", "source_name": "Intel Corp., 4600 S. Dobson Road, Chandler, AZ 85248", "street_adddress": "4500 S Dobson Rd, Chandler, AZ 85248, USA", "lat": "33.24160080", "lng": "-111.88390830", "type": "company", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.05894.pdf"], "doi": []}, {"id": "396aacab076a3607429f58ce442d5d57b5aaa794", "title": "Semantic Instance Annotation of Street Scenes by 3D to 2D Label Transfer", "addresses": [{"name": "University of Washington", "source_name": "University of Washington", "street_adddress": "University of Washington, Rainier Vista, Montlake, University District, Seattle, King County, Washington, 98195, USA", "lat": "47.65432380", "lng": "-122.30800894", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1511.03240.pdf"], "doi": []}, {"id": "6fe1439e40429c7cd7029ecf83ca6f36fd0c8040", "title": "Deep Matching and Validation Network: An End-to-End Solution to Constrained Image Splicing Localization and Detection", "addresses": [{"name": "Information Sciences Institute, Marina Del Rey, CA", "source_name": "Information Sciences Institute, Marina Del Rey, CA, USA", "street_adddress": "4676 Admiralty Way #1001, Marina Del Rey, CA 90292, USA", "lat": "33.98007070", "lng": "-118.44003850", "type": "edu", "country": "United States"}], "year": "2017", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3123411"]}, {"id": "5a40efdd3a50ab2e3bce106f92d921713ef068b3", "title": "Learning Saliency Prediction From Sparse Fixation Pixel Map", "addresses": [{"name": "Sichuan University, Chengdu", "source_name": "Sichuan Univ., Chengdu", "street_adddress": "\u56db\u5ddd\u5927\u5b66\uff08\u534e\u897f\u6821\u533a\uff09, \u6821\u4e1c\u8def, \u6b66\u4faf\u533a, \u6b66\u4faf\u533a (Wuhou), \u6210\u90fd\u5e02 / Chengdu, \u56db\u5ddd\u7701, 610014, \u4e2d\u56fd", "lat": "30.64276900", "lng": "104.06751175", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.00644.pdf"], "doi": []}, {"id": "745a913b6a3dd28f3d1c583e80497d6d627a9ca4", "title": "OBJ2TEXT: Generating Visually Descriptive Language from Object Layouts", "addresses": [{"name": "University of Virginia", "source_name": "University of Virginia", "street_adddress": "University of Virginia, Rotunda Alley, Carr's Hill, Albemarle County, Virginia, 22904-4119, USA", "lat": "38.03536820", "lng": "-78.50353220", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.07102.pdf"], "doi": []}, {"id": "a43280a668f12cffdb7b4c9917984aa55b12759b", "title": "Zoom Out-and-In Network with Recursive Training for Object Proposal", "addresses": [{"name": "Chinese University of Hong Kong", "source_name": "Chinese University of Hong Kong", "street_adddress": "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "lat": "22.41626320", "lng": "114.21093180", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1702.05711.pdf"], "doi": []}, {"id": "aa7914646c6a4bbad0727cb84ab9b05e5b381af4", "title": "Framework for Evaluating Vision-based Autonomous Steering Control Model", "addresses": [{"name": "DGIST", "source_name": "DGIST", "street_adddress": "South Korea, Daegu, Dalseong-gun, Yuga-myeon, \ud14c\ud06c\ub178\uc911\uc559\ub300\ub85c 333", "lat": "35.70528600", "lng": "128.45710200", "type": "edu", "country": "South Korea"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8569717"]}, {"id": "3ab93fe26a46f8bc0999e68af71a0907a63a5e65", "title": "ESTHER: Extremely Simple Image Translation Through Self-Regularization", "addresses": [{"name": "University of Southern California", "source_name": "University of Southern California", "street_adddress": "University of Southern California, Watt Way, Saint James Park, LA, Los Angeles County, California, 90089, USA", "lat": "34.02241490", "lng": "-118.28634407", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/3ab9/3fe26a46f8bc0999e68af71a0907a63a5e65.pdf"], "doi": []}, {"id": "1d82e7736268917cc3d87a2ee0896b03e02a5ff6", "title": "The Promise of Premise: Harnessing Question Premises in Visual Question Answering", "addresses": [{"name": "Virginia Tech", "source_name": "Virginia Tech", "street_adddress": "Blacksburg, VA 24061, USA", "lat": "37.22838430", "lng": "-80.42341670", "type": "edu", "country": "United States"}, {"name": "Georgia Institute of Technology", "source_name": "Georgia Institute of Technology", "street_adddress": "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.00601.pdf"], "doi": []}, {"id": "58d16e23e1192be4acaf6a29c1f5995817146554", "title": "Bringing back simplicity and lightliness into neural image captioning", "addresses": [{"name": "University of Mons", "source_name": "Faculty of Engineering, University of Mons, Belgium", "street_adddress": "Place du Parc 20, 7000 Mons, Belgium", "lat": "50.45877140", "lng": "3.95216520", "type": "edu", "country": "Belgium"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.06245.pdf"], "doi": []}, {"id": "7771807cd05f78a4591f2d0b094ddd3e0bd5339a", "title": "Adaptive Feeding: Achieving Fast and Accurate Detections by Adaptively Combining Object Detectors", "addresses": [{"name": "Nanjing University", "source_name": "Nanjing University", "street_adddress": "NJU, \u4e09\u6c5f\u8def, \u9f13\u697c\u533a, \u5357\u4eac\u5e02, \u6c5f\u82cf\u7701, 210093, \u4e2d\u56fd", "lat": "32.05659570", "lng": "118.77408833", "type": "edu", "country": "China"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.06399.pdf"], "doi": []}, {"id": "b2c60061ad32e28eb1e20aff42e062c9160786be", "title": "Diverse and Controllable Image Captioning with Part-of-Speech Guidance", "addresses": [{"name": "University of Illinois, Urbana-Champaign", "source_name": "University of Illinois, Urbana-Champaign", "street_adddress": "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.12589.pdf"], "doi": []}, {"id": "20a91b0e7c2598d327169517cdeaafc433caa700", "title": "Inshore Ship Detection Based on Mask R-CNN", "addresses": [{"name": "Beihang University", "source_name": "Beihang University", "street_adddress": "\u5317\u4eac\u822a\u7a7a\u822a\u5929\u5927\u5b66, 37, \u5b66\u9662\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100083, \u4e2d\u56fd", "lat": "39.98083330", "lng": "116.34101249", "type": "edu", "country": "China"}], "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8519123"]}, {"id": "07f4ba45b771ed123b08261d88acda19406a7987", "title": "Real-Time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identification", "addresses": [{"name": "Tsinghua University", "source_name": "Tsinghua University", "street_adddress": "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "lat": "40.00229045", "lng": "116.32098908", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.04427.pdf"], "doi": []}, {"id": "cb4fc4d49783f2049c48a062169f04eb744443ec", "title": "Paying More Attention to Saliency: Image Captioning with Saliency and Context Attention", "addresses": [{"name": "University of Modena and Reggio Emilia", "source_name": "University of Modena and Reggio Emilia 41125, Modena, Italy", "street_adddress": "Via Universit\u00e0, 4, 41121 Modena MO, Italy", "lat": "44.64510460", "lng": "10.92792680", "type": "edu", "country": "Italy"}, {"name": "University of Udine", "source_name": "University of Udine, Italy", "street_adddress": "Universit\u00e0 degli Studi di Udine, Via delle Scienze, 206, 33100 Udine UD, Italy", "lat": "46.08107230", "lng": "13.21194740", "type": "edu", "country": "Italy"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1706.08474.pdf"], "doi": []}, {"id": "38262d92b09564aba747beb7150b92c92998170c", "title": "A Visual Attention Grounding Neural Model for Multimodal Machine Translation", "addresses": [{"name": "University of California, Davis", "source_name": "University of California, Davis", "street_adddress": "University of California, Davis, Apiary Drive, Yolo County, California, 95616-5270, USA", "lat": "38.53363490", "lng": "-121.79077264", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.08266.pdf"], "doi": []}]}
\ No newline at end of file