diff options
Diffstat (limited to 'site/datasets/citations/coco.json')
| -rw-r--r-- | site/datasets/citations/coco.json | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/site/datasets/citations/coco.json b/site/datasets/citations/coco.json index 89bfda48..7e3f35dc 100644 --- a/site/datasets/citations/coco.json +++ b/site/datasets/citations/coco.json @@ -1 +1 @@ -{"id": "5e0f8c355a37a5a89351c02f174e7a5ddcb98683", "paper": {"paperId": "5e0f8c355a37a5a89351c02f174e7a5ddcb98683", "key": "coco", "title": "Microsoft COCO: Common Objects in Context", "journal": "Unknown", "address": "", "country": "", "address_type": "", "lat": "", "lng": "", "pdf_link": "https://arxiv.org/pdf/1405.0312.pdf", "report_link": "papers/5e0f8c355a37a5a89351c02f174e7a5ddcb98683.html", "citation_count": 999, "citations_geocoded": 569, "citations_unknown": 430, "citations_empty": 29, "citations_pdf": 799, "citations_doi": 193, "name": "COCO"}, "address": null, "citations": [["Generating Natural Video Descriptions via Multimodal Processing", "", "Carnegie Mellon University", "Carnegie Mellon University", "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "37.41021930", "-122.05965487", "edu", "", "United States", "2016"], ["Pyramid Scene Parsing Network", "", "SenseTime", "SenseTime", "China, Beijing Shi, Haidian Qu, WuDaoKou, Zhongguancun E Rd, 1\u53f7-7", "39.99300800", "116.32988200", "company", "1 Zhongguancun E Rd, Haidian Qu, China", "China", "2017"], ["Analysis of Spatial, Temporal, and Content Characteristics of Videos in the YFCC100M Dataset", "Yonsei University, Incheon, South Korea", "Yonsei University", "Yonsei University", "\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", "37.56004060", "126.93692480", "edu", "", "South Korea", "2016"], ["Context-Aware Captions from Context-Agnostic Supervision", "", "Georgia Institute of Technology", "Georgia Institute of Technology", "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "33.77603300", "-84.39884086", "edu", "", "United States", "2017"], ["Understanding Convolution for Semantic Segmentation", "", "TuSimple", "TuSimple", "9191 Towne Centre Dr STE 600, San Diego, CA 92122, USA", "32.87344550", "-117.20656360", "edu", "", "", "2018"], ["GLA: Global\u2013Local Attention for Image Description", "Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China", "Chinese Academy of Sciences", "Chinese Academy of Sciences", "\u4e2d\u56fd\u79d1\u5b66\u9662\u5fc3\u7406\u7814\u7a76\u6240, 16, \u6797\u8403\u8def, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100101, \u4e2d\u56fd", "40.00447950", "116.37023800", "edu", "", "China", "2018"], ["Generative Attention Model with Adversarial Self-learning for Visual Question Answering", "National University of Singapore, Singapore, Singapore", "National University of Singapore", "National University of Singapore", "NUS, Former 1936 British Outpost, Nepal Hill, Clementi, Southwest, 117542, Singapore", "1.29620180", "103.77689944", "edu", "", "Singapore", "2017"], ["Superpixel Filtering for Mean Field Inference in CRFs Integrated with Convolutional Neural Networks", "", "University of Oxford", "University of Oxford", "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "51.75345380", "-1.25400997", "edu", "", "United Kingdom", "2015"], ["Computer Vision and Deep Learning for Automated Surveillance Technology", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "United States", "2016"], ["Socratic Learning: Augmenting Generative Models to Incorporate Latent Subsets in Training Data", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "United States", "2016"], ["Multi-Person Pose Estimation for PoseTrack with Enhanced Part Affinity Fields", "", "Beijing, China", "Beijing, China", "Beijing, China", "39.90419990", "116.40739630", "edu", "", "China", "2017"], ["ChestX-Ray8: Hospital-Scale Chest X-Ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases", "", "National Institutes of Health", "National Institutes of Health", "NIH, Pooks Hill, Bethesda, Montgomery County, Maryland, USA", "39.00041165", "-77.10327775", "edu", "", "United States", "2017"], ["Where to put the Image in an Image Caption Generator", "", "University of Malta", "University of Malta", "University of Malta, Ring Road, Japanese Garden, L-Imsida, Malta, MSD 9027, Malta", "35.90232260", "14.48341890", "edu", "", "Malta", "2018"], ["Towards Context-aware Interaction Recognition", "", "University of Adelaide", "University of Adelaide", "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "-34.91892260", "138.60423668", "edu", "", "Australia", "2017"], ["Regional Gating Neural Networks for Multi-label Image Classification", "", "Shanghai, China", "Shanghai, China", "Shanghai, China", "31.23039040", "121.47370210", "edu", "", "", "2016"], ["BDD100K: A Diverse Driving Video Database with Scalable Annotation Tooling", "", "Peking University", "Peking University", "\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", "39.99223790", "116.30393816", "edu", "", "China", "2018"], ["The Color of the Cat is Gray: 1 Million Full-Sentences Visual Question Answering (FSVQA).", "", "University of Tokyo", "University of Tokyo", "\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", "35.90204480", "139.93622009", "edu", "", "Japan", "2016"], ["Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour.", "", "Facebook", "Facebook", "250 Bryant St, Mountain View, CA 94041, USA", "37.39367170", "-122.08072620", "company", "Facebook, Mountain View, CA", "United States", "2017"], ["SIGNet: Semantic Instance Aided Unsupervised 3D Geometry Perception", "", "UC San Diego", "UC San Diego", "9500 Gilman Dr, La Jolla, CA 92093, USA", "32.88006040", "-117.23401350", "edu", "", "United States", "2018"], ["Action Classification via Concepts and Attributes", "", "Weizmann Institute of Science", "Weizmann Institute of Science", "\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", "31.90784990", "34.81334092", "edu", "", "Israel", "2018"], ["Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks", "Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong", "Chinese University of Hong Kong", "Chinese University of Hong Kong", "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "22.41626320", "114.21093180", "edu", "", "China", "2017"], ["Learning to Learn: Model Regression Networks for Easy Small Sample Learning", "", "Robotics Institute", "Robotics Institute", "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", "13.65450525", "100.49423171", "edu", "", "Thailand", "2016"], ["Rethinking Atrous Convolution for Semantic Image Segmentation", "", "Google", "Google, Inc.", "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "37.42199990", "-122.08405750", "company", "Google, Mountain View, CA", "United States", "2017"], ["UMDFaces: An annotated face dataset for training deep networks", "University of Maryland, College Park", "University of Maryland", "University of Maryland", "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "39.28996850", "-76.62196103", "edu", "", "United States", "2017"], ["Grounding of Textual Phrases in Images by Reconstruction", "", "Max Planck Institute for Informatics", "Max Planck Institute for Informatics", "MPII, E1 4, Campus, Universit\u00e4t, Sankt Johann, Bezirk Mitte, Saarbr\u00fccken, Regionalverband Saarbr\u00fccken, Saarland, 66123, Deutschland", "49.25795660", "7.04577417", "edu", "", "Germany", "2016"], ["Image Captioning with Sentiment Terms via Weakly-Supervised Sentiment Dataset", "", "University of Tokyo", "University of Tokyo", "\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", "35.90204480", "139.93622009", "edu", "", "Japan", "2016"], ["iLab-20M: A Large-Scale Controlled Object Dataset to Investigate Deep Learning", "", "Amirkabir University of Technology", "Amirkabir University of Technology", "\u062f\u0627\u0646\u0634\u06af\u0627\u0647 \u0635\u0646\u0639\u062a\u06cc \u0627\u0645\u06cc\u0631\u06a9\u0628\u06cc\u0631, \u0648\u0644\u06cc \u0639\u0635\u0631, \u0645\u06cc\u062f\u0627\u0646 \u0648\u0644\u06cc\u0639\u0635\u0631, \u0645\u0646\u0637\u0642\u0647 \u06f6 \u0634\u0647\u0631 \u062a\u0647\u0631\u0627\u0646, \u062a\u0647\u0631\u0627\u0646, \u0628\u062e\u0634 \u0645\u0631\u06a9\u0632\u06cc \u0634\u0647\u0631\u0633\u062a\u0627\u0646 \u062a\u0647\u0631\u0627\u0646, \u0634\u0647\u0631\u0633\u062a\u0627\u0646 \u062a\u0647\u0631\u0627\u0646, \u0627\u0633\u062a\u0627\u0646 \u062a\u0647\u0631\u0627\u0646, \u0646\u0628\u0634 \u0628\u0631\u0627\u062f\u0631\u0627\u0646 \u0645\u0638\u0641\u0631, \u200f\u0627\u06cc\u0631\u0627\u0646\u200e", "35.70451400", "51.40972058", "edu", "", "Iran", "2016"], ["Social Image Tags as a Source of Word Embeddings: A Task-oriented Evaluation", "", "Waseda University", "Waseda University", "\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", "33.88987280", "130.70856205", "edu", "", "Japan", "2018"], ["Modeling Image Virality with Pairwise Spatial Transformer Networks", "", "MIT", "Massachusetts Institute", "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "42.35839610", "-71.09567788", "edu", "", "United States", "2017"], ["Aided Action Recognition Using Single Images", "", "Lehigh University", "Lehigh University", "Lehigh University, Library Drive, Sayre Park, Bethlehem, Northampton County, Pennsylvania, 18015, USA", "40.60680280", "-75.37824880", "edu", "", "United States", "2017"], ["Aligning Text and Document Illustrations: Towards Visually Explainable Digital Humanities", "University of of Modena and Reggio Emilia", "University of of Modena and Reggio Emilia", "University of of Modena and Reggio Emilia", "Via Universit\u00e0, 4, 41121 Modena MO, Italy", "44.64510460", "10.92792680", "edu", "", "Italy", "2018"], ["Weakly- and Semi-supervised Panoptic Segmentation", "", "University of Oxford", "University of Oxford", "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "51.75345380", "-1.25400997", "edu", "", "United Kingdom", "2018"], ["Learning Object Detectors from Scratch with Gated Recurrent Feature Pyramids", "", "Fudan University", "Fudan University", "\u590d\u65e6\u5927\u5b66, 220, \u90af\u90f8\u8def, \u4e94\u89d2\u573a\u8857\u9053, \u6768\u6d66\u533a, \u4e0a\u6d77\u5e02, 200433, \u4e2d\u56fd", "31.30104395", "121.50045497", "edu", "", "China", "2017"], ["Analysing object detectors from the perspective of co-occurring object categories", "", "Budapest, Hungary", "Budapest, Hungary", "Budapest, Hungary", "47.49791200", "19.04023500", "edu", "", "", "2018"], ["ScaleNet: Guiding Object Proposal Generation in Supermarkets and Beyond", "", "Shanghai University", "Shanghai University", "\u4e0a\u6d77\u5927\u5b66, \u9526\u79cb\u8def, \u5927\u573a\u9547, \u5b9d\u5c71\u533a (Baoshan), \u4e0a\u6d77\u5e02, 201906, \u4e2d\u56fd", "31.32235655", "121.38400941", "edu", "", "China", "2017"], ["Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "United States", "2019"], ["Image Caption with Endogenous\u2013Exogenous Attention", "School of Electronic and Information Engineering, Sun Yat-sen University, Guangzhou, China", "Sun Yat-Sen University", "Sun Yat-Sen University", "\u4e2d\u5927, \u65b0\u6e2f\u897f\u8def, \u9f99\u8239\u6ed8, \u5eb7\u4e50, \u6d77\u73e0\u533a (Haizhu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510105, \u4e2d\u56fd", "23.09461185", "113.28788994", "edu", "", "China", "2019"], ["Identity-Aware Textual-Visual Matching with Latent Co-attention", "", "Chinese University of Hong Kong", "Chinese University of Hong Kong", "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "22.41626320", "114.21093180", "edu", "", "China", "2017"], ["Multi-label image classification with recurrently learning semantic dependencies", "School of Computer and Information, Hefei University of Technology, Hefei, China", "Hefei University of Technology", "Hefei University of Technology", "\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", "31.84691800", "117.29053367", "edu", "", "China", "2018"], ["Can You See the (Linguistic) Difference? Exploring Mass/Count Distinction in Vision", "", "University of Padova", "University of Padova", "Via Giovanni Gradenigo, 6, 35131 Padova PD, Italy", "45.40811720", "11.89437860", "edu", "University of Padova, Via Gradenigo, 6 - 35131- Padova, Italy", "Italy", "2017"], ["Dropout during inference as a model for neurological degeneration in an image captioning network", "", "University of Toronto", "University of Toronto", "University of Toronto, St. George Street, Bloor Street Culture Corridor, Old Toronto, Toronto, Ontario, M5S 1A5, Canada", "43.66333345", "-79.39769975", "edu", "", "Canada", "2018"], ["Weakly-Supervised Visual Grounding of Phrases with Linguistic Structures", "", "University of California, Davis", "University of California, Davis", "University of California, Davis, Apiary Drive, Yolo County, California, 95616-5270, USA", "38.53363490", "-121.79077264", "edu", "", "United States", "2017"], ["Deep Multimodal Learning: An Effective Method for Video Classification", "", "Tsinghua University", "Tsinghua University", "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "40.00229045", "116.32098908", "edu", "", "China", "2018"], ["Predicting Motivations of Actions by Leveraging Text", "", "University of Maryland", "University of Maryland", "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "39.28996850", "-76.62196103", "edu", "", "United States", "2016"], ["Semantic image segmentation using fully convolutional neural networks with multi-scale images and multi-scale dilated convolutions", "Pattern Recognition and Machine Learning Lab, Gachon University, Seongnam, Korea", "Gachon University", "Gachon University, Gyeonggi-do, South Korea", "1342 Seongnam-daero, Bokjeong-dong, Sujeong-gu, Seongnam-si, Gyeonggi-do, South Korea", "37.45074520", "127.12884740", "edu", "", "South Korea", "2018"], ["Cross-media Multi-level Alignment with Relation Attention Network", "", "Peking University", "Peking University", "\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", "39.99223790", "116.30393816", "edu", "", "China", "2018"], ["Non-parametric human segmentation using support vector machine", "Yonsei University, Seoul 03722, South Korea", "Yonsei University", "Yonsei University", "\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", "37.56004060", "126.93692480", "edu", "", "South Korea", "2016"], ["Multispectral Pedestrian Detection via Simultaneous Detection and Segmentation", "", "Zhejiang University", "Zhejiang University", "\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", "30.19331415", "120.11930822", "edu", "", "China", "2018"], ["Toward Efficient Simultaneous Detection and Segmentation", "Peking University, National Engineering Laboratory for Video Technology, School of EE&CS, Beijing, China", "Peking University", "Peking University", "\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", "39.99223790", "116.30393816", "edu", "", "China", "2018"], ["Spatially Adaptive Computation Time for Residual Networks", "", "Google", "Google, Inc.", "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "37.42199990", "-122.08405750", "company", "Google, Mountain View, CA", "United States", "2017"], ["Pre-gen Metrics: Predicting Caption Quality Metrics Without Generating Captions", "University of Malta, Msida, Malta", "University of Malta", "University of Malta", "University of Malta, Ring Road, Japanese Garden, L-Imsida, Malta, MSD 9027, Malta", "35.90232260", "14.48341890", "edu", "", "Malta", "2018"], ["Learning to Evaluate Image Captioning", "", "Cornell University", "Cornell University", "Cornell University, Forest Home Drive, Forest Home, Tompkins County, New York, 14853, USA", "42.45055070", "-76.47835130", "edu", "", "United States", "2018"], ["Style Transfer at 100+ FPS Via Sub-Pixel Super-Resolution", "South China University of Technology", "South China University of Technology", "South China University of Technology", "\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", "23.05020420", "113.39880323", "edu", "", "China", "2018"], ["A Semi-supervised Framework for Image Captioning", "", "ETH Zurich", "ETH Zurich", "R\u00e4mistrasse 101, 8092 Z\u00fcrich, Switzerland", "47.37631300", "8.54766990", "edu", "", "Switzerland", "2016"], ["Language Models for Image Captioning: The Quirks and What Works", "", "Microsoft", "Microsoft Corporation, Redmond, WA, USA", "One Microsoft Way, Redmond, WA 98052, USA", "47.64233180", "-122.13693020", "company", "", "United States", "2015"], ["Automatic Dataset Augmentation", "", "Harbin Institute of Technology", "Harbin Institute of Technology", "\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", "45.74139210", "126.62552755", "edu", "", "China", "2017"], ["The Helping Hand: An Assistive Manipulation Framework Using Augmented Reality and Tongue-Drive Interfaces", "Institute for Robotics and Intelligent Machines, Georgia Institute of Technology, GA, USA", "Georgia Institute of Technology", "Georgia Institute of Technology", "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "33.77603300", "-84.39884086", "edu", "", "United States", "2018"], ["Consistent Optimization for Single-Shot Object Detection", "", "Tsinghua University", "Tsinghua University", "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "40.00229045", "116.32098908", "edu", "", "China", "2019"], ["Object Proposal Generation With Fully Convolutional Networks", "Keio-National University of Singapore (NUS) Connective Ubiquitous Technology for Embodiments Center, Interactive and Digital Media Institute, NUS, Singapore", "Singapore", "Singapore", "Singapore", "1.35208300", "103.81983600", "edu", "", "Singapore", "2018"], ["ProNet: Learning to Propose Object-Specific Boxes for Cascaded Neural Networks", "", "University of California, Berkeley", "University of California, Berkeley", "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "37.86871260", "-122.25586815", "edu", "", "United States", "2016"], ["Revisiting Graph Construction for Fast Image Segmentation", "", "Xiamen University", "Xiamen University", "\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", "24.43994190", "118.09301781", "edu", "", "China", "2018"], ["Large-Scale Sparse Learning From Noisy Tags for Semantic Segmentation", "Key Laboratory of Machine Perception, School of Electronics Engineering and Computer Science, Peking University, Beijing, China", "Peking University", "Peking University", "\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", "39.99223790", "116.30393816", "edu", "", "China", "2016"], ["Detection of valuable left-behind items in vehicle cabins", "Visual Information Lab, University of Bristol, UK", "University of Bristol", "University of Bristol", "Victoria Rooms, Whiteladies Road, Cliftonwood, Spike Island, Bristol, City of Bristol, South West England, England, BS8 2PY, UK", "51.45848370", "-2.60977520", "edu", "", "United Kingdom", "2017"], ["Automatic Generation of Grounded Visual Questions", "", "Tianjin University", "Tianjin University", "\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", "36.20304395", "117.05842113", "edu", "", "China", "2017"], ["Multi-Networks Joint Learning for Large-Scale Cross-Modal Retrieval", "University of Texas at San Antonio, San Antonio, TX, USA", "University of Texas at San Antonio", "University of Texas at San Antonio", "UTSA, Paseo Principal, San Antonio, Bexar County, Texas, 78249-1620, USA", "29.58333105", "-98.61944505", "edu", "", "United States", "2017"], ["Learning to Classify Fine-Grained Categories with Privileged Visual-Semantic Misalignment", "Institute of Automation, CAS Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Beijing, P.R. China", "Chinese Academy of Sciences", "Chinese Academy of Sciences", "\u4e2d\u56fd\u79d1\u5b66\u9662\u5fc3\u7406\u7814\u7a76\u6240, 16, \u6797\u8403\u8def, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100101, \u4e2d\u56fd", "40.00447950", "116.37023800", "edu", "", "China", "2017"], ["Learning a Recurrent Visual Representation for Image Caption Generation", "", "Microsoft", "Microsoft Corporation, Redmond, WA, USA", "One Microsoft Way, Redmond, WA 98052, USA", "47.64233180", "-122.13693020", "company", "", "United States", "2014"], ["Intelligent surveillance system for abandoned luggage", "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", "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", "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", "Kalkanl\u0131, G\u00fczelyurt", "35.24908700", "33.02407600", "edu", "", "Turkey", "2018"], ["Exploring Visual Relationship for Image Captioning", "", "Sun Yat-Sen University", "Sun Yat-Sen University", "\u4e2d\u5927, \u65b0\u6e2f\u897f\u8def, \u9f99\u8239\u6ed8, \u5eb7\u4e50, \u6d77\u73e0\u533a (Haizhu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510105, \u4e2d\u56fd", "23.09461185", "113.28788994", "edu", "", "China", "2018"], ["Learning Transferrable Knowledge for Semantic Segmentation with Deep Convolutional Neural Network", "", "University of Michigan", "University of Michigan", "University of Michigan, 500, Hayward Street, Ann Arbor, Washtenaw County, Michigan, 48109, USA", "42.29421420", "-83.71003894", "edu", "", "United States", "2016"], ["Deep affordance learning for single- and multiple-instance object detection", "School of Electrical and Electronic Engineering Nanyang Technological University, Singapore Block S2.1, 50 Nanyang Avenue, Singapore 639798", "Singapore", "Singapore", "Singapore", "1.35208300", "103.81983600", "edu", "", "Singapore", "2017"], ["ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation", "", "University of Washington", "University of Washington", "University of Washington, Rainier Vista, Montlake, University District, Seattle, King County, Washington, 98195, USA", "47.65432380", "-122.30800894", "edu", "", "United States", "2018"], ["A Multi-Layer Approach to Superpixel-based Higher-order Conditional Random Field for Semantic Image Segmentation", "", "University of Texas at Arlington", "University of Texas at Arlington", "University of Texas at Arlington, South Nedderman Drive, Arlington, Tarrant County, Texas, 76010, USA", "32.72836830", "-97.11201835", "edu", "", "United States", "2018"], ["Scene Image Synthesis from Natural Sentences Using Hierarchical Syntactic Analysis", "The University of Tokyo, Tokyo, Japan", "University of Tokyo", "University of Tokyo", "\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", "35.90204480", "139.93622009", "edu", "", "Japan", "2016"], ["Terahertz Image Detection with the Improved Faster Region-Based Convolutional Neural Network", "", "Xidian University", "Xidian University", "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", "34.12358250", "108.83546000", "edu", "", "China", "2018"], ["Image Classification using Transfer Learning from Siamese Networks based on Text Metadata Similarity", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "United States", "2016"], ["BubbleView: an alternative to eye-tracking for crowdsourcing image importance", "", "MIT CSAIL", "MIT CSAIL", "32 Vassar St, Cambridge, MA 02139, USA", "42.36194070", "-71.09043780", "edu", "", "United States", "2017"], ["Benchmarking and Error Diagnosis in Multi-instance Pose Estimation", "", "California Institute of Technology", "California Institute of Technology", "California Institute of Technology, San Pasqual Walk, Madison Heights, Pasadena, Los Angeles County, California, 91126, USA", "34.13710185", "-118.12527487", "edu", "", "United States", "2017"], ["Meta Networks for Neural Style Transfer", "", "Peking University", "Peking University", "\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", "39.99223790", "116.30393816", "edu", "", "China", "2017"], ["Revisiting Unreasonable Effectiveness of Data in Deep Learning Era", "", "Carnegie Mellon University", "Carnegie Mellon University", "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "37.41021930", "-122.05965487", "edu", "", "United States", "2017"], ["Semantic Amodal Segmentation", "", "Rutgers University", "Rutgers University", "Rutgers Cook Campus - North, Biel Road, New Brunswick, Middlesex County, New Jersey, 08901, USA", "40.47913175", "-74.43168868", "edu", "", "United States", "2017"], ["Deep Feature Pyramid Reconfiguration for Object Detection", "", "Tsinghua University", "Tsinghua University", "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "40.00229045", "116.32098908", "edu", "", "China", "2018"], ["Person Search via a Mask-Guided Two-Stream CNN Model", "", "University of Sydney", "University of Sydney", "USyd, Fisher Road, Camperdown, Sydney, NSW, 2006, Australia", "-33.88890695", "151.18943366", "edu", "", "Australia", "2018"], ["Employing Weak Annotations for Medical Image Analysis Problems", "", "Nagoya University", "Nagoya University", "SuperDARN (Hokkaido West), \u592a\u8f9b\u7b2c1\u652f\u7dda\u6797\u9053, \u9678\u5225\u753a, \u8db3\u5bc4\u90e1, \u5341\u52dd\u7dcf\u5408\u632f\u8208\u5c40, \u5317\u6d77\u9053, \u5317\u6d77\u9053\u5730\u65b9, \u65e5\u672c", "43.53750985", "143.60768225", "edu", "", "Japan", "2017"], ["Watching the TV Watchers", "Georgia Institute of Technology, Center for Behavioral Imaging and School of Electrical and Computer Engineering, Atlanta, GA, USA", "Georgia Institute of Technology", "Georgia Institute of Technology", "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "33.77603300", "-84.39884086", "edu", "", "United States", "2018"], ["Deep Priority Hashing", "", "Tsinghua University", "Tsinghua University", "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "40.00229045", "116.32098908", "edu", "", "China", "2018"], ["Single-Shot Bidirectional Pyramid Networks for High-Quality Object Detection", "", "Zhejiang University", "Zhejiang University", "\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", "30.19331415", "120.11930822", "edu", "", "China", "2018"], ["Neighbourhood Watch: Referring Expression Comprehension via Language-guided Graph Attention Networks", "", "University of Adelaide", "University of Adelaide", "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "-34.91892260", "138.60423668", "edu", "", "Australia", "2018"], ["Text and Object Detection on Billboards", "Faculty of Information Technology, King Mongkut\u2019s Institute of Technology Ladkrabang, Bangkok, 10520, Thailand", "Faculty of Information Technology, King Mongkut\u2019s Institute of Technology Ladkrabang, Bangkok, 10520, Thailand", "Faculty of Information Technology, King Mongkut\u2019s Institute of Technology Ladkrabang, Bangkok, 10520, Thailand", "1 Thanon Chalong Krung, Lat Krabang, Khet Lat Krabang, Krung Thep Maha Nakhon 10520, Thailand", "13.73095530", "100.78117740", "edu", "", "Thailand", "2018"], ["Parallel Attention: A Unified Framework for Visual Object Discovery Through Dialogs and Queries", "", "University of Adelaide", "University of Adelaide", "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "-34.91892260", "138.60423668", "edu", "", "Australia", "2018"], ["Learning Instance-Aware Object Detection Using Determinantal Point Processes", "", "Seoul National University", "Seoul National University", "\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", "37.26728000", "126.98411510", "edu", "", "South Korea", "2018"], ["Maximum Classifier Discrepancy for Unsupervised Domain Adaptation", "", "University of Tokyo", "University of Tokyo", "\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", "35.90204480", "139.93622009", "edu", "", "Japan", "2018"], ["Multi-oriented Scene Text Detection via Corner Localization and Region Segmentation", "", "National University of Singapore", "National University of Singapore", "NUS, Former 1936 British Outpost, Nepal Hill, Clementi, Southwest, 117542, Singapore", "1.29620180", "103.77689944", "edu", "", "Singapore", "2018"], ["Mind Your Language: Abuse and Offense Detection for Code-Switched Languages", "", "Singapore", "Singapore", "Singapore", "1.35208300", "103.81983600", "edu", "", "Singapore", "2018"], ["Efficient Video Object Segmentation via Network Modulation", "", "Google", "Google, Inc.", "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "37.42199990", "-122.08405750", "company", "Google, Mountain View, CA", "United States", "2018"], ["Strong-Weak Distribution Alignment for Adaptive Object Detection.", "", "Boston University", "Boston University", "BU, Bay State Road, Fenway, Boston, Suffolk County, Massachusetts, 02215, USA", "42.35042530", "-71.10056114", "edu", "", "United States", "2018"], ["Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi-Supervised Semantic Segmentation", "", "IBM Thomas J. Watson Research Center", "IBM Thomas J. Watson Research Center", "IBM Yorktown research lab, Adams Road, Millwood, Town of New Castle, Westchester County, New York, 10562, USA", "41.21002475", "-73.80407056", "company", "", "United States", "2018"], ["Detecting Sex From Handwritten Examples", "Fab Lab, Independent University Bangladesh, Dhaka, Bangladesh", "Independent University Bangladesh", "Fab Lab, Independent University Bangladesh, Dhaka, Bangladesh", "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", "23.81524690", "90.42796720", "edu", "", "Bangladesh", "2018"], ["Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel Concepts", "", "Australian National University", "Australian National University", "Canberra ACT 0200, Australia", "-35.27769990", "149.11852700", "edu", "", "Australia", "2018"], ["Training CNNs from Synthetic Data for Part Handling in Industrial Environments", "Mercedes-Benz-Cars Daimler AG, Stuttgart, Germany", "Mercedes-Benz-Cars Daimler AG, Stuttgart, Germany", "Mercedes-Benz-Cars Daimler AG, Stuttgart, Germany", "Stuttgarter Str. 90, 70736 Fellbach, Germany", "48.81313800", "9.26374900", "edu", "", "", "2018"], ["Query : \" A man in a red sweatshirt performing breakdance \"", "", "University of California, Berkeley", "University of California, Berkeley", "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "37.86871260", "-122.25586815", "edu", "", "United States", "2018"], ["Semantic segmentation based on iterative contraction and merging", "National Chiao Tung University, Hsinchu, Taiwan", "National Chiao Tung University", "National Chiao Tung University", "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", "24.78676765", "120.99724412", "edu", "", "Taiwan", "2017"], ["Training Constrained Deconvolutional Networks for Road Scene Semantic Segmentation", "", "Cambridge University", "Cambridge University", "University, Cambridge Road, Old Portsmouth, Portsmouth, South East, England, PO1 2HB, UK", "50.79440260", "-1.09717480", "edu", "", "United Kingdom", "2016"], ["A sequential guiding network with attention for image captioning", "", "North China Electric Power University", "North China Electric Power University", "\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", "38.87604460", "115.49738730", "edu", "", "China", "2018"], ["Discriminative Learning of Open-Vocabulary Object Retrieval and Localization by Negative Phrase Augmentation", "", "University of Tokyo", "University of Tokyo", "\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", "35.90204480", "139.93622009", "edu", "", "Japan", "2018"], ["A Vision-based Transfer Learning Approach for Recognizing Behavioral Symptoms in People with Dementia", "", "Edge Hill University", "Edge Hill University", "Edge Hill University, St Helens Road, West Lancashire, Lancs, North West England, England, L39 4QP, UK", "53.55821550", "-2.86904651", "edu", "", "United Kingdom", "2018"], ["One-shot Texture Segmentation", "", "University of T\u00fcbingen", "University of T\u00fcbingen", "Geschwister-Scholl-Platz, 72074 T\u00fcbingen, Germany", "48.52947820", "9.04377400", "edu", "", "", "2018"], ["Self-supervised Learning of Motion Capture", "", "University of Pittsburgh", "University of Pittsburgh", "University of Pittsburgh, Sutherland Drive, West Oakland, PGH, Allegheny County, Pennsylvania, 15240, USA", "40.44415295", "-79.96243993", "edu", "", "United States", "2017"], ["Visual Dialog", "", "Georgia Institute of Technology", "Georgia Institute of Technology", "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "33.77603300", "-84.39884086", "edu", "", "United States", "2017"], ["Chat-crowd: A Dialog-based Platform for Visual Layout Composition", "", "University of Virginia", "University of Virginia", "University of Virginia, Rotunda Alley, Carr's Hill, Albemarle County, Virginia, 22904-4119, USA", "38.03536820", "-78.50353220", "edu", "", "United States", "2018"], ["VISER: Visual Self-Regularization", "", "University of Washington", "University of Washington", "University of Washington, Rainier Vista, Montlake, University District, Seattle, King County, Washington, 98195, USA", "47.65432380", "-122.30800894", "edu", "", "United States", "2018"], ["BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation", "", "Microsoft", "Microsoft Corporation, Redmond, WA, USA", "One Microsoft Way, Redmond, WA 98052, USA", "47.64233180", "-122.13693020", "company", "", "United States", "2015"], ["Visual Referring Expression Recognition: What Do Systems Actually Learn?", "", "Carnegie Mellon University", "Carnegie Mellon University", "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "37.41021930", "-122.05965487", "edu", "", "United States", "2018"], ["Auto-Encoding Scene Graphs for Image Captioning", "", "Nanyang Technological University", "Nanyang Technological University", "NTU, Faculty Avenue, Jurong West, Southwest, 637460, Singapore", "1.34841040", "103.68297965", "edu", "", "Singapore", "2018"], ["Fast Object Localization Using a CNN Feature Map Based Multi-Scale Search", "", "University of California", "University of California", "Berkeley, CA, USA", "37.87189920", "-122.25853990", "edu", "", "United States", "2016"], ["Dense Image Representation with Spatial Pyramid VLAD Coding of CNN for Locally Robust Captioning", "", "University of Tokyo", "University of Tokyo", "\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", "35.90204480", "139.93622009", "edu", "", "Japan", "2016"], ["G-Distillation: Reducing Overconfident Errors on Novel Samples", "", "University of Illinois, Urbana-Champaign", "University of Illinois, Urbana-Champaign", "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "40.11116745", "-88.22587665", "edu", "", "United States", "2018"], ["Proposal Incorporating Structural Bias into Neural Networks", "", "Carnegie Mellon University", "Carnegie Mellon University", "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "37.41021930", "-122.05965487", "edu", "", "United States", "2017"], ["Image Captioning with an Intermediate Attributes Layer", "", "University of Adelaide", "University of Adelaide", "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "-34.91892260", "138.60423668", "edu", "", "Australia", "2015"], ["Weakly Supervised Attention Learning for Textual Phrases Grounding", "", "University of California, Irvine", "University of California, Irvine", "Irvine, CA 92697, USA", "33.64049520", "-117.84429620", "edu", "", "", "2018"], ["Classification of Crash and Near-Crash Events from Dashcam Videos and Telematics", "Verizon Connect Research, via Paisiello 16-20, Florence, 50144, Italy", "Verizon Connect Research, via Paisiello 16-20, Florence, 50144, Italy", "Verizon Connect Research, via Paisiello 16-20, Florence, 50144, Italy", "Via Giovanni Paisiello, 20, 50144 Firenze FI, Italy", "43.78205540", "11.23259400", "edu", "", "Italy", "2018"], ["Identifying Most Walkable Direction for Navigation in an Outdoor Environment", "", "University of Washington", "University of Washington", "University of Washington, Rainier Vista, Montlake, University District, Seattle, King County, Washington, 98195, USA", "47.65432380", "-122.30800894", "edu", "", "United States", "2017"], ["WebVision Database: Visual Learning and Understanding from Web Data", "", "ETH Zurich", "ETH Zurich", "R\u00e4mistrasse 101, 8092 Z\u00fcrich, Switzerland", "47.37631300", "8.54766990", "edu", "", "Switzerland", "2017"], ["Pose Flow: Efficient Online Pose Tracking", "", "Shanghai, China", "Shanghai, China", "Shanghai, China", "31.23039040", "121.47370210", "edu", "", "", "2018"], ["MetaAnchor: Learning to Detect Objects with Customized Anchors", "", "Fudan University", "Fudan University", "\u590d\u65e6\u5927\u5b66, 220, \u90af\u90f8\u8def, \u4e94\u89d2\u573a\u8857\u9053, \u6768\u6d66\u533a, \u4e0a\u6d77\u5e02, 200433, \u4e2d\u56fd", "31.30104395", "121.50045497", "edu", "", "China", "2018"], ["Image Description using Deep Neural Networks", "", "Rochester Institute of Technology", "Rochester Institute of Technology", "Rochester Institute of Technology (RIT), 1, Lomb Memorial Drive, Bailey, Henrietta Town, Monroe County, New York, 14623, USA", "43.08250655", "-77.67121663", "edu", "", "United States", "2016"], ["Combining Weakly and Webly Supervised Learning for Classifying Food Images", "", "SRI International", "SRI International", "SRI International Building, West 1st Street, Menlo Park, San Mateo County, California, 94025, USA", "37.45857960", "-122.17560525", "edu", "", "United States", "2017"], ["Measuring and Modifying the Intrinsic Memorability of Images", "", "MIT", "Massachusetts Institute", "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "42.35839610", "-71.09567788", "edu", "", "United States", "2015"], ["SSP: Supervised Sparse Projections for Large-Scale Retrieval in High Dimensions", "", "University of British Columbia", "University of British Columbia", "University of British Columbia, Eagles Drive, Hawthorn Place, University Endowment Lands, Metro Vancouver, British Columbia, V6T, Canada", "49.25839375", "-123.24658161", "edu", "", "Canada", "2016"], ["Semantic Video Segmentation by Gated Recurrent Flow Propagation", "", "Lund University", "Lund University", "TEM at Lund University, 9, Klostergatan, Stadsk\u00e4rnan, Centrum, Lund, Sk\u00e5ne, G\u00f6taland, 22222, Sverige", "55.70395710", "13.19020110", "edu", "", "Sweden", "2016"], ["Swap Retrieval: Retrieving Images of Cats When the Query Shows a Dog", "KULeuven, Leuven, Belgium", "KULeuven, Leuven, Belgium", "KULeuven, Leuven, Belgium", "Oude Markt 13, 3000 Leuven, Belgium", "50.87795450", "4.70029530", "edu", "", "Spain", "2015"], ["Maya Codical Glyph Segmentation: A Crowdsourcing Approach", "Idiap Research Institute, and the School of Electrical Engineering, Swiss Federal Institute of Technology in Lausanne (EPFL), Martigny, Switzerland", "IDIAP Research Institute", "IDIAP Research Institute", "Idiap Research Institute, Parking Centre du parc, Martigny, Valais/Wallis, 1920, Schweiz/Suisse/Svizzera/Svizra", "46.10923700", "7.08453549", "edu", "", "Switzerland", "2018"], ["Deep Learning for Classification of Colorectal Polyps on Whole-slide Images", "", "Dartmouth College", "Dartmouth College", "Dartmouth College, Tuck Mall, Hanover, Grafton County, New Hampshire, 03755, USA", "43.70479270", "-72.29259090", "edu", "", "United States", "2017"], ["VCI 2 R at the NTCIR-13 Lifelog-2 Lifelog Semantic Access Task", "", "Singapore", "Singapore", "Singapore", "1.35208300", "103.81983600", "edu", "", "Singapore", "2017"], ["Survey on the attention based RNN model and its applications in computer vision", "", "Delft University of Technology", "Delft University of Technology", "TU Delft, Mekelweg, TU-wijk, Delft, Zuid-Holland, Nederland, 2628, Nederland", "51.99882735", "4.37396037", "edu", "", "Netherlands", "2016"], ["Scalable, High-Quality Object Detection", "", "University of Michigan", "University of Michigan", "University of Michigan, 500, Hayward Street, Ann Arbor, Washtenaw County, Michigan, 48109, USA", "42.29421420", "-83.71003894", "edu", "", "United States", "2014"], ["An Integral Pose Regression System for the ECCV2018 PoseTrack Challenge", "", "Zhejiang University", "Zhejiang University", "\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", "30.19331415", "120.11930822", "edu", "", "China", "2018"], ["Joint Flow: Temporal Flow Fields for Multi Person Tracking", "", "University of Bonn", "University of Bonn", "Rheinische Friedrich-Wilhelms-Universit\u00e4t Bonn, Arkadenhof, Bonn-Zentrum, Stadtbezirk Bonn, Bonn, Regierungsbezirk K\u00f6ln, Nordrhein-Westfalen, 53113, Deutschland", "50.73381240", "7.10224650", "edu", "", "Germany", "2018"], ["Snuba: Automating Weak Supervision to Label Training Data", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "United States", "2018"], ["A 2 A : Attention to Attention Reasoning for Movie Question Answering", "", "Institute of Information Science", "Institute of Information Science", "\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", "25.04107280", "121.61475620", "edu", "", "Taiwan", "2018"], ["Anchor Box Optimization for Object Detection", "", "Microsoft", "Microsoft Corporation, Redmond, WA, USA", "One Microsoft Way, Redmond, WA 98052, USA", "47.64233180", "-122.13693020", "company", "", "United States", "2018"], ["Learning Representation for Scene Understanding: Epitomes, CRFs, and CNNs", "", "University of California", "University of California", "Berkeley, CA, USA", "37.87189920", "-122.25853990", "edu", "", "United States", "2015"], ["Taskonomy: Disentangling Task Transfer Learning", "", "University of California, Berkeley", "University of California, Berkeley", "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "37.86871260", "-122.25586815", "edu", "", "United States", "2018"], ["Multi-scale Location-Aware Kernel Representation for Object Detection", "", "Dalian University of Technology", "Dalian University of Technology", "\u5927\u8fde\u7406\u5de5\u5927\u5b66, \u7ea2\u51cc\u8def, \u7518\u4e95\u5b50\u533a, \u51cc\u6c34\u9547, \u7518\u4e95\u5b50\u533a / Ganjingzi, \u5927\u8fde\u5e02 / Dalian, \u8fbd\u5b81\u7701, 116023, \u4e2d\u56fd", "38.88140235", "121.52281098", "edu", "", "China", "2018"], ["Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input", "", "MIT", "Massachusetts Institute", "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "42.35839610", "-71.09567788", "edu", "", "United States", "2018"], ["Who Are Raising Their Hands ? Hand-Raiser Seeking Based on Object Detection and Pose Estimation", "", "Shanghai Jiao Tong University", "Shanghai Jiao Tong University", "\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", "31.20081505", "121.42840681", "edu", "", "China", "2018"], ["Robust Adversarial Perturbation on Deep Proposal-based Models", "", "GE Global Research Center", "GE Global Research Center", "GE Global Research Center, Aqueduct, Niskayuna, Schenectady County, New York, USA", "42.82982480", "-73.87719385", "edu", "", "United States", "2018"], ["Cross-Dataset Adaptation for Visual Question Answering", "", "University of Southern California", "University of Southern California", "University of Southern California, Watt Way, Saint James Park, LA, Los Angeles County, California, 90089, USA", "34.02241490", "-118.28634407", "edu", "", "United States", "2018"], ["Grounded Objects and Interactions for Video Captioning", "", "Georgia Institute of Technology", "Georgia Institute of Technology", "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "33.77603300", "-84.39884086", "edu", "", "United States", "2017"], ["Priming Neural Networks", "", "York University", "York University", "York University, Keele Campus, Campus Walk, North York, Toronto, Ontario, M3J 2S5, Canada", "43.77439110", "-79.50481085", "edu", "", "Canada", "2018"], ["Neural Baby Talk", "", "Georgia Institute of Technology", "Georgia Institute of Technology", "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "33.77603300", "-84.39884086", "edu", "", "United States", "2018"], ["End-to-End Recovery of Human Shape and Pose", "", "University of California, Berkeley", "University of California, Berkeley", "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "37.86871260", "-122.25586815", "edu", "", "United States", "2018"], ["HashNet: Deep Learning to Hash by Continuation", "", "University of Illinois at Chicago", "University of Illinois at Chicago", "University of Illinois at Chicago, West Taylor Street, Greektown, Chicago, Cook County, Illinois, 60607, USA", "41.86898915", "-87.64856256", "edu", "", "United States", "2017"], ["Associative Embedding: End-to-End Learning for Joint Detection and Grouping", "", "University of Michigan", "University of Michigan", "University of Michigan, 500, Hayward Street, Ann Arbor, Washtenaw County, Michigan, 48109, USA", "42.29421420", "-83.71003894", "edu", "", "United States", "2017"], ["Transforming sensor data to the image domain for deep learning \u2014 An application to footstep detection", "", "University of Fribourg", "University of Fribourg", "Avenue de l'Europe 20, 1700 Fribourg, Switzerland", "46.80635700", "7.15200600", "edu", "", "Switzerland", "2017"], ["Towards Deep Cellular Phenotyping in Placental Histology", "", "University of Oxford", "University of Oxford", "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "51.75345380", "-1.25400997", "edu", "", "United Kingdom", "2018"], ["People and Vehicles in Danger - A Fire and Flood Detection System in Social Media", "CERTH-ITI, Thessaloniki, Greece", "CERTH-ITI, Thessaloniki, Greece", "CERTH-ITI, Thessaloniki, Greece", "Thermi 570 01, Greece", "40.56676110", "22.99801470", "edu", "", "Greece", "2018"], ["Personalized Serious Games for Cognitive Intervention with Lifelog Visual Analytics", "Singapore Bioimaging Consortium, A*STAR, Singapore, Singapore", "Singapore Bioimaging Consortium, A*STAR, Singapore, Singapore", "Singapore Bioimaging Consortium, A*STAR, Singapore, Singapore", "11 Biopolis Way, Singapore 138667", "1.30452010", "103.79165150", "edu", "", "Singapore", "2018"], ["From UI Design Image to GUI Skeleton: A Neural Machine Translator to Bootstrap Mobile GUI Implementation", "Nanyang Technological University, Singapore", "Nanyang Technological University", "Nanyang Technological University", "NTU, Faculty Avenue, Jurong West, Southwest, 637460, Singapore", "1.34841040", "103.68297965", "edu", "", "Singapore", "2018"], ["Selective Refinement Network for High Performance Face Detection", "", "University of Chinese Academy of Sciences", "University of Chinese Academy of Sciences", "University of Chinese Academy of Sciences, UCAS, Yuquanlu, \u7389\u6cc9\u8def, \u7530\u6751, \u6d77\u6dc0\u533a, 100049, \u4e2d\u56fd", "39.90828040", "116.24585270", "edu", "", "China", "2018"], ["Describing Common Human Visual Actions in Images", "", "California Institute of Technology", "California Institute of Technology", "California Institute of Technology, San Pasqual Walk, Madison Heights, Pasadena, Los Angeles County, California, 91126, USA", "34.13710185", "-118.12527487", "edu", "", "United States", "2015"], ["Person Retrieval in Surveillance Video using Height, Color and Gender", "", "Ahmedabad University", "Ahmedabad University", "School of Science and Technology, University Road, Gurukul, Gulbai tekra, Ahmedabad, Ahmedabad District, Gujarat, 380001, India", "23.03787430", "72.55180046", "edu", "", "India", "2018"], ["A Robot Localization Framework Using CNNs for Object Detection and Pose Estimation", "", "Otto von Guericke University", "Otto von Guericke University", "Otto-von-Guericke-Universit\u00e4t Magdeburg, 2, Universit\u00e4tsplatz, Kr\u00f6kentorviertel/Breiter Weg NA, Alte Neustadt, Magdeburg, Sachsen-Anhalt, 39106, Deutschland", "52.14005065", "11.64471248", "edu", "", "Germany", "2018"], ["Automatic Concept Discovery from Parallel Text and Visual Corpora", "", "Tsinghua University", "Tsinghua University", "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "40.00229045", "116.32098908", "edu", "", "China", "2015"], ["Image Captioning With Visual-Semantic Double Attention", "School of Electronics and Information Technology, Sun Yat-Sen University, Guangdong, People's Republic of China", "Sun Yat-Sen University", "Sun Yat-Sen University", "\u4e2d\u5927, \u65b0\u6e2f\u897f\u8def, \u9f99\u8239\u6ed8, \u5eb7\u4e50, \u6d77\u73e0\u533a (Haizhu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510105, \u4e2d\u56fd", "23.09461185", "113.28788994", "edu", "", "China", "2019"], ["Understanding Fake Faces", "", "Waseda University", "Waseda University", "\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", "33.88987280", "130.70856205", "edu", "", "Japan", "2018"], ["SketchyScene: Richly-Annotated Scene Sketches", "", "Simon Fraser University", "Simon Fraser University", "SFU Burnaby, South Campus Road, Barnet, Burnaby, Metro Vancouver, British Columbia, V5A 4X6, Canada", "49.27674540", "-122.91777375", "edu", "", "Canada", "2018"], ["Much Ado About Time: Exhaustive Annotation of Temporal Data", "", "Carnegie Mellon University", "Carnegie Mellon University", "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "37.41021930", "-122.05965487", "edu", "", "United States", "2016"], ["Mainstream: Dynamic Stem-Sharing for Multi-Tenant Video Processing", "", "Carnegie Mellon University", "Carnegie Mellon University", "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "37.41021930", "-122.05965487", "edu", "", "United States", "2018"], ["A Multi-Oriented Scene Text Detector with Position-Sensitive Segmentation", "University of Chinese Academy of Sciences, Beijing, China", "University of Chinese Academy of Sciences", "University of Chinese Academy of Sciences", "University of Chinese Academy of Sciences, UCAS, Yuquanlu, \u7389\u6cc9\u8def, \u7530\u6751, \u6d77\u6dc0\u533a, 100049, \u4e2d\u56fd", "39.90828040", "116.24585270", "edu", "", "China", "2018"], ["Simple Baselines for Human Pose Estimation and Tracking", "", "University of Electronic Science and Technology of China", "University of Electronic Science and Technology of China", "Columbus, OH 43210, USA", "40.01419050", "-83.03091430", "edu", "", "United States", "2018"], ["Image describing based on bidirectional LSTM and improved sequence sampling", "College of Computer Science. Chongqing University, Chongqing, China", "Chongqing University", "Chongqing University", "\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", "29.50841740", "106.57858552", "edu", "", "China", "2017"], ["Learning from PhotoShop Operation Videos : the PSOV Dataset", "", "University of California", "University of California", "Berkeley, CA, USA", "37.87189920", "-122.25853990", "edu", "", "United States", "2018"], ["Deep conditional neural network for image segmentation", "Department of Computing, The Hong Kong Polytechnic University", "Hong Kong Polytechnic University", "Hong Kong Polytechnic University", "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", "22.30457200", "114.17976285", "edu", "", "China", "2016"], ["Human Centred Object Co-Segmentation", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "United States", "2016"], ["Image Captioning with both Object and Scene Information", "Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China", "Chinese Academy of Sciences", "Chinese Academy of Sciences", "\u4e2d\u56fd\u79d1\u5b66\u9662\u5fc3\u7406\u7814\u7a76\u6240, 16, \u6797\u8403\u8def, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100101, \u4e2d\u56fd", "40.00447950", "116.37023800", "edu", "", "China", "2016"], ["SuperNeurons: FFT-based Gradient Sparsification in the Distributed Training of Deep Neural Networks", "", "Brown University", "Brown University", "Brown University, Waterman Street, College Hill, Providence, Bristol, Rhode Island, 02912, USA", "41.82686820", "-71.40123146", "edu", "", "United States", "2018"], ["A Data Driven Approach for Compound Figure Separation Using Convolutional Neural Networks", "", "Indiana University", "Indiana University", "Indiana University East, West Cart Road, Richmond, Wayne County, Indiana, 47374, USA", "39.86948105", "-84.87956905", "edu", "", "United States", "2017"], ["Intention Oriented Image Captions with Guiding Objects", "", "Tsinghua University", "Tsinghua University", "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "40.00229045", "116.32098908", "edu", "", "China", "2018"], ["Aligning Books and Movies: Towards Story-Like Visual Explanations by Watching Movies and Reading Books", "", "MIT", "Massachusetts Institute", "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "42.35839610", "-71.09567788", "edu", "", "United States", "2015"], ["Multi-scale Patch Aggregation (MPA) for Simultaneous Detection and Segmentation", "", "Chinese University of Hong Kong", "Chinese University of Hong Kong", "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "22.41626320", "114.21093180", "edu", "", "China", "2016"], ["Interpretable Explanations of Black Boxes by Meaningful Perturbation", "", "University of Oxford", "University of Oxford", "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "51.75345380", "-1.25400997", "edu", "", "United Kingdom", "2017"], ["A Restricted Visual Turing Test for Deep Scene and Event Understanding", "", "University of California, Los Angeles", "University of California, Los Angeles", "200 UCLA, Medical Plaza Driveway Suite 540, Los Angeles, CA 90095, USA", "34.06877880", "-118.44500940", "edu", "", "United States", "2015"], ["Euphrates: Algorithm-SoC Co-Design for Low-Power Mobile Continuous Vision", "", "Georgia Institute of Technology", "Georgia Institute of Technology", "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "33.77603300", "-84.39884086", "edu", "", "United States", "2018"], ["Similarity Reasoning over Semantic Context\u2013graphs", "", "Brown University", "Brown University", "Brown University, Waterman Street, College Hill, Providence, Bristol, Rhode Island, 02912, USA", "41.82686820", "-71.40123146", "edu", "", "United States", "2015"], ["Multimodal Differential Network for Visual Question Generation", "", "Indian Institute of Technology Delhi", "IIIT-Delhi, India", "IIIT-Delhi, Mathura Road, Friends Colony, South East Delhi, Delhi, 110020, India", "28.54632595", "77.27325504", "edu", "", "India", "2018"], ["Learning Spatial Regularization with Image-Level Supervisions for Multi-label Image Classification", "", "University of Sydney", "University of Sydney", "USyd, Fisher Road, Camperdown, Sydney, NSW, 2006, Australia", "-33.88890695", "151.18943366", "edu", "", "Australia", "2017"], ["Visual Question Reasoning on General Dependency Tree", "", "Sun Yat-Sen University", "Sun Yat-Sen University", "\u4e2d\u5927, \u65b0\u6e2f\u897f\u8def, \u9f99\u8239\u6ed8, \u5eb7\u4e50, \u6d77\u73e0\u533a (Haizhu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510105, \u4e2d\u56fd", "23.09461185", "113.28788994", "edu", "", "China", "2018"], ["Interactive Demonstration of Probabilistic Predicates", "University of Washington &Microsoft, Seattle, WA, USA", "University of Washington", "University of Washington", "University of Washington, Rainier Vista, Montlake, University District, Seattle, King County, Washington, 98195, USA", "47.65432380", "-122.30800894", "edu", "", "United States", "2018"], ["A Dataset and Exploration of Models for Understanding Video Data through Fill-in-the-Blank Question-Answering", "", "Polytechnique Montreal", "Polytechnique Montr\u00b4eal", "2900 Boulevard Edouard-Montpetit, Montr\u00e9al, QC H3T 1J4, Canada", "45.50438400", "-73.61288290", "edu", "Polytechnique Montreal, Montreal, Quebec, Canada", "Canada", "2017"], ["Are You Talking to Me? Reasoned Visual Dialog Generation Through Adversarial Learning", "", "Northwestern Polytechnical University", "Northwestern Polytechnical University", "\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", "34.24691520", "108.91061982", "edu", "", "China", "2018"], ["MovieQA: Understanding Stories in Movies through Question-Answering", "", "Karlsruhe Institute of Technology", "Karlsruhe Institute of Technology", "KIT, Leopoldshafener Allee, Linkenheim, Linkenheim-Hochstetten, Landkreis Karlsruhe, Regierungsbezirk Karlsruhe, Baden-W\u00fcrttemberg, 76351, Deutschland", "49.10184375", "8.43312560", "edu", "", "Germany", "2016"], ["ReDMark: Framework for Residual Diffusion Watermarking on Deep Networks", "", "University of Queensland", "University of Queensland", "University of Queensland, University Drive, Hill End, St Lucia, Brisbane, QLD, 4072, Australia", "-27.49741805", "153.01316956", "edu", "", "Australia", "2018"], ["Transitive Invariance for Self-Supervised Visual Representation Learning", "", "Carnegie Mellon University", "Carnegie Mellon University", "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "37.41021930", "-122.05965487", "edu", "", "United States", "2017"], ["Using Segmentation to Predict the Absence of Occluded Parts", "", "University of California", "University of California", "Berkeley, CA, USA", "37.87189920", "-122.25853990", "edu", "", "United States", "2015"], ["LabelBank: Revisiting Global Perspectives for Semantic Segmentation", "", "Simon Fraser University", "Simon Fraser University", "SFU Burnaby, South Campus Road, Barnet, Burnaby, Metro Vancouver, British Columbia, V5A 4X6, Canada", "49.27674540", "-122.91777375", "edu", "", "Canada", "2017"], ["Application of a Hybrid Model Based on a Convolutional Auto-Encoder and Convolutional Neural Network in Object-Oriented Remote Sensing Classification", "", "Wuhan University of Technology", "Wuhan University of Technology", "\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", "30.60903415", "114.35142840", "edu", "", "China", "2018"], ["Visual Storytelling", "", "Virginia Tech", "Virginia Tech", "Blacksburg, VA 24061, USA", "37.22838430", "-80.42341670", "edu", "", "United States", "2016"], ["Boundary aware image segmentation with unsupervised mixture models", "Image Analysis Group, Technical University Dortmund, Otto-Hahn-Str. 4, 44227 Dortmund, Germany", "Technical University Dortmund", "Image Analysis Group, Technical University Dortmund, Otto-Hahn-Str. 4, 44227 Dortmund, Germany", "Emil-Figge-Stra\u00dfe 50, 44227 Dortmund, Germany", "51.49219020", "7.41413620", "edu", "", "Germany", "2017"], ["Edge-Cloud Collaborative Processing for Intelligent Internet of Things: A Case Study on Smart Surveillance", "Georgia Institute of Technology", "Georgia Institute of Technology", "Georgia Institute of Technology", "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "33.77603300", "-84.39884086", "edu", "", "United States", "2018"], ["Uncovering the Temporal Context for Video Question Answering", "SCS, Carnegie Mellon University, Pittsburgh, USA", "Carnegie Mellon University", "Carnegie Mellon University", "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "37.41021930", "-122.05965487", "edu", "", "United States", "2017"], ["Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks", "", "Cornell University", "Cornell University", "Cornell University, Forest Home Drive, Forest Home, Tompkins County, New York, 14853, USA", "42.45055070", "-76.47835130", "edu", "", "United States", "2016"], ["Deep learning-based human head detection and extraction for robotic portrait drawing", "Shenzhen Academy of Robotics, Shenzhen, Guangdong, China", "Shenzhen Academy of Robotics, Shenzhen, Guangdong, China", "Shenzhen Academy of Robotics, Shenzhen, Guangdong, China", "Shenzhen, Guangdong, China", "22.54309600", "114.05786500", "edu", "", "China", "2017"], ["On the Origin of Deep Learning On the Origin of Deep Learning", "", "Carnegie Mellon University", "Carnegie Mellon University", "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "37.41021930", "-122.05965487", "edu", "", "United States", "2017"], ["A survey on deep neural network-based image captioning", "School of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, People\u2019s Republic of China", "Shandong University", "Shandong University", "\u5c71\u4e1c\u5927\u5b66, \u6cf0\u5b89\u8857, \u9ccc\u5c71\u536b\u8857\u9053, \u5373\u58a8\u533a, \u9752\u5c9b\u5e02, \u5c71\u4e1c\u7701, 266200, \u4e2d\u56fd", "36.36934730", "120.67381800", "edu", "", "China", "2018"], ["Leveraging Visual Question Answering for Image-Caption Ranking", "", "Virginia Tech", "Virginia Tech", "Blacksburg, VA 24061, USA", "37.22838430", "-80.42341670", "edu", "", "United States", "2016"], ["An object based graph representation for video comparison", "Dept. of Electrical and Computer Engineering, NYU Tandon School of Engineering, New York, USA", "Chongqing University of Technology", "Chongqing University of Technology, China", "69 Hongguang Ave, Banan Qu, Chongqing Shi, China", "29.45832600", "106.52994700", "edu", "", "China", "2017"], ["Phrase Localization and Visual Relationship Detection with Comprehensive Image-Language Cues", "", "University of Illinois, Urbana-Champaign", "University of Illinois, Urbana-Champaign", "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "40.11116745", "-88.22587665", "edu", "", "United States", "2017"], ["Deep image representations using caption generators", "", "Indian Institute of Science Bangalore", "Indian Institute of Science Bangalore", "IISc, Gulmohar Marg, RMV Stage II - 1st Block, Aramane Nagara Ward, West Zone, Bengaluru, Bangalore Urban, Karnataka, 560012, India", "13.02223470", "77.56718325", "edu", "", "India", "2017"], ["Convolution Neural Networks With Two Pathways for Image Style Recognition", "Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China", "Tsinghua University", "Tsinghua University", "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "40.00229045", "116.32098908", "edu", "", "China", "2017"], ["Natural Language Object Retrieval", "", "University of Massachusetts", "University of Massachusetts", "University of Massachusetts, Hicks Way, Amherst, Hampshire, Massachusetts, 01003, USA", "42.38897850", "-72.52869870", "edu", "", "United States", "2016"], ["Watch and learn: Semi-supervised learning of object detectors from videos", "", "Robotics Institute", "Robotics Institute", "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", "13.65450525", "100.49423171", "edu", "", "Thailand", "2015"], ["Advanced Deep-Learning Techniques for Salient and Category-Specific Object Detection: A Survey", "Northwestern Polytechnical University, Xi'an, 710072, China", "Northwestern Polytechnical University", "Northwestern Polytechnical University", "\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", "34.24691520", "108.91061982", "edu", "", "China", "2018"], ["Word Prior Detection Segmentation Input \" The left guy \" Image : Query : a guy left the youth Energy", "", "IBM Thomas J. Watson Research Center", "IBM Thomas J. Watson Research Center", "IBM Yorktown research lab, Adams Road, Millwood, Town of New Castle, Westchester County, New York, 10562, USA", "41.21002475", "-73.80407056", "company", "", "United States", "2017"], ["Image Caption with Synchronous Cross-Attention", "Beijing University of Posts and Telecommunications, Beijing, China", "Beijing University of Posts and Telecommunications", "Beijing University of Posts and Telecommunications", "\u5317\u4eac\u90ae\u7535\u5927\u5b66, \u897f\u571f\u57ce\u8def, \u6d77\u6dc0\u533a, \u5317\u4eac\u5e02, 100082, \u4e2d\u56fd", "39.96014880", "116.35193921", "edu", "", "China", "2017"], ["Exploring confusing scene classes for the places dataset: Insights and solutions", "Department of Electrical Engineering, University of Southern California, Los Angeles, CA 90089, U.S.A.", "University of Southern California", "University of Southern California", "University of Southern California, Watt Way, Saint James Park, LA, Los Angeles County, California, 90089, USA", "34.02241490", "-118.28634407", "edu", "", "United States", "2017"], ["Adversarial Ranking for Language Generation", "", "University of Washington", "University of Washington", "University of Washington, Rainier Vista, Montlake, University District, Seattle, King County, Washington, 98195, USA", "47.65432380", "-122.30800894", "edu", "", "United States", "2017"], ["3D-SSD: Learning Hierarchical Features from RGB-D Images for Amodal 3D Object Detection", "", "Zhejiang University", "Zhejiang University", "\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", "30.19331415", "120.11930822", "edu", "", "China", "2017"], ["Neuron-level Selective Context Aggregation for Scene Segmentation", "", "Shandong University", "Shandong University", "\u5c71\u4e1c\u5927\u5b66, \u6cf0\u5b89\u8857, \u9ccc\u5c71\u536b\u8857\u9053, \u5373\u58a8\u533a, \u9752\u5c9b\u5e02, \u5c71\u4e1c\u7701, 266200, \u4e2d\u56fd", "36.36934730", "120.67381800", "edu", "", "China", "2017"], ["Factors Influencing The Performance of Image Captioning Model: An Evaluation", "SoICT, HUST and School of Information and Communication Technology, Hanoi University of Science and Technology, Hanoi, Vietnam", "Hanoi University of Science and Technology", "Hanoi University of Science and Technology", "HUST, Tr\u1ea7n \u0110\u1ea1i Ngh\u0129a, Hai B\u00e0 Tr\u01b0ng, H\u00e0 N\u1ed9i, 10999, Vietnam", "21.00395200", "105.84360183", "edu", "", "Vietnam", "2016"], ["Accurate License Plate Recognition and Super-Resolution Using a Generative Adversarial Networks on Traffic Surveillance Video", "Gwangju Institute of Science and Technology", "Gwangju Institute of Science and Technology", "Gwangju Institute of Science and Technology", "123 Cheomdangwagi-ro, Oryong-dong, Buk-gu, Kwangju, South Korea", "35.22652880", "126.83998700", "edu", "", "", "2018"], ["Progressive Neural Architecture Search", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "United States", "2018"], ["Beyond Domain Adaptation: Unseen Domain Encapsulation via Universal Non-volume Preserving Models", "", "University of Illinois, Urbana-Champaign", "University of Illinois, Urbana-Champaign", "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "40.11116745", "-88.22587665", "edu", "", "United States", "2018"], ["From Known to the Unknown: Transferring Knowledge to Answer Questions about Novel Visual and Semantic Concepts", "", "Australian National University", "Australian National University", "Canberra ACT 0200, Australia", "-35.27769990", "149.11852700", "edu", "", "Australia", "2018"], ["Weakly Supervised Salient Object Detection Using Image Labels", "", "SenseTime", "SenseTime", "China, Beijing Shi, Haidian Qu, WuDaoKou, Zhongguancun E Rd, 1\u53f7-7", "39.99300800", "116.32988200", "company", "1 Zhongguancun E Rd, Haidian Qu, China", "China", "2018"], ["Reducing Network Agnostophobia", "", "University of Colorado, Colorado Springs", "University of Colorado Colorado Springs", "Main Hall, The Spine, Colorado Springs, El Paso County, Colorado, 80907, USA", "38.89207560", "-104.79716389", "edu", "", "United States", "2018"], ["DistInit: Learning Video Representations without a Single Labeled Video", "", "Carnegie Mellon University", "Carnegie Mellon University", "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "37.41021930", "-122.05965487", "edu", "", "United States", "2019"], ["Image2song: Song Retrieval via Bridging Image Content and Lyric Words", "", "Northwestern Polytechnical University", "Northwestern Polytechnical University", "\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", "34.24691520", "108.91061982", "edu", "", "China", "2017"], ["Exploring Person Context and Local Scene Context for Object Detection.", "", "University of California, Berkeley", "University of California, Berkeley", "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "37.86871260", "-122.25586815", "edu", "", "United States", "2015"], ["An efficient framework for learning sentence representations", "", "University of Michigan", "University of Michigan", "University of Michigan, 500, Hayward Street, Ann Arbor, Washtenaw County, Michigan, 48109, USA", "42.29421420", "-83.71003894", "edu", "", "United States", "2018"], ["Semantic Correspondence: A Hierarchical Approach", "", "Queensland University of Technology", "Queensland University of Technology", "Queensland University of Technology, Macgregor Lane, Merthyr, South Brisbane, Brisbane, QLD, 4000, Australia", "-27.47715625", "153.02841004", "edu", "", "Australia", "2018"], ["Contextual Memory Trees", "", "Microsoft", "Microsoft Corporation, Redmond, WA, USA", "One Microsoft Way, Redmond, WA 98052, USA", "47.64233180", "-122.13693020", "company", "", "United States", "2018"], ["Object Referring in Videos with Language and Human Gaze", "", "ETH Zurich", "ETH Zurich", "R\u00e4mistrasse 101, 8092 Z\u00fcrich, Switzerland", "47.37631300", "8.54766990", "edu", "", "Switzerland", "2018"], ["Adding object detection skills to visual dialogue agents", "", "University of Amsterdam", "University of Amsterdam", "Institute for Logic, Language and Computation (ILLC), 107, Science Park, Oost-Watergraafsmeer, Amsterdam, Oost, Amsterdam, Noord-Holland, Nederland, 1098XG, Nederland", "52.35536550", "4.95016440", "edu", "", "Netherlands", "2018"], ["Generate, Segment and Replace: Towards Generic Manipulation Segmentation.", "", "University of Maryland", "University of Maryland", "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "39.28996850", "-76.62196103", "edu", "", "United States", "2018"], ["Grasp2Vec: Learning Object Representations from Self-Supervised Grasping", "", "University of California, Berkeley", "University of California, Berkeley", "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "37.86871260", "-122.25586815", "edu", "", "United States", "2018"], ["Self-view Grounding Given a Narrated 360{\\deg} Video", "", "Microsoft Research Asia", "Microsoft Research Asia", "1 Memorial Dr, Cambridge, MA 02142, USA", "42.36142560", "-71.08120920", "company", "", "United States", "2017"], ["Learning RoI Transformer for Detecting Oriented Objects in Aerial Images", "", "Wuhan University of Technology", "Wuhan University of Technology", "\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", "30.60903415", "114.35142840", "edu", "", "China", "2018"], ["Survey of Recent Advances in Visual Question Answering", "", "Adobe Systems", "Adobe Systems", "343 Preston St, Ottawa, ON K1S 1N4, Canada", "45.40242130", "-75.70955410", "edu", "", "South Korea", "2017"], ["Richer Semantic Visual and Language Representation for Video Captioning", "Tongji University, Shanghai, China", "Tongji University", "Tongji University", "\u540c\u6d4e\u5927\u5b66, 1239, \u56db\u5e73\u8def, \u6c5f\u6e7e, \u8679\u53e3\u533a, \u4e0a\u6d77\u5e02, 200092, \u4e2d\u56fd", "31.28473925", "121.49694909", "edu", "", "China", "2017"], ["Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments", "", "Cornell University", "Cornell University", "Cornell University, Forest Home Drive, Forest Home, Tompkins County, New York, 14853, USA", "42.45055070", "-76.47835130", "edu", "", "United States", "2018"], ["Visual attribute transfer through deep image analogy", "", "Microsoft", "Microsoft Corporation, Redmond, WA, USA", "One Microsoft Way, Redmond, WA 98052, USA", "47.64233180", "-122.13693020", "company", "", "United States", "2017"], ["Towards Improved Design and Evaluation of Epileptic Seizure Predictors", "Mayo Systems Electrophysiology Laboratory, Departments of Neurology and Biomedical EngineeringMayo Clinic", "TU Berlin", "TU Berlin", "Franklinstra\u00dfe 28-29, 10587 Berlin, Germany", "52.51806410", "13.32504250", "edu", "Franklinstr. 28/29, 10587, Germany", "Germany", "2018"], ["PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentation", "", "RWTH Aachen University", "RWTH Aachen University", "RWTH Aachen, Mies-van-der-Rohe-Stra\u00dfe, K\u00f6nigsh\u00fcgel, Aachen-Mitte, Aachen, St\u00e4dteregion Aachen, Regierungsbezirk K\u00f6ln, Nordrhein-Westfalen, 52074, Deutschland", "50.77917030", "6.06728733", "edu", "", "Germany", "2018"], ["Explicit Bias Discovery in Visual Question Answering Models", "", "University of Maryland", "University of Maryland", "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "39.28996850", "-76.62196103", "edu", "", "United States", "2018"], ["AUTOMATIC IMAGE ANNOTATION MODEL USING LSTM APPROACH", "", "Varanasi", "Varanasi", "Varanasi, Uttar Pradesh, India", "25.31764520", "82.97391440", "edu", "", "India", "2017"], ["Mo 2 Cap 2 : Real-time Mo bile 3 D Mo tion Cap ture with a Cap-mounted Fisheye Camera", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "United States", "2018"], ["Stroke Controllable Fast Style Transfer with Adaptive Receptive Fields", "", "University of Sydney", "University of Sydney", "USyd, Fisher Road, Camperdown, Sydney, NSW, 2006, Australia", "-33.88890695", "151.18943366", "edu", "", "Australia", "2018"], ["Learning Visually Grounded Sentence Representations", "", "University of California, Berkeley", "University of California, Berkeley", "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "37.86871260", "-122.25586815", "edu", "", "United States", "2018"], ["Learning 3 D Scene Synthesis from Annotated RGB-D Images", "", "Zhejiang University", "Zhejiang University", "\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", "30.19331415", "120.11930822", "edu", "", "China", "2016"], ["Bottom-up Pose Estimation of Multiple Person with Bounding Box Constraint", "", "Zhejiang University", "Zhejiang University", "\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", "30.19331415", "120.11930822", "edu", "", "China", "2018"], ["Transferable Interactiveness Prior for Human-Object Interaction Detection", "", "Shanghai Jiao Tong University", "Shanghai Jiao Tong University", "\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", "31.20081505", "121.42840681", "edu", "", "China", "2018"], ["A Fully Convolutional Two-Stream Fusion Network for Interactive Image Segmentation", "", "Loughborough University", "Loughborough University", "Computer Science, University Road, Charnwood, Leicestershire, East Midlands, England, LE11 3TP, UK", "52.76635770", "-1.22924610", "edu", "", "United Kingdom", "2019"], ["A Corpus for Reasoning About Natural Language Grounded in Photographs", "", "University of Maryland", "University of Maryland", "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "39.28996850", "-76.62196103", "edu", "", "United States", "2018"], ["Persuasive Faces: Generating Faces in Advertisements", "", "University of Pittsburgh", "University of Pittsburgh", "University of Pittsburgh, Sutherland Drive, West Oakland, PGH, Allegheny County, Pennsylvania, 15240, USA", "40.44415295", "-79.96243993", "edu", "", "United States", "2018"], ["Video Object Segmentation with Re-identification", "", "SenseTime", "SenseTime", "China, Beijing Shi, Haidian Qu, WuDaoKou, Zhongguancun E Rd, 1\u53f7-7", "39.99300800", "116.32988200", "company", "1 Zhongguancun E Rd, Haidian Qu, China", "China", "2017"], ["POL-LWIR Vehicle Detection: Convolutional Neural Networks Meet Polarised Infrared Sensors", "", "Heriot-Watt University", "Heriot-Watt University", "Heriot-Watt University - Edinburgh Campus, Third Gait, Currie, Gogarbank, City of Edinburgh, Scotland, EH14 4AS, UK", "55.91029135", "-3.32345777", "edu", "", "United Kingdom", "2018"], ["Videos as Space-Time Region Graphs", "", "Robotics Institute", "Robotics Institute", "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", "13.65450525", "100.49423171", "edu", "", "Thailand", "2018"], ["Object Detection via End-to-End Integration of Aspect Ratio and Context Aware Part-based Models and Fully Convolutional Networks", "", "North Carolina State University", "North Carolina State University", "North Carolina State University, Oval Drive, West Raleigh, Raleigh, Wake County, North Carolina, 27695, USA", "35.77184965", "-78.67408695", "edu", "", "United States", "2016"], ["Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation", "", "Princeton University", "Princeton University", "Lot 9, University Place, Princeton Township, Mercer County, New Jersey, 08540, USA", "40.34829285", "-74.66308325", "edu", "", "United States", "2019"], ["Face2Text: Collecting an Annotated Image Description Corpus for the Generation of Rich Face Descriptions", "", "University of Copenhagen", "University of Copenhagen", "K\u00f8benhavns Universitet, Krystalgade, K\u00f8dbyen, Vesterbro, K\u00f8benhavn, K\u00f8benhavns Kommune, Region Hovedstaden, 1165, Danmark", "55.68015020", "12.57232700", "edu", "", "Denmark", "2018"], ["Textually Enriched Neural Module Networks for Visual Question Answering", "", "Carnegie Mellon University", "Carnegie Mellon University", "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "37.41021930", "-122.05965487", "edu", "", "United States", "2018"], ["Slum Segmentation and Change Detection : A Deep Learning Approach", "", "Indian Institute of Science Bangalore", "Indian Institute of Science Bangalore", "IISc, Gulmohar Marg, RMV Stage II - 1st Block, Aramane Nagara Ward, West Zone, Bengaluru, Bangalore Urban, Karnataka, 560012, India", "13.02223470", "77.56718325", "edu", "", "India", "2018"], ["Input Reconstruction Side and top down view Part Segmentation Input Reconstruction Side and top down view Part Segmentation", "", "University of California, Berkeley", "University of California, Berkeley", "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "37.86871260", "-122.25586815", "edu", "", "United States", "2017"], ["Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning", "", "Cornell University", "Cornell University", "Cornell University, Forest Home Drive, Forest Home, Tompkins County, New York, 14853, USA", "42.45055070", "-76.47835130", "edu", "", "United States", "2018"], ["Gather-Excite : Exploiting Feature Context in Convolutional Neural Networks", "", "University of Oxford", "University of Oxford", "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "51.75345380", "-1.25400997", "edu", "", "United Kingdom", "2018"], ["Adversarial Removal of Gender from Deep Image Representations", "", "University of Virginia", "University of Virginia", "University of Virginia, Rotunda Alley, Carr's Hill, Albemarle County, Virginia, 22904-4119, USA", "38.03536820", "-78.50353220", "edu", "", "United States", "2018"], ["Regularizing Deep Networks by Modeling and Predicting Label Structure", "", "Toyota Technological Institute at Chicago", "Toyota Technological Institute at Chicago", "6045 S Kenwood Ave, Chicago, IL 60637, USA", "41.78469820", "-87.59258480", "company", "", "United States", "2018"], ["Probability-based Detection Quality (PDQ): A Probabilistic Approach to Detection Evaluation", "", "Queensland University of Technology (QUT)", "Queensland University of Technology (QUT)", "2 George St, Brisbane City QLD 4000, Australia", "-27.47735700", "153.02841500", "edu", "", "Australia", "2018"], ["Receptive Field Block Net for Accurate and Fast Object Detection", "", "Beihang University", "Beihang University", "\u5317\u4eac\u822a\u7a7a\u822a\u5929\u5927\u5b66, 37, \u5b66\u9662\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100083, \u4e2d\u56fd", "39.98083330", "116.34101249", "edu", "", "China", "2018"], ["SPNet: Superpixel Pyramid Network for Scene Parsing", "Faculty of Information Technology, Beijing University of Technologyy, Beijing, 100124, China", "Beijing University of Technologyy", "Faculty of Information Technology, Beijing University of Technologyy, Beijing, 100124, China", "Chaoyang, China, 100124", "39.87161100", "116.47952900", "edu", "", "China", "2018"], ["Unsupervised Learning of Important Objects from First-Person Videos", "", "University of Pennsylvania", "University of Pennsylvania", "Penn Museum, 3260, South Street, University City, Philadelphia, Philadelphia County, Pennsylvania, 19104, USA", "39.94923440", "-75.19198985", "edu", "", "United States", "2017"], ["Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks", "", "University of Oxford", "University of Oxford", "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "51.75345380", "-1.25400997", "edu", "", "United Kingdom", "2018"], ["Open-vocabulary Phrase Detection", "", "Boston University", "Boston University", "BU, Bay State Road, Fenway, Boston, Suffolk County, Massachusetts, 02215, USA", "42.35042530", "-71.10056114", "edu", "", "United States", "2018"], ["SHPD: Surveillance Human Pose Dataset and Performance Evaluation for Coarse-Grained Pose Estimation", "School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China", "Shanghai Jiao Tong University", "Shanghai Jiao Tong University", "\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", "31.20081505", "121.42840681", "edu", "", "China", "2018"], ["Weakly Supervised Vehicle Detection in Satellite Images via Multiple Instance Ranking", "Fujian Key Laboratory of Sensing and Computing for Smart City, School of Information Science and Engineering, Xiamen University, 361005, P. R. China", "Xiamen University", "Xiamen University", "\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", "24.43994190", "118.09301781", "edu", "", "China", "2018"], ["Towards Closing the Gap in Weakly Supervised Semantic Segmentation with DCNNs: Combining Local and Global Models.", "", "ETH Z\u00fcrich", "ETH Z\u00fcrich", "ETH Z\u00fcrich, 101, R\u00e4mistrasse, Hochschulen, Altstadt, Z\u00fcrich, Bezirk Z\u00fcrich, Z\u00fcrich, 8092, Schweiz/Suisse/Svizzera/Svizra", "47.37645340", "8.54770931", "edu", "", "Switzerland", "2018"], ["Learning to Interpret Satellite Images Using Wikipedia", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "United States", "2018"], ["Pixel-wise object tracking", "", "New York University", "New York University", "NYU, West 4th Street, NoHo Historic District, NoHo, Manhattan, Manhattan Community Board 2, New York County, NYC, New York, 10012, USA", "40.72925325", "-73.99625394", "edu", "", "United States", "2017"], ["CNN+CNN: Convolutional Decoders for Image Captioning", "", "City University of Hong Kong", "City University of Hong Kong", "\u9999\u6e2f\u57ce\u5e02\u5927\u5b78 City University of Hong Kong, \u9054\u5eb7\u8def Tat Hong Avenue, \u5927\u7aa9\u576a Tai Wo Ping, \u6df1\u6c34\u57d7\u5340 Sham Shui Po District, \u4e5d\u9f8d Kowloon, HK, KIL 3348, \u4e2d\u56fd", "22.34000115", "114.16970291", "edu", "", "China", "2018"], ["Neurons Merging Layer: Towards Progressive Redundancy Reduction for Deep Supervised Hashing", "", "University of Chinese Academy of Sciences", "University of Chinese Academy of Sciences", "University of Chinese Academy of Sciences, UCAS, Yuquanlu, \u7389\u6cc9\u8def, \u7530\u6751, \u6d77\u6dc0\u533a, 100049, \u4e2d\u56fd", "39.90828040", "116.24585270", "edu", "", "China", "2018"], ["Learning Semantic Segmentation from Synthetic Data: A Geometrically Guided Input-Output Adaptation Approach", "", "ETH Zurich", "ETH Zurich", "R\u00e4mistrasse 101, 8092 Z\u00fcrich, Switzerland", "47.37631300", "8.54766990", "edu", "", "Switzerland", "2018"], ["End-to-End Airplane Detection Using Transfer Learning in Remote Sensing Images", "", "Huazhong University of Science and Technology", "Huazhong University of Science and Technology", "\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", "30.50975370", "114.40628810", "edu", "", "China", "2018"], ["Playing for Benchmarks", "", "Intel Labs", "Intel Labs", "4720 Forbes Ave, Pittsburgh, PA 15213, USA", "40.44397890", "-79.94646340", "company", "", "United States", "2017"], ["Advances in deep learning approaches for image tagging", "", "Microsoft", "Microsoft Corporation, Redmond, WA, USA", "One Microsoft Way, Redmond, WA 98052, USA", "47.64233180", "-122.13693020", "company", "", "United States", "2017"], ["Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding", "", "Max Planck Institute for Informatics", "Max Planck Institute for Informatics", "MPII, E1 4, Campus, Universit\u00e4t, Sankt Johann, Bezirk Mitte, Saarbr\u00fccken, Regionalverband Saarbr\u00fccken, Saarland, 66123, Deutschland", "49.25795660", "7.04577417", "edu", "", "Germany", "2016"], ["What Makes for Effective Detection Proposals?", "", "Max Planck Institute for Informatics", "Max Planck Institute for Informatics", "MPII, E1 4, Campus, Universit\u00e4t, Sankt Johann, Bezirk Mitte, Saarbr\u00fccken, Regionalverband Saarbr\u00fccken, Saarland, 66123, Deutschland", "49.25795660", "7.04577417", "edu", "", "Germany", "2016"], ["A cascaded long short-term memory (LSTM) driven generic visual question answering (VQA)", "Queensland University of Technology", "Queensland University of Technology", "Queensland University of Technology", "Queensland University of Technology, Macgregor Lane, Merthyr, South Brisbane, Brisbane, QLD, 4000, Australia", "-27.47715625", "153.02841004", "edu", "", "Australia", "2017"], ["Adaptive Object Detection Using Adjacency and Zoom Prediction", "", "University of Illinois, Urbana-Champaign", "University of Illinois, Urbana-Champaign", "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "40.11116745", "-88.22587665", "edu", "", "United States", "2016"], ["Shallow and Deep Convolutional Networks for Saliency Prediction", "", "Dublin City University", "DUBLIN CITY UNIVERSITY", "Dublin City University Glasnevin Campus, Lower Car Park, Wad, Whitehall A ED, Dublin 9, Dublin, County Dublin, Leinster, D09 FW22, Ireland", "53.38522185", "-6.25740874", "edu", "", "Ireland", "2016"], ["Self-Supervised Learning of Visual Features through Embedding Images into Text Topic Spaces", "", "CVIT, KCIS, IIIT Hyderabad, India", "CVIT, KCIS, IIIT Hyderabad, India", "IIIT, Gachibowli, Gachibowli, Hyderabad, Telangana 500032, India", "17.44509810", "78.34976780", "edu", "", "India", "2017"], ["Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbation", "", "Pennsylvania State University", "Pennsylvania State University", "Old Main, State College, PA 16801, USA", "40.79821330", "-77.85990840", "edu", "", "United States", "2018"], ["Pixel Objectness", "", "University of Texas at Austin", "University of Texas at Austin", "University of Texas at Austin, 1, East 23rd Street, The Drag, Austin, Travis County, Texas, 78712, USA", "30.28415100", "-97.73195598", "edu", "", "United States", "2017"], ["Semi-automatic video object segmentation by advanced manipulation of segmentation hierarchies", "Disney Research Zurich", "Disney Research Zurich", "Disney Research Zurich", "Stampfenbachstrasse 48, 8006 Z\u00fcrich, Switzerland", "47.38047690", "8.54299640", "company", "", "Switzerland", "2015"], ["VADRA: Visual Adversarial Domain Randomization and Augmentation", "", "Carnegie Mellon University", "Carnegie Mellon University", "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "37.41021930", "-122.05965487", "edu", "", "United States", "2018"], ["Zero-Shot Object Detection", "", "NEC Labs America", "NEC Labs America", "4 Independence Way #200, Princeton, NJ 08540, USA", "40.35981820", "-74.59502250", "company", "", "United States", "2018"], ["Automatic Semantic Content Removal by Learning to Neglect.", "", "University of California", "University of California", "Berkeley, CA, USA", "37.87189920", "-122.25853990", "edu", "", "United States", "2018"], ["Directional Edge Boxes: Exploiting Inner Normal Direction Cues for Effective Object Proposal Generation", "School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China", "Huazhong University of Science and Technology", "Huazhong University of Science and Technology", "\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", "30.50975370", "114.40628810", "edu", "", "China", "2017"], ["Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection", "", "Carnegie Mellon University", "Carnegie Mellon University", "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "37.41021930", "-122.05965487", "edu", "", "United States", "2017"], ["On the Effects of Spam Filtering and Incremental Learning for Web-Supervised Visual Concept Classification", "German National Library of Science and Technology & Leibniz Universit\u00e4t Hannover, Hannover, Germany", "Leibniz Universit\u00e4t Hannover, Hannover, Germany", "Leibniz Universit\u00e4t Hannover, Hannover, Germany", "Welfengarten 1, 30167 Hannover, Germany", "52.38296410", "9.71969890", "edu", "", "Germany", "2016"], ["Learning Visually-Grounded Semantics from Contrastive Adversarial Samples", "", "Tsinghua University", "Tsinghua University", "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "40.00229045", "116.32098908", "edu", "", "China", "2018"], ["Generation and Comprehension of Unambiguous Object Descriptions", "", "University of Oxford", "University of Oxford", "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "51.75345380", "-1.25400997", "edu", "", "United Kingdom", "2016"], ["Visual Question Answering Dataset for Bilingual Image Understanding: A Study of Cross-Lingual Transfer Using Attention Maps", "", "Tokyo Institute of Technology", "Tokyo Institute of Technology", "\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", "35.51675380", "139.48342251", "edu", "", "Japan", "2018"], ["Event Specific Multimodal Pattern Mining for Knowledge Base Construction", "Rensselaer Polytechnic Institute, Troy, NY, USA", "Rensselaer Polytechnic Institute", "Rensselaer Polytechnic Institute", "Rensselaer Polytechnic Institute, Sage Avenue, Downtown, City of Troy, Rensselaer County, New York, 12180, USA", "42.72984590", "-73.67950216", "edu", "", "United States", "2016"], ["Bachelor Project Image Captioning with Convolutional Neural Networks", "", "Czech Technical University", "Czech Technical University", "\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", "50.07642960", "14.41802312", "edu", "", "Czech Republic", "2017"], ["Asking for Help with the Right Question by Predicting Human Visual Performance", "", "University of California, Santa Barbara", "University of California, Santa Barbara", "UCSB, Santa Barbara County, California, 93106, USA", "34.41459370", "-119.84581950", "edu", "", "United States", "2016"], ["What value high level concepts in vision to language problems ?", "", "University of Adelaide", "University of Adelaide", "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "-34.91892260", "138.60423668", "edu", "", "Australia", "2015"], ["Training Deep Networks with Structured Layers by Matrix Backpropagation", "", "University of Bonn", "University of Bonn", "Rheinische Friedrich-Wilhelms-Universit\u00e4t Bonn, Arkadenhof, Bonn-Zentrum, Stadtbezirk Bonn, Bonn, Regierungsbezirk K\u00f6ln, Nordrhein-Westfalen, 53113, Deutschland", "50.73381240", "7.10224650", "edu", "", "Germany", "2015"], ["TRAFFIC ANALYSIS USING VISUAL OBJECT DETECTION AND TRACKING", "", "University of Chinese Academy of Sciences", "University of Chinese Academy of Sciences", "University of Chinese Academy of Sciences, UCAS, Yuquanlu, \u7389\u6cc9\u8def, \u7530\u6751, \u6d77\u6dc0\u533a, 100049, \u4e2d\u56fd", "39.90828040", "116.24585270", "edu", "", "China", "2017"], ["Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells.", "", "University of Adelaide", "University of Adelaide", "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "-34.91892260", "138.60423668", "edu", "", "Australia", "2018"], ["Image captioning based on deep reinforcement learning", "", "Beijing, China", "Beijing, China", "Beijing, China", "39.90419990", "116.40739630", "edu", "", "China", "2018"], ["What Action Causes This? Towards Naive Physical Action-Effect Prediction", "", "Microsoft", "Microsoft Corporation, Redmond, WA, USA", "One Microsoft Way, Redmond, WA 98052, USA", "47.64233180", "-122.13693020", "company", "", "United States", "2018"], ["Controllable Top-down Feature Transformer", "", "University of California, San Diego", "University of California, San Diego", "UCSD, 9500, Gilman Drive, Sixth College, University City, San Diego, San Diego County, California, 92093, USA", "32.87935255", "-117.23110049", "edu", "", "United States", "2017"], ["Natural Language Driven Image Edits using a Semantic Image Manipulation Language (SIMPL)", "", "Virginia Tech", "Virginia Tech", "Blacksburg, VA 24061, USA", "37.22838430", "-80.42341670", "edu", "", "United States", "2018"], ["The Impact of Visual Saliency Prediction in Image Classification", "", "Dublin City University", "DUBLIN CITY UNIVERSITY", "Dublin City University Glasnevin Campus, Lower Car Park, Wad, Whitehall A ED, Dublin 9, Dublin, County Dublin, Leinster, D09 FW22, Ireland", "53.38522185", "-6.25740874", "edu", "", "Ireland", "2017"], ["Oracle Performance for Visual Captioning", "", "New York University", "New York University", "NYU, West 4th Street, NoHo Historic District, NoHo, Manhattan, Manhattan Community Board 2, New York County, NYC, New York, 10012, USA", "40.72925325", "-73.99625394", "edu", "", "United States", "2016"], ["Linguistic Unit Discovery from Multi-Modal Inputs in Unwritten Languages: Summary of the \u201cSpeaking Rosetta\u201d JSALT 2017 Workshop", "", "University of Illinois, Urbana-Champaign", "University of Illinois, Urbana-Champaign", "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "40.11116745", "-88.22587665", "edu", "", "United States", "2018"], ["Boosted Attention: Leveraging Human Attention for Image Captioning", "", "University of Minnesota", "University of Minnesota", "WeismanArt, 333, East River Parkway, Marcy-Holmes, Phillips, Minneapolis, Hennepin County, Minnesota, 55455, USA", "44.97308605", "-93.23708813", "edu", "", "United States", "2018"], ["Road Damage Detection And Classification In Smartphone Captured Images Using Mask R-CNN", "", "Indian Institute of Science Bangalore", "Indian Institute of Science Bangalore", "IISc, Gulmohar Marg, RMV Stage II - 1st Block, Aramane Nagara Ward, West Zone, Bengaluru, Bangalore Urban, Karnataka, 560012, India", "13.02223470", "77.56718325", "edu", "", "India", "2018"], ["Fast Efficient Object Detection Using Selective Attention", "", "University of Sydney", "University of Sydney", "USyd, Fisher Road, Camperdown, Sydney, NSW, 2006, Australia", "-33.88890695", "151.18943366", "edu", "", "Australia", "2018"], ["ScratchDet: Exploring to Train Single-Shot Object Detectors from Scratch", "", "University of Chinese Academy of Sciences", "University of Chinese Academy of Sciences", "University of Chinese Academy of Sciences, UCAS, Yuquanlu, \u7389\u6cc9\u8def, \u7530\u6751, \u6d77\u6dc0\u533a, 100049, \u4e2d\u56fd", "39.90828040", "116.24585270", "edu", "", "China", "2018"], ["Design Pseudo Ground Truth with Motion Cue for Unsupervised Video Object Segmentation.", "", "National Taiwan University", "National Taiwan University", "\u81fa\u5927;\u53f0\u5927, 1, \u7f85\u65af\u798f\u8def\u56db\u6bb5, \u5b78\u5e9c\u91cc, \u5927\u5b89\u5340, \u81fa\u5317\u5e02, 10617, \u81fa\u7063", "25.01682835", "121.53846924", "edu", "", "Taiwan", "2018"], ["Partially-Supervised Image Captioning", "", "Australian National University", "Australian National University", "Canberra ACT 0200, Australia", "-35.27769990", "149.11852700", "edu", "", "Australia", "2018"], ["Rank of Experts: Detection Network Ensemble", "", "Electronics and Telecommunications Research Institute, Daejeon, South Korea", "Electronics and Telecommunications Research Institute, Daejeon, South Korea", "Electronics and Telecommunications Research Institute, Sinseong-dong, Daejeon, South Korea", "36.38376500", "127.36694000", "edu", "", "South Korea", "2017"], ["Emergent Translation in Multi-Agent Communication", "", "New York University", "New York University", "NYU, West 4th Street, NoHo Historic District, NoHo, Manhattan, Manhattan Community Board 2, New York County, NYC, New York, 10012, USA", "40.72925325", "-73.99625394", "edu", "", "United States", "2017"], ["Tag-based video retrieval by embedding semantic content in a continuous word space", "", "University of Amsterdam", "University of Amsterdam", "Institute for Logic, Language and Computation (ILLC), 107, Science Park, Oost-Watergraafsmeer, Amsterdam, Oost, Amsterdam, Noord-Holland, Nederland, 1098XG, Nederland", "52.35536550", "4.95016440", "edu", "", "Netherlands", "2016"], ["FastMask: Segment Multi-scale Object Candidates in One Shot", "", "Fudan University", "Fudan University", "\u590d\u65e6\u5927\u5b66, 220, \u90af\u90f8\u8def, \u4e94\u89d2\u573a\u8857\u9053, \u6768\u6d66\u533a, \u4e0a\u6d77\u5e02, 200433, \u4e2d\u56fd", "31.30104395", "121.50045497", "edu", "", "China", "2017"], ["Beyond Pixels: A Comprehensive Survey from Bottom-up to Semantic Image Segmentation and Cosegmentation", "", "Nanyang Technological University", "Nanyang Technological University", "NTU, Faculty Avenue, Jurong West, Southwest, 637460, Singapore", "1.34841040", "103.68297965", "edu", "", "Singapore", "2016"], ["Looking at Hands in Autonomous Vehicles: A ConvNet Approach using Part Affinity Fields", "", "University of California, San Diego", "University of California, San Diego", "UCSD, 9500, Gilman Drive, Sixth College, University City, San Diego, San Diego County, California, 92093, USA", "32.87935255", "-117.23110049", "edu", "", "United States", "2018"], ["Learning visual attribute from image and text \u2217", "", "Tohoku University", "Tohoku University", "Tohoku University, \u4e94\u6a4b\u901a, \u9752\u8449\u533a, \u4ed9\u53f0\u5e02, \u5bae\u57ce\u770c, \u6771\u5317\u5730\u65b9, 980-0811, \u65e5\u672c", "38.25309450", "140.87365930", "edu", "", "Japan", "2015"], ["Adopting Abstract Images for Semantic Scene Understanding", "Microsoft Research, One Microsoft Way, Redmond, WA", "Microsoft", "Microsoft Corporation, Redmond, WA, USA", "One Microsoft Way, Redmond, WA 98052, USA", "47.64233180", "-122.13693020", "company", "", "United States", "2016"], ["Indirect deep structured learning for 3D human body shape and pose prediction.", "", "University of Cambridge", "University of Cambridge", "Clifford Allbutt Lecture Theatre, Robinson Way, Romsey, Cambridge, Cambridgeshire, East of England, England, CB2 0QH, UK", "52.17638955", "0.14308882", "edu", "", "United Kingdom", "2017"], ["Tackling Low Resolution for Better Scene Understanding", "", "International Institute of Information Technology", "International Institute of Information Technology", "International Institute of Information Technology, Hyderabad, Campus Road, Ward 105 Gachibowli, Greater Hyderabad Municipal Corporation West Zone, Hyderabad, Rangareddy District, Telangana, 500032, India", "17.44549570", "78.34854698", "edu", "", "India", "2018"], ["Add English to image Chinese captioning", "PDL, National Laboratory for Parallel and Distributed Processing, NUDT, National University of Defense Technology, Changsha, China", "National University of Defense Technology, China", "National University of Defence Technology, Changsha 410000, China", "\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", "28.22902090", "112.99483204", "mil", "", "China", "2017"], ["Deep Generative Models for Weakly-Supervised Multi-Label Classification", "", "Carnegie Mellon University", "Carnegie Mellon University", "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "37.41021930", "-122.05965487", "edu", "", "United States", "2018"], ["Visual Question Answering : Datasets , Methods , Challenges and Oppurtunities", "", "Princeton University", "Princeton University", "Lot 9, University Place, Princeton Township, Mercer County, New Jersey, 08540, USA", "40.34829285", "-74.66308325", "edu", "", "United States", "2018"], ["Learning 3D Scene Synthesis from Annotated RGB-D Images", "", "Zhejiang University", "Zhejiang University", "\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", "30.19331415", "120.11930822", "edu", "", "China", "2016"], ["Active Grounding of Visual Situations", "", "Santa Fe Institute", "Santa Fe Institute", "Santa Fe Institute, Hyde Park Road, Santa Fe, Santa Fe County, New Mexico, 87501, USA", "35.70028780", "-105.90864847", "edu", "", "United States", "2017"], ["A two-stage training deep neural network for small pedestrian detection", "Graduate School of Science and Engineering, Teikyo University", "Teikyo University", "Teikyo University", "Japan, \u3012173-8605 Tokyo, \u677f\u6a4b\u533a\u52a0\u8cc0\uff12\u4e01\u76ee\uff11\uff11\u2212\uff11", "35.75927460", "139.71450290", "edu", "", "Japan", "2017"], ["ABC-CNN: An Attention Based Convolutional Neural Network for Visual Question Answering", "", "University of Southern California", "University of Southern California", "University of Southern California, Watt Way, Saint James Park, LA, Los Angeles County, California, 90089, USA", "34.02241490", "-118.28634407", "edu", "", "United States", "2015"], ["A New Deep Learning-Based Food Recognition System for Dietary Assessment on An Edge Computing Service Infrastructure", "University of Massachusetts, Lowell, MA", "University of Massachusetts", "University of Massachusetts", "University of Massachusetts, Hicks Way, Amherst, Hampshire, Massachusetts, 01003, USA", "42.38897850", "-72.52869870", "edu", "", "United States", "2018"], ["Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers", "", "The Pennsylvania State University", "The Pennsylvania State University", "Old Main, State College, PA 16801, USA", "40.79821330", "-77.85990840", "edu", "", "United States", "2018"], ["Complex event processing for content-based text, image, and video retrieval", "United States Air Force Research Laboratory, Dayton, OH", "United States Air Force Research Laboratory, Dayton, OH", "United States Air Force Research Laboratory, Dayton, OH", "1864 4th St, Wright-Patterson AFB, OH 45433, USA", "39.79084110", "-84.09897580", "mil", "", "United States", "2016"], ["Non-parametric Structured Output Networks", "", "Disney Research", "Disney Research", "521 Circle 7 Dr, Glendale, CA 91201, USA", "34.15797420", "-118.28947290", "company", "", "United States", "2017"], ["A Rotation Invariant Latent Factor Model for Moveme Discovery from Static Poses", "", "California Institute of Technology", "California Institute of Technology", "California Institute of Technology, San Pasqual Walk, Madison Heights, Pasadena, Los Angeles County, California, 91126, USA", "34.13710185", "-118.12527487", "edu", "", "United States", "2016"], ["Bidirectional Long-Short Term Memory for Video Description", "", "University of Queensland", "University of Queensland", "University of Queensland, University Drive, Hill End, St Lucia, Brisbane, QLD, 4072, Australia", "-27.49741805", "153.01316956", "edu", "", "Australia", "2016"], ["Recurrent Topic-Transition GAN for Visual Paragraph Generation", "", "Carnegie Mellon University", "Carnegie Mellon University", "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "37.41021930", "-122.05965487", "edu", "", "United States", "2017"], ["Beyond Forward Shortcuts: Fully Convolutional Master-Slave Networks (MSNets) with Backward Skip Connections for Semantic Segmentation", "", "University of Illinois, Urbana-Champaign", "University of Illinois, Urbana-Champaign", "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "40.11116745", "-88.22587665", "edu", "", "United States", "2017"], ["A Reinforcement Learning Framework for Natural Question Generation using Bi-discriminators", "", "Fudan University", "Fudan University", "\u590d\u65e6\u5927\u5b66, 220, \u90af\u90f8\u8def, \u4e94\u89d2\u573a\u8857\u9053, \u6768\u6d66\u533a, \u4e0a\u6d77\u5e02, 200433, \u4e2d\u56fd", "31.30104395", "121.50045497", "edu", "", "China", "2018"], ["VSE++: Improving Visual-Semantic Embeddings with Hard Negatives", "", "University of Toronto", "University of Toronto", "University of Toronto, St. George Street, Bloor Street Culture Corridor, Old Toronto, Toronto, Ontario, M5S 1A5, Canada", "43.66333345", "-79.39769975", "edu", "", "Canada", "2018"], ["NLE@MediaEval'17: Combining Cross-Media Similarity and Embeddings for Retrieving Diverse Social Images", "", "Naver Labs Europe, Meylan, France", "Naver Labs Europe, Meylan, France", "6 Chemin de Maupertuis, 38240 Meylan, France", "45.21739890", "5.79213490", "edu", "", "France", "2017"], ["Accelerating Machine Learning Inference with Probabilistic Predicates", "Princeton University &Microsoft, Princeton, NJ, USA", "Princeton University &Microsoft", "Princeton University &Microsoft, Princeton, NJ, USA", "Princeton, NJ 08544, USA", "40.34398880", "-74.65144810", "edu", "", "United States", "2018"], ["Actor-Critic Sequence Training for Image Captioning", "", "University of Edinburgh", "University of Edinburgh", "New College, New College Courtyard, The Mound, Old Town, Edinburgh, City of Edinburgh, Scotland, EH1 2LX, UK", "55.94951105", "-3.19534913", "edu", "", "United Kingdom", "2017"], ["Neural Image Captioning for Intelligent Vehicle-to-Passenger Communication", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "United States", "2017"], ["Hybrid Supervised-unsupervised Image Topic Visualization with Convolutional Neural Network and LDA", "", "Indiana University", "Indiana University", "Indiana University East, West Cart Road, Richmond, Wayne County, Indiana, 47374, USA", "39.86948105", "-84.87956905", "edu", "", "United States", "2017"], ["Image captioning in Turkish with subword units", "Bilgisayar M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc, Hacettepe \u00dcniversitesi, Ankara, T\u00fcrkiye", "Bilgisayar M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc, Hacettepe \u00dcniversitesi, Ankara, T\u00fcrkiye", "Bilgisayar M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc, Hacettepe \u00dcniversitesi, Ankara, T\u00fcrkiye", "\u00dcniversiteler Mh., Hacettepe Beytepe Kamp\u00fcs\u00fc No:21, 06800 \u00c7ankaya/Ankara, Turkey", "39.87143010", "32.73636570", "edu", "", "Turkey", "2018"], ["Cross-linguistic differences and similarities in image descriptions", "", "University of Edinburgh", "University of Edinburgh", "New College, New College Courtyard, The Mound, Old Town, Edinburgh, City of Edinburgh, Scotland, EH1 2LX, UK", "55.94951105", "-3.19534913", "edu", "", "United Kingdom", "2017"], ["Comixify: Transform video into a comics", "", "Warsaw University of Technology", "Warsaw University of Technology", "Politechnika Warszawska, 1, Plac Politechniki, VIII, \u015ar\u00f3dmie\u015bcie, Warszawa, mazowieckie, 00-661, RP", "52.22165395", "21.00735776", "edu", "", "Poland", "2018"], ["Fine-grained Video Retrieval using Query Phrases \u2014 Waseda_Meisei TRECVID 2017 AVS System \u2014", "Faculty of Science and Engineering, Waseda University, Tokyo, 162-0042, Japan", "Waseda University", "Waseda University", "\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", "33.88987280", "130.70856205", "edu", "", "Japan", "2018"], ["DSOD: Learning Deeply Supervised Object Detectors from Scratch", "", "Fudan University", "Fudan University", "\u590d\u65e6\u5927\u5b66, 220, \u90af\u90f8\u8def, \u4e94\u89d2\u573a\u8857\u9053, \u6768\u6d66\u533a, \u4e0a\u6d77\u5e02, 200433, \u4e2d\u56fd", "31.30104395", "121.50045497", "edu", "", "China", "2017"], ["Exploiting Negative Evidence for Deep Latent Structured Models", "Sorbonne Universit\u00e9s, Paris, France", "CEDRIC-Conservatoire National des Arts et M\u00e9tiers, Paris, France", "CEDRIC-Conservatoire National des Arts et M\u00e9tiers, Paris, France", "32 Rue du Faubourg Saint-Martin, 75010 Paris, France", "48.87008750", "2.35638710", "edu", "", "France", "2018"], ["Detecting Animals in Infrared Images from Camera-Traps", "Research, MVTec Software GmbH, Munich, Germany", "Research, MVTec Software GmbH, Munich, Germany", "Research, MVTec Software GmbH, Munich, Germany", "Arnulfstra\u00dfe 205, 80634 M\u00fcnchen, Germany", "48.14952580", "11.52082560", "edu", "", "Germany", "2018"], ["PIRC Net : Using Proposal Indexing, Relationships and Context for Phrase Grounding", "", "University of Southern California", "University of Southern California", "University of Southern California, Watt Way, Saint James Park, LA, Los Angeles County, California, 90089, USA", "34.02241490", "-118.28634407", "edu", "", "United States", "2018"], ["Learning Unsupervised Visual Grounding Through Semantic Self-Supervision.", "", "Carnegie Mellon University", "Carnegie Mellon University", "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "37.41021930", "-122.05965487", "edu", "", "United States", "2018"], ["Title Multi-Object Classification and Unsupervised Scene Understanding Using Deep Learning Features and Latent Tree Probabilistic Models Permalink", "", "University of California", "University of California", "Berkeley, CA, USA", "37.87189920", "-122.25853990", "edu", "", "United States", "2015"], ["Recurrent Pixel Embedding for Instance Grouping", "", "University of California, Irvine", "University of California, Irvine", "Irvine, CA 92697, USA", "33.64049520", "-117.84429620", "edu", "", "", "2018"], ["Distorting Neural Representations to Generate Highly Transferable Adversarial Examples", "", "Australian National University", "Australian National University", "Canberra ACT 0200, Australia", "-35.27769990", "149.11852700", "edu", "", "Australia", "2018"], ["Neural Motifs: Scene Graph Parsing with Global Context", "", "Carnegie Mellon University", "Carnegie Mellon University", "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "37.41021930", "-122.05965487", "edu", "", "United States", "2018"], ["Artistic Image Generation from Sketch by Using Conditional Adversarial Network and Style Feature Transform", "", "Wuhan University of Technology", "Wuhan University of Technology", "\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", "30.60903415", "114.35142840", "edu", "", "China", "2018"], ["C-WSL: Count-Guided Weakly Supervised Localization", "", "University of Maryland", "University of Maryland", "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "39.28996850", "-76.62196103", "edu", "", "United States", "2018"], ["Non-local RoI for Cross-Object Perception", "", "Academia Sinica, Taiwan", "Academia Sinica, Taiwan", "No. 128\u865f, Section 2, Academia Rd, Nangang District, Taipei City, Taiwan 11529", "25.04218520", "121.61454770", "edu", "", "Taiwan", "2018"], ["Learning from Multiview Correlations in Open-Domain Videos", "", "Imperial College London", "Imperial College London", "Imperial College London, Exhibition Road, Brompton, Royal Borough of Kensington and Chelsea, London, Greater London, England, SW7 2AZ, UK", "51.49887085", "-0.17560797", "edu", "", "United Kingdom", "2018"], ["Exploring the Design Space of Deep Convolutional Neural Networks at Large Scale", "", "University of California, Berkeley", "University of California, Berkeley", "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "37.86871260", "-122.25586815", "edu", "", "United States", "2016"], ["BING++: A Fast High Quality Object Proposal Generator at 100fps", "", "Nankai University", "Nankai University", "94 Weijin Rd, Nankai Qu, China, 300071", "39.10394430", "117.17422320", "edu", "", "", "2015"], ["Actor-Action Semantic Segmentation with Region Masks", "", "Wuhan University of Technology", "Wuhan University of Technology", "\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", "30.60903415", "114.35142840", "edu", "", "China", "2018"], ["Stability Based Filter Pruning for Accelerating Deep CNNs", "", "IIT Kanpur", "IIT Kanpur", "Kalyanpur, Kanpur, Uttar Pradesh 208016, India", "26.51233880", "80.23290000", "edu", "", "India", "2018"], ["4D Generic Video Object Proposals", "", "RWTH Aachen University", "RWTH Aachen University", "RWTH Aachen, Mies-van-der-Rohe-Stra\u00dfe, K\u00f6nigsh\u00fcgel, Aachen-Mitte, Aachen, St\u00e4dteregion Aachen, Regierungsbezirk K\u00f6ln, Nordrhein-Westfalen, 52074, Deutschland", "50.77917030", "6.06728733", "edu", "", "Germany", "2019"], ["Self-Supervised Adversarial Hashing Networks for Cross-Modal Retrieval", "", "University of Sydney", "University of Sydney", "USyd, Fisher Road, Camperdown, Sydney, NSW, 2006, Australia", "-33.88890695", "151.18943366", "edu", "", "Australia", "2018"], ["Active Transfer Learning with Zero-Shot Priors: Reusing Past Datasets for Future Tasks", "", "University of Amsterdam", "University of Amsterdam", "Institute for Logic, Language and Computation (ILLC), 107, Science Park, Oost-Watergraafsmeer, Amsterdam, Oost, Amsterdam, Noord-Holland, Nederland, 1098XG, Nederland", "52.35536550", "4.95016440", "edu", "", "Netherlands", "2015"], ["Question Part Relevance and Editing for Cooperative and Context-Aware VQA (C2VQA)", "Universit\u00e0 di Salerno, Dipartimento di Informatica, Fisciano, Italy", "Universit\u00e0 di Salerno, Dipartimento di Informatica, Fisciano, Italy", "Universit\u00e0 di Salerno, Dipartimento di Informatica, Fisciano, Italy", "Universit\u00e0 di Salerno Via Papa, Via Giovanni Paolo II, 132, 84084 Fisciano SA, Italy", "40.77434920", "14.78901500", "edu", "", "Italy", "2017"], ["Finding Tiny Faces", "", "Carnegie Mellon University", "Carnegie Mellon University", "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "37.41021930", "-122.05965487", "edu", "", "United States", "2017"], ["Multiview Cross-supervision for Semantic Segmentation", "", "University of Minnesota", "University of Minnesota", "WeismanArt, 333, East River Parkway, Marcy-Holmes, Phillips, Minneapolis, Hennepin County, Minnesota, 55455, USA", "44.97308605", "-93.23708813", "edu", "", "United States", "2018"], ["Asymmetric Deep Supervised Hashing", "", "Nanjing University", "Nanjing University", "NJU, \u4e09\u6c5f\u8def, \u9f13\u697c\u533a, \u5357\u4eac\u5e02, \u6c5f\u82cf\u7701, 210093, \u4e2d\u56fd", "32.05659570", "118.77408833", "edu", "", "China", "2018"], ["Simple Baseline for Visual Question Answering", "", "MIT", "Massachusetts Institute", "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "42.35839610", "-71.09567788", "edu", "", "United States", "2015"], ["SPICE: Semantic Propositional Image Caption Evaluation", "", "Macquarie University", "Macquarie University, Sydney, Australia", "Balaclava Rd, Macquarie Park NSW 2109, Australia", "-33.77382370", "151.11264980", "edu", "", "Australia", "2016"], ["Image Captioning with Text-Based Visual Attention", "School of Electronics and Information Engineering, Sun Yat-sen University, Guangzhou, China", "Sun Yat-Sen University", "Sun Yat-Sen University", "\u4e2d\u5927, \u65b0\u6e2f\u897f\u8def, \u9f99\u8239\u6ed8, \u5eb7\u4e50, \u6d77\u73e0\u533a (Haizhu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510105, \u4e2d\u56fd", "23.09461185", "113.28788994", "edu", "", "China", "2018"], ["CBAM: Convolutional Block Attention Module", "", "Adobe Research, San Jose, CA, USA", "Adobe Research, San Jose, CA, USA", "San Jose, CA, USA", "37.33820820", "-121.88632860", "edu", "", "United States", "2018"], ["Panoptic Segmentation with a Joint Semantic and Instance Segmentation Network", "", "TU Eindhoven", "TU Eindhoven", "Technische Universiteit Eindhoven, 2, De Rondom, Villapark, Eindhoven, Noord-Brabant, Nederland, 5600 MB, Nederland", "51.44866020", "5.49039957", "edu", "", "Netherlands", "2018"], ["Semantic soft segmentation", "MIT CSAIL and ETH Z\u00fcrich, Switzerland", "MIT CSAIL and ETH Z\u00fcrich, Switzerland", "MIT CSAIL and ETH Z\u00fcrich, Switzerland", "32 Vassar St, Cambridge, MA 02139, USA", "42.36194070", "-71.09043780", "edu", "", "United States", "2018"], ["Semantic Segmentation , Urban Navigation , and Research Directions", "", "Princeton University", "Princeton University", "Lot 9, University Place, Princeton Township, Mercer County, New Jersey, 08540, USA", "40.34829285", "-74.66308325", "edu", "", "United States", "2018"], ["Implementation of human-robot VQA interaction system with dynamic memory networks", "School of Electrical Engineering, KAIST, Daejeon, Republic of Korea", "KAIST", "KAIST", "291 Daehak-ro, Eoeun-dong, Yuseong-gu, Daejeon, South Korea", "36.37214270", "127.36039000", "edu", "", "South Korea", "2017"], ["Adversarial Cross-Modal Retrieval", "University of Electronic Science and Technology of China, Chengdu, China", "University of Electronic Science and Technology of China", "University of Electronic Science and Technology of China", "Columbus, OH 43210, USA", "40.01419050", "-83.03091430", "edu", "", "United States", "2017"], ["Data Analysis Project : Using Knowledge Graphs for Image Classification", "", "Carnegie Mellon University", "Carnegie Mellon University", "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "37.41021930", "-122.05965487", "edu", "", "United States", "2018"], ["Structure Inference Net: Object Detection Using Scene-Level Context and Instance-Level Relationships", "", "University of Chinese Academy of Sciences", "University of Chinese Academy of Sciences", "University of Chinese Academy of Sciences, UCAS, Yuquanlu, \u7389\u6cc9\u8def, \u7530\u6751, \u6d77\u6dc0\u533a, 100049, \u4e2d\u56fd", "39.90828040", "116.24585270", "edu", "", "China", "2018"], ["Statistical Iterative CBCT Reconstruction Based on Neural Network", "Key Laboratory of Image Processing and Intelligent Control of Ministry of Education of China, Huazhong University of Science and Technology, Wuhan, China", "Huazhong University of Science and Technology", "Huazhong University of Science and Technology", "\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", "30.50975370", "114.40628810", "edu", "", "China", "2018"], ["Fusion Scheme for Semantic and Instance-level Segmentation", "Computer Science Department, Technical University of Cluj-Napoca, Image Processing and Pattern Recognition Group, Romania", "Technical University of Cluj-Napoca", "Technical University of Cluj-Napoca", "Strada Memorandumului 28, Cluj-Napoca 400114, Romania", "46.76929900", "23.58561300", "edu", "", "Romania", "2018"], ["Where and Who? Automatic Semantic-Aware Person Composition", "", "University of Virginia", "University of Virginia", "University of Virginia, Rotunda Alley, Carr's Hill, Albemarle County, Virginia, 22904-4119, USA", "38.03536820", "-78.50353220", "edu", "", "United States", "2018"], ["Findings of the Second Shared Task on Multimodal Machine Translation and Multilingual Image Description", "", "University of Edinburgh", "University of Edinburgh", "New College, New College Courtyard, The Mound, Old Town, Edinburgh, City of Edinburgh, Scotland, EH1 2LX, UK", "55.94951105", "-3.19534913", "edu", "", "United Kingdom", "2017"], ["Learning to predict where to look in interactive environments using deep recurrent q-learning", "", "National University of Ireland", "National University of Ireland, Galway", "University Rd, Galway, Ireland", "53.27702430", "-9.06148640", "edu", "", "Ireland", "2016"], ["EmotioNet Challenge: Recognition of facial expressions of emotion in the wild", "", "Ohio State University", "The Ohio State University", "The Ohio State University, Woody Hayes Drive, Columbus, Franklin County, Ohio, 43210, USA", "40.00471095", "-83.02859368", "edu", "", "United States", "2017"], ["EMPIRICAL PERFORMANCE UPPER BOUNDS FOR IM- AGE AND VIDEO CAPTIONING", "", "New York University", "New York University", "NYU, West 4th Street, NoHo Historic District, NoHo, Manhattan, Manhattan Community Board 2, New York County, NYC, New York, 10012, USA", "40.72925325", "-73.99625394", "edu", "", "United States", "2016"], ["Automatic Annotation of Object Instances by Region-Based Recurrent Neural Networks", "Faculty of Electronics, Telecommunications and Information Technology, University Politehnica of Bucharest, Bucharest, 061071, Romania", "University Politehnica of Bucharest", "University Politehnica of Bucharest", "Universitatea Politehnica din Bucure\u0219ti, Novum Invest, Bucure\u0219ti, Militari, Sector 6, Municipiul Bucure\u0219ti, 060042, Rom\u00e2nia", "44.43918115", "26.05044565", "edu", "", "Romania", "2018"], ["Perceptual Material Attributes Arise in Local Material Recognition", "", "Drexel University", "Drexel University", "Drexel University, Arch Street, Powelton Village, Philadelphia, Philadelphia County, Pennsylvania, 19104, USA", "39.95740000", "-75.19026706", "edu", "", "United States", "2016"], ["Hierarchical Co-Attention for Visual Question Answering", "", "Virginia Tech", "Virginia Tech", "Blacksburg, VA 24061, USA", "37.22838430", "-80.42341670", "edu", "", "United States", "2016"], ["Intelligent Film Assistant for Personalized Video Creation on Mobile Devices", "University of Applied Sciences, Technikum Wien, Vienna, Austria", "University of Applied Sciences", "National Kaohsiung, University of Applied Sciences, Kaohsiung, Taiwan. jspan@cc.kuas.edu.tw", "No. 415\u865f, Jiangong Road, Sanmin District, Kaohsiung City, Taiwan 807", "22.64894580", "120.32831570", "edu", "", "Taiwan", "2017"], ["Crowd Counting via Scale-Adaptive Convolutional Neural Network", "", "Shanghai Jiaotong University", "Shanghai Jiaotong University", "China, Shanghai, Minhang, \u4e1c\u5ddd\u8def \u90ae\u653f\u7f16\u7801: 200240", "31.02522010", "121.43377840", "edu", "", "China", "2018"], ["Action Machine: Rethinking Action Recognition in Trimmed Videos", "", "University of Chinese Academy of Sciences", "University of Chinese Academy of Sciences", "University of Chinese Academy of Sciences, UCAS, Yuquanlu, \u7389\u6cc9\u8def, \u7530\u6751, \u6d77\u6dc0\u533a, 100049, \u4e2d\u56fd", "39.90828040", "116.24585270", "edu", "", "China", "2018"], ["S4Net: Single Stage Salient-Instance Segmentation", "", "Nankai University", "Nankai University", "94 Weijin Rd, Nankai Qu, China, 300071", "39.10394430", "117.17422320", "edu", "", "", "2017"], ["Answerer in Questioner's Mind for Goal-Oriented Visual Dialogue", "", "Seoul National University", "Seoul National University", "\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", "37.26728000", "126.98411510", "edu", "", "South Korea", "2017"], ["Beyond Manual Annotations for Learning Visual Representations", "", "University of California, Berkeley", "University of California, Berkeley", "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "37.86871260", "-122.25586815", "edu", "", "United States", "2016"], ["Deep Neural Networks for Semantic Segmentation of Multispectral Remote Sensing Imagery", "", "Rochester Institute of Technology", "Rochester Institute of Technology", "Rochester Institute of Technology (RIT), 1, Lomb Memorial Drive, Bailey, Henrietta Town, Monroe County, New York, 14623, USA", "43.08250655", "-77.67121663", "edu", "", "United States", "2017"], ["Best of Both Worlds: Transferring Knowledge from Discriminative Learning to a Generative Visual Dialog Model", "", "Georgia Institute of Technology", "Georgia Institute of Technology", "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "33.77603300", "-84.39884086", "edu", "", "United States", "2017"], ["A vision-grounded dataset for predicting typical locations for verbs", "", "University of California at Berkeley", "International Computer Science Institute, University of California at Berkeley, Berkeley, USA", "1947 Center St, Berkeley, CA 94704, USA", "37.87015430", "-122.27123120", "edu", "", "United States", "2018"], ["Leveraging Motion Priors in Videos for Improving Human Segmentation", "", "National Tsing Hua University", "National Tsing Hua University", "\u570b\u7acb\u6e05\u83ef\u5927\u5b78, 101, \u514b\u606d\u6a4b, \u5149\u660e\u91cc, \u8d64\u571f\u5d0e, \u6771\u5340, \u65b0\u7af9\u5e02, 30013, \u81fa\u7063", "24.79254840", "120.99511830", "edu", "", "Taiwan", "2018"], ["Shape and Pose Estimation for Closely Interacting Persons Using Multi-view Images", "", "Tianjin University", "Tianjin University", "\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", "36.20304395", "117.05842113", "edu", "", "China", "2018"], ["Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference", "", "Google", "Google, Inc.", "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "37.42199990", "-122.08405750", "company", "Google, Mountain View, CA", "United States", "2018"], ["Gibson Env: Real-World Perception for Embodied Agents", "", "University of California, Berkeley", "University of California, Berkeley", "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "37.86871260", "-122.25586815", "edu", "", "United States", "2018"], ["Explaining the Ambiguity of Object Detection and 6D Pose from Visual Data", "", "University of Oxford", "University of Oxford", "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "51.75345380", "-1.25400997", "edu", "", "United Kingdom", "2018"], ["AutoFocus: Efficient Multi-Scale Inference", "", "University of Maryland", "University of Maryland", "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "39.28996850", "-76.62196103", "edu", "", "United States", "2018"], ["Large-Scale Active Learning with Approximations of Expected Model Output Changes", "", "Friedrich Schiller University Jena", "Computer Vision Group, Friedrich Schiller University Jena, Germany", "Ernst-Abbe-Platz 2, 07743 Jena, Germany", "50.92776710", "11.58217290", "edu", "", "Germany", "2016"], ["Multi-modal deep feature learning for RGB-D object detection", "", "University of Rochester", "University of Rochester", "Memorial Art Gallery, 500, University Avenue, East End, Rochester, Monroe County, New York, 14607, USA", "43.15769690", "-77.58829158", "edu", "", "United States", "2017"], ["Beyond Grids : Learning Graph Representations for Visual Recognition", "", "Carnegie Mellon University", "Carnegie Mellon University", "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "37.41021930", "-122.05965487", "edu", "", "United States", "2018"], ["ALFA: Agglomerative Late Fusion Algorithm for Object Detection", "Institute of Computational Mathematics and Information Technologies, Kazan Federal University, Russia", "Czech Technical University", "Czech Technical University", "\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", "50.07642960", "14.41802312", "edu", "", "Czech Republic", "2018"], ["Question Type Guided Attention in Visual Question Answering", "", "California Institute of Technology", "California Institute of Technology", "California Institute of Technology, San Pasqual Walk, Madison Heights, Pasadena, Los Angeles County, California, 91126, USA", "34.13710185", "-118.12527487", "edu", "", "United States", "2018"], ["Unsupervised Domain Adaptation for Semantic Segmentation with GANs", "", "GE Global Research Center", "GE Global Research Center", "GE Global Research Center, Aqueduct, Niskayuna, Schenectady County, New York, USA", "42.82982480", "-73.87719385", "edu", "", "United States", "2017"], ["Unsupervised Ensemble Regression", "", "IBM Thomas J. Watson Research Center", "IBM Thomas J. Watson Research Center", "IBM Yorktown research lab, Adams Road, Millwood, Town of New Castle, Westchester County, New York, 10562, USA", "41.21002475", "-73.80407056", "company", "", "United States", "2017"], ["Dockerface: an easy to install and use Faster R-CNN face detector in a Docker container", "", "Georgia Institute of Technology", "Georgia Institute of Technology", "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "33.77603300", "-84.39884086", "edu", "", "United States", "2017"], ["Integrating Local Material Recognition with Large-Scale Perceptual Attribute Discovery", "", "Drexel University", "Drexel University", "Drexel University, Arch Street, Powelton Village, Philadelphia, Philadelphia County, Pennsylvania, 19104, USA", "39.95740000", "-75.19026706", "edu", "", "United States", "2016"], ["Approximate Distribution Matching for Sequence-to-Sequence Learning", "", "Microsoft Research Asia", "Microsoft Research Asia", "1 Memorial Dr, Cambridge, MA 02142, USA", "42.36142560", "-71.08120920", "company", "", "United States", "2018"], ["Webly Supervised Learning of Convolutional Networks", "", "Carnegie Mellon University", "Carnegie Mellon University", "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "37.41021930", "-122.05965487", "edu", "", "United States", "2015"], ["Action-driven 3D indoor scene evolution", "", "Microsoft", "Microsoft Corporation, Redmond, WA, USA", "One Microsoft Way, Redmond, WA 98052, USA", "47.64233180", "-122.13693020", "company", "", "United States", "2016"], ["Pedestrian Detection by Feature Selected Self-Similarity Features", "National Key Laboratory of Science and Technology on Communications, University of Electronic Science and Technology of China, Chengdu, China", "University of Electronic Science and Technology of China", "University of Electronic Science and Technology of China", "Columbus, OH 43210, USA", "40.01419050", "-83.03091430", "edu", "", "United States", "2018"], ["Multiple Instance Learning Convolutional Neural Networks for object recognition", "", "University of Missouri", "University of Missouri", "L1, Maguire Boulevard, Lemone Industrial Park, Columbia, Boone County, Missouri, 65201, USA", "38.92676100", "-92.29193783", "edu", "", "United States", "2016"], ["Amodal Instance Segmentation", "", "University of California, Berkeley", "University of California, Berkeley", "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "37.86871260", "-122.25586815", "edu", "", "United States", "2016"], ["Dictionary-Guided Editing Networks for Paraphrase Generation", "", "Beihang University", "Beihang University", "\u5317\u4eac\u822a\u7a7a\u822a\u5929\u5927\u5b66, 37, \u5b66\u9662\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100083, \u4e2d\u56fd", "39.98083330", "116.34101249", "edu", "", "China", "2018"], ["Improving Image Captioning by Leveraging Knowledge Graphs", "", "The Pennsylvania State University", "The Pennsylvania State University", "Old Main, State College, PA 16801, USA", "40.79821330", "-77.85990840", "edu", "", "United States", "2019"], ["Ex Paucis Plura : Learning Affordance Segmentation from Very Few Examples", "", "University of Bonn", "University of Bonn", "Rheinische Friedrich-Wilhelms-Universit\u00e4t Bonn, Arkadenhof, Bonn-Zentrum, Stadtbezirk Bonn, Bonn, Regierungsbezirk K\u00f6ln, Nordrhein-Westfalen, 53113, Deutschland", "50.73381240", "7.10224650", "edu", "", "Germany", "2018"], ["Story Understanding in Video Advertisements", "", "University of Pittsburgh", "University of Pittsburgh", "University of Pittsburgh, Sutherland Drive, West Oakland, PGH, Allegheny County, Pennsylvania, 15240, USA", "40.44415295", "-79.96243993", "edu", "", "United States", "2018"], ["Prototype GOD: prototype Generic Objects Dataset for an Object Detection System based on Bird\u2019s \u2013Eye View", "Visual Intelligence Research Group Electronics and Telecommunications Research Institute, Daejeon, Korea", "Electronics and Telecommunications Research Institute, Korea", "Electronics and Telecommunications Research Institute (ETRI), Republic of Korea", "South Korea", "35.90775700", "127.76692200", "edu", "", "South Korea", "2018"], ["A Multi-Stream Convolutional Neural Network Framework for Group Activity Recognition", "", "Amirkabir University of Technology", "Amirkabir University of Technology", "\u062f\u0627\u0646\u0634\u06af\u0627\u0647 \u0635\u0646\u0639\u062a\u06cc \u0627\u0645\u06cc\u0631\u06a9\u0628\u06cc\u0631, \u0648\u0644\u06cc \u0639\u0635\u0631, \u0645\u06cc\u062f\u0627\u0646 \u0648\u0644\u06cc\u0639\u0635\u0631, \u0645\u0646\u0637\u0642\u0647 \u06f6 \u0634\u0647\u0631 \u062a\u0647\u0631\u0627\u0646, \u062a\u0647\u0631\u0627\u0646, \u0628\u062e\u0634 \u0645\u0631\u06a9\u0632\u06cc \u0634\u0647\u0631\u0633\u062a\u0627\u0646 \u062a\u0647\u0631\u0627\u0646, \u0634\u0647\u0631\u0633\u062a\u0627\u0646 \u062a\u0647\u0631\u0627\u0646, \u0627\u0633\u062a\u0627\u0646 \u062a\u0647\u0631\u0627\u0646, \u0646\u0628\u0634 \u0628\u0631\u0627\u062f\u0631\u0627\u0646 \u0645\u0638\u0641\u0631, \u200f\u0627\u06cc\u0631\u0627\u0646\u200e", "35.70451400", "51.40972058", "edu", "", "Iran", "2018"], ["Peephole: Predicting Network Performance Before Training", "", "Chinese University of Hong Kong", "Chinese University of Hong Kong", "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "22.41626320", "114.21093180", "edu", "", "China", "2017"], ["AutoMarkov DNNs for object classification", "University Politehnica of Bucharest, Faculty of Electronics, Telecommunications and Information Technology, Applied Electronics and Information Engineering Department, 1-3, Iuliu Maniu Ave., Romania 061071", "University Politehnica of Bucharest", "University Politehnica of Bucharest", "Universitatea Politehnica din Bucure\u0219ti, Novum Invest, Bucure\u0219ti, Militari, Sector 6, Municipiul Bucure\u0219ti, 060042, Rom\u00e2nia", "44.43918115", "26.05044565", "edu", "", "Romania", "2016"], ["Aggregated Residual Transformations for Deep Neural Networks", "", "UC San Diego", "UC San Diego", "9500 Gilman Dr, La Jolla, CA 92093, USA", "32.88006040", "-117.23401350", "edu", "", "United States", "2017"], ["Looking deeper and transferring attention for image captioning", "Shanghai Engineering Research Center of Industrial Vision Perception & Intelligent Computing, Shanghai, China", "Shanghai Engineering Research Center of Industrial Vision Perception & Intelligent Computing, Shanghai, China", "Shanghai Engineering Research Center of Industrial Vision Perception & Intelligent Computing, Shanghai, China", "Shanghai, China", "31.23039040", "121.47370210", "edu", "", "China", "2018"], ["Evaluating ResNeXt Model Architecture for Image Classification", "", "University of Waterloo", "University of Waterloo", "University of Waterloo, 200, University Avenue West, Northdale, Beechwood, Waterloo, Regional Municipality of Waterloo, Ontario, N2L 3G1, Canada", "43.47061295", "-80.54724732", "edu", "", "Canada", "2018"], ["Robot Classification of Human Interruptibility and a Study of Its Effects", "Georgia Institute of Technology, Atlanta, GA", "Georgia Institute of Technology", "Georgia Institute of Technology", "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "33.77603300", "-84.39884086", "edu", "", "United States", "2018"], ["Fake Sentence Detection as a Training Task for Sentence Encoding", "", "Stony Brook University", "Stony Brook University", "Stony Brook University, 100, Nicolls Road, Stony Brook, Suffolk County, New York, 11794, USA", "40.91531960", "-73.12706260", "edu", "", "United States", "2018"], ["Decoupled Novel Object Captioner", "", "Chinese Academy of Sciences", "Chinese Academy of Sciences", "\u4e2d\u56fd\u79d1\u5b66\u9662\u5fc3\u7406\u7814\u7a76\u6240, 16, \u6797\u8403\u8def, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100101, \u4e2d\u56fd", "40.00447950", "116.37023800", "edu", "", "China", "2018"], ["ScratchDet : Training Single-Shot Object Detectors from Scratch", "", "University of Chinese Academy of Sciences", "University of Chinese Academy of Sciences", "University of Chinese Academy of Sciences, UCAS, Yuquanlu, \u7389\u6cc9\u8def, \u7530\u6751, \u6d77\u6dc0\u533a, 100049, \u4e2d\u56fd", "39.90828040", "116.24585270", "edu", "", "China", "2018"], ["The Emotional Impact of Audio-Visual Stimuli", "", "Rochester Institute of Technology", "Rochester Institute of Technology", "Rochester Institute of Technology (RIT), 1, Lomb Memorial Drive, Bailey, Henrietta Town, Monroe County, New York, 14623, USA", "43.08250655", "-77.67121663", "edu", "", "United States", "2018"], ["Question action relevance and editing for visual question answering", "Dipartimento di Informatica, Universit\u00e0 di Salerno, Fisciano, Italy", "Dipartimento di Informatica, Universit\u00e0 di Salerno, Fisciano, Italy", "Dipartimento di Informatica, Universit\u00e0 di Salerno, Fisciano, Italy", "Universit\u00e0 di Salerno Via Papa, Via Giovanni Paolo II, 132, 84084 Fisciano SA, Italy", "40.77434920", "14.78901500", "edu", "", "Italy", "2018"], ["Cross Modal Distillation for Supervision Transfer", "", "University of California, Berkeley", "University of California, Berkeley", "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "37.86871260", "-122.25586815", "edu", "", "United States", "2016"], ["Hot Anchors: A Heuristic Anchors Sampling Method in RCNN-Based Object Detection", "", "University of Chinese Academy of Sciences", "University of Chinese Academy of Sciences", "University of Chinese Academy of Sciences, UCAS, Yuquanlu, \u7389\u6cc9\u8def, \u7530\u6751, \u6d77\u6dc0\u533a, 100049, \u4e2d\u56fd", "39.90828040", "116.24585270", "edu", "", "China", "2018"], ["HiDDeN: Hiding Data With Deep Networks", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "United States", "2018"], ["Spatial-Aware Object Embeddings for Zero-Shot Localization and Classification of Actions", "", "University of Amsterdam", "University of Amsterdam", "Institute for Logic, Language and Computation (ILLC), 107, Science Park, Oost-Watergraafsmeer, Amsterdam, Oost, Amsterdam, Noord-Holland, Nederland, 1098XG, Nederland", "52.35536550", "4.95016440", "edu", "", "Netherlands", "2017"], ["Subitizing with Variational Autoencoders", "", "University of Amsterdam", "University of Amsterdam", "Institute for Logic, Language and Computation (ILLC), 107, Science Park, Oost-Watergraafsmeer, Amsterdam, Oost, Amsterdam, Noord-Holland, Nederland, 1098XG, Nederland", "52.35536550", "4.95016440", "edu", "", "Netherlands", "2018"], ["PoseTrack: Joint Multi-person Pose Estimation and Tracking", "", "University of Adelaide", "University of Adelaide", "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "-34.91892260", "138.60423668", "edu", "", "Australia", "2017"], ["Fast, Diverse and Accurate Image Captioning Guided By Part-of-Speech", "", "University of Illinois, Urbana-Champaign", "University of Illinois, Urbana-Champaign", "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "40.11116745", "-88.22587665", "edu", "", "United States", "2018"], ["Answer-Type Prediction for Visual Question Answering", "", "Rochester Institute of Technology", "Rochester Institute of Technology", "Rochester Institute of Technology (RIT), 1, Lomb Memorial Drive, Bailey, Henrietta Town, Monroe County, New York, 14623, USA", "43.08250655", "-77.67121663", "edu", "", "United States", "2016"], ["Semantic Image Segmentation via Deep Parsing Network", "", "Chinese University of Hong Kong", "Chinese University of Hong Kong", "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "22.41626320", "114.21093180", "edu", "", "China", "2015"], ["Bird Species Classification using Transfer Learning with Multistage Training", "", "Jadavpur University", "Jadavpur University", "Jadavpur University, Chingrighata Flyover, Basani Devi Colony, Kolkata, H\u0101ora, West Bengal, 700098, India", "22.56115370", "88.41310194", "edu", "", "India", "2018"], ["Traits & Transferability of Adversarial Examples against Instance Segmentation & Object Detection", "", "University of Illinois, Urbana-Champaign", "University of Illinois, Urbana-Champaign", "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "40.11116745", "-88.22587665", "edu", "", "United States", "2018"], ["Hierarchical Recurrent Neural Encoder for Video Representation with Application to Captioning", "", "University of Technology Sydney", "University of Technology Sydney", "University of Technology Sydney, Omnibus Lane, Ultimo, Sydney, NSW, 2007, Australia", "-33.88096510", "151.20107299", "edu", "", "Australia", "2016"], ["Self-Contained Stylization via Steganography for Reverse and Serial Style Transfer", "", "National Chiao Tung University", "National Chiao Tung University", "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", "24.78676765", "120.99724412", "edu", "", "Taiwan", "2018"], ["Improving Fast Segmentation With Teacher-Student Learning", "", "Nanyang Technological University", "Nanyang Technological University", "NTU, Faculty Avenue, Jurong West, Southwest, 637460, Singapore", "1.34841040", "103.68297965", "edu", "", "Singapore", "2018"], ["Describing Natural Images Containing Novel Objects with Knowledge Guided Assitance", "", "Karlsruhe Institute of Technology", "Karlsruhe Institute of Technology", "KIT, Leopoldshafener Allee, Linkenheim, Linkenheim-Hochstetten, Landkreis Karlsruhe, Regierungsbezirk Karlsruhe, Baden-W\u00fcrttemberg, 76351, Deutschland", "49.10184375", "8.43312560", "edu", "", "Germany", "2017"], ["Do deep features retrieve X ? : A tool for quick inspection of deep visual similarities", "", "University of British Columbia", "University of British Columbia", "University of British Columbia, Eagles Drive, Hawthorn Place, University Endowment Lands, Metro Vancouver, British Columbia, V6T, Canada", "49.25839375", "-123.24658161", "edu", "", "Canada", "2015"], ["The Middle Child Problem: Revisiting Parametric Min-Cut and Seeds for Object Proposals", "", "Oregon State University", "Oregon State University", "OSU Beaver Store, 538, Southwest 6th Avenue, Portland Downtown, Portland, Multnomah County, Oregon, 97204, USA", "45.51982890", "-122.67797964", "edu", "", "United States", "2015"], ["The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "United States", "2016"], ["Traffic-Sign Detection and Classification in the Wild", "", "Beijing, China", "Beijing, China", "Beijing, China", "39.90419990", "116.40739630", "edu", "", "China", "2016"], ["Progressively Diffused Networks for Semantic Image Segmentation", "", "SenseTime", "SenseTime", "China, Beijing Shi, Haidian Qu, WuDaoKou, Zhongguancun E Rd, 1\u53f7-7", "39.99300800", "116.32988200", "company", "1 Zhongguancun E Rd, Haidian Qu, China", "China", "2017"], ["Subspace Alignment Based Domain Adaptation for RCNN Detector", "", "IIT Kanpur", "IIT Kanpur", "Kalyanpur, Kanpur, Uttar Pradesh 208016, India", "26.51233880", "80.23290000", "edu", "", "India", "2015"], ["Segment-Phrase Table for Semantic Segmentation, Visual Entailment and Paraphrasing", "", "University of Washington", "University of Washington", "University of Washington, Rainier Vista, Montlake, University District, Seattle, King County, Washington, 98195, USA", "47.65432380", "-122.30800894", "edu", "", "United States", "2015"], ["Towards High Performance Video Object Detection for Mobiles", "", "Microsoft Research Asia", "Microsoft Research Asia", "1 Memorial Dr, Cambridge, MA 02142, USA", "42.36142560", "-71.08120920", "company", "", "United States", "2018"], ["Loss Functions for Multiset Prediction", "", "New York University", "New York University", "NYU, West 4th Street, NoHo Historic District, NoHo, Manhattan, Manhattan Community Board 2, New York County, NYC, New York, 10012, USA", "40.72925325", "-73.99625394", "edu", "", "United States", "2018"], ["Fast Online Object Tracking and Segmentation: A Unifying Approach", "", "University of Oxford", "University of Oxford", "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "51.75345380", "-1.25400997", "edu", "", "United Kingdom", "2018"], ["Looking for ELMo's friends: Sentence-Level Pretraining Beyond Language Modeling.", "", "Johns Hopkins University", "Johns Hopkins University", "Baltimore, MD 21218, USA", "39.32990130", "-76.62051770", "edu", "", "", "2018"], ["Transferable Semi-Supervised Semantic Segmentation", "", "Beckman Institute", "Beckman Institute", "Beckman Institute, The Presidents' Walk, Urbana, Champaign County, Illinois, 61801-2341, USA", "40.11571585", "-88.22750772", "edu", "", "United States", "2018"], ["Multi-modal Capsule Routing for Actor and Action Video Segmentation Conditioned on Natural Language Queries", "", "University of Central Florida", "University of Central Florida", "University of Central Florida, Libra Drive, University Park, Orange County, Florida, 32816, USA", "28.59899755", "-81.19712501", "edu", "", "United States", "2018"], ["Enhancement of SSD by concatenating feature maps for object detection.", "", "Seoul National University", "Seoul National University", "\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", "37.26728000", "126.98411510", "edu", "", "South Korea", "2017"], ["Generation with Recursive Neural Networks", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "United States", "2016"], ["Active learning and discovery of object categories in the presence of unnameable instances", "Computer Vision Group, Friedrich Schiller University Jena, Germany", "Friedrich Schiller University Jena", "Computer Vision Group, Friedrich Schiller University Jena, Germany", "Ernst-Abbe-Platz 2, 07743 Jena, Germany", "50.92776710", "11.58217290", "edu", "", "Germany", "2015"], ["Ambiguity Helps: Classification with Disagreements in Crowdsourced Annotations", "", "Harvard University", "Harvard University", "Harvard University, Soldiers Field Road, Allston, Boston, Suffolk County, Massachusetts, 02163, USA", "42.36782045", "-71.12666653", "edu", "", "United States", "2016"], ["Spott: On-the-Spot e-Commerce for Television Using Deep Learning-Based Video Analysis Techniques", "Ghent University - imec, ELIS - IDLab, Pietersnieuwstraat, Ghent", "Ghent University", "Ghent University", "St. Pietersnieuwstraat 33, 9000 Gent, Belgium", "51.04656190", "3.72791810", "edu", "", "Belgium", "2017"], ["Improving Multi-Person Pose Estimation using Label Correction", "", "Keio University", "Keio University", "\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", "35.54169690", "139.63471840", "edu", "", "Japan", "2018"], ["A Focused Dynamic Attention Model for Visual Question Answering", "", "National University of Singapore", "National University of Singapore", "NUS, Former 1936 British Outpost, Nepal Hill, Clementi, Southwest, 117542, Singapore", "1.29620180", "103.77689944", "edu", "", "Singapore", "2016"], ["Solving Visual Madlibs with Multiple Cues", "", "University of Illinois, Urbana-Champaign", "University of Illinois, Urbana-Champaign", "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "40.11116745", "-88.22587665", "edu", "", "United States", "2016"], ["Could we create a training set for image captioning using automatic translation?", "Bilgisayar Mühendisliği, Orta Doggu Teknik Üniversitesi, Ankara, Türkiye", "Bilgisayar M\u00fchendisli\u011fi, Orta Doggu Teknik \u00dcniversitesi, Ankara, T\u00fcrkiye", "Bilgisayar Mühendisliği, Orta Doggu Teknik Üniversitesi, Ankara, Türkiye", "\u00dcniversiteler Mh., 06800 \u00c7ankaya/Ankara, Turkey", "39.89183900", "32.78334710", "edu", "", "Poland", "2017"], ["Unprecedented Usage of Pre-trained CNNs on Beauty Product", "University of Malaya, Kuala Lumpur, Malaysia", "University of Malaya", "University of Malaya", "UM, Lingkaran Wawasan, Bukit Pantai, Bangsar, KL, 50603, Malaysia", "3.12267405", "101.65356103", "edu", "", "Malaysia", "2018"], ["Improved Image Captioning via Policy Gradient optimization of SPIDEr", "", "University of Oxford", "University of Oxford", "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "51.75345380", "-1.25400997", "edu", "", "United Kingdom", "2017"], ["High performance and fast object detection in road environments", "DGIST", "DGIST", "DGIST", "South Korea, Daegu, Dalseong-gun, Yuga-myeon, \ud14c\ud06c\ub178\uc911\uc559\ub300\ub85c 333", "35.70528600", "128.45710200", "edu", "", "South Korea", "2017"], ["Object Recognition Based on Amounts of Unlabeled Data", "", "Beijing Institute of Technology", "Beijing Institute of Technology University", "\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", "39.95866520", "116.30971281", "edu", "", "China", "2016"], ["Multi-Label Music Genre Classification from Audio, Text and Images Using Deep Features", "", "Universitat Pompeu Fabra", "Universitat Pompeu Fabra", "Dip\u00f2sit de les Aig\u00fces, Carrer de Wellington, la Vila Ol\u00edmpica del Poblenou, Ciutat Vella, Barcelona, BCN, CAT, 08071, Espa\u00f1a", "41.39044285", "2.18891949", "edu", "", "Spain", "2017"], ["Zero-Shot Detection", "", "Boston University", "Boston University", "BU, Bay State Road, Fenway, Boston, Suffolk County, Massachusetts, 02215, USA", "42.35042530", "-71.10056114", "edu", "", "United States", "2018"], ["What are the Visual Features Underlying Human Versus Machine Vision?", "", "Brown University", "Brown University", "Brown University, Waterman Street, College Hill, Providence, Bristol, Rhode Island, 02912, USA", "41.82686820", "-71.40123146", "edu", "", "United States", "2017"], ["Material Recognition from Local Appearance in Global Context", "", "Drexel University", "Drexel University", "Drexel University, Arch Street, Powelton Village, Philadelphia, Philadelphia County, Pennsylvania, 19104, USA", "39.95740000", "-75.19026706", "edu", "", "United States", "2016"], ["Complex Object Classification: A Multi-Modal Multi-Instance Multi-Label Deep Network with Optimal Transport", "Nanjing University, Nanjing, China", "Nanjing University", "Nanjing University", "NJU, \u4e09\u6c5f\u8def, \u9f13\u697c\u533a, \u5357\u4eac\u5e02, \u6c5f\u82cf\u7701, 210093, \u4e2d\u56fd", "32.05659570", "118.77408833", "edu", "", "China", "2018"], ["What's the point: Semantic segmentation with point supervision", "", "University of Edinburgh", "University of Edinburgh", "New College, New College Courtyard, The Mound, Old Town, Edinburgh, City of Edinburgh, Scotland, EH1 2LX, UK", "55.94951105", "-3.19534913", "edu", "", "United Kingdom", "2016"], ["Extreme Clicking for Efficient Object Annotation", "", "University of Edinburgh", "University of Edinburgh", "New College, New College Courtyard, The Mound, Old Town, Edinburgh, City of Edinburgh, Scotland, EH1 2LX, UK", "55.94951105", "-3.19534913", "edu", "", "United Kingdom", "2017"], ["Visual Question Answering with Memory-Augmented Networks", "", "University of Adelaide", "University of Adelaide", "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "-34.91892260", "138.60423668", "edu", "", "Australia", "2018"], ["Data Augmentation for Cnn-Based People Detection in Aerial Images", "Department of Information Engineering and Computer Science, Feng Chia University, Taiwan", "Feng Chia University", "Feng Chia University", "\u9022\u7532\u5927\u5b78, 100, \u6587\u83ef\u8def, \u897f\u5e73\u91cc, \u897f\u5c6f\u5340, \u81fa\u4e2d\u5e02, 40724, \u81fa\u7063", "24.18005755", "120.64836072", "edu", "", "Taiwan", "2018"], ["Deep correlation for matching images and text", "Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, United Kingdom, GU2 7XH", "University of Surrey", "University of Surrey", "University of Surrey, Spine Road, Guildford Park, Guildford, Surrey, South East, England, GU2 7XH, UK", "51.24303255", "-0.59001382", "edu", "", "United Kingdom", "2015"], ["Recurrent Models for Situation Recognition", "", "University of Illinois, Urbana-Champaign", "University of Illinois, Urbana-Champaign", "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "40.11116745", "-88.22587665", "edu", "", "United States", "2017"], ["Deep Attribute-preserving Metric Learning for Natural Language Object Retrieval", "National University of Singapore, Singapore, Singapore", "National University of Singapore", "National University of Singapore", "NUS, Former 1936 British Outpost, Nepal Hill, Clementi, Southwest, 117542, Singapore", "1.29620180", "103.77689944", "edu", "", "Singapore", "2017"], ["Using Syntax to Ground Referring Expressions in Natural Images", "", "Carnegie Mellon University", "Carnegie Mellon University", "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "37.41021930", "-122.05965487", "edu", "", "United States", "2018"], ["GANtruth - an unpaired image-to-image translation method for driving scenarios", "", "KTH Royal Institute of Technology, Stockholm", "KTH Royal Institute of Technology, Stockholm", "KTH, Teknikringen, L\u00e4rkstaden, Norra Djurg\u00e5rden, \u00d6stermalms stadsdelsomr\u00e5de, Sthlm, Stockholm, Stockholms l\u00e4n, Svealand, 114 28, Sverige", "59.34986645", "18.07063213", "edu", "", "Sweden", "2018"], ["Revisiting Pre-training: An Efficient Training Method for Image Classification", "", "Beckman Institute", "Beckman Institute", "Beckman Institute, The Presidents' Walk, Urbana, Champaign County, Illinois, 61801-2341, USA", "40.11571585", "-88.22750772", "edu", "", "United States", "2018"], ["Evaluation of Segmentation Quality via Adaptive Composition of Reference Segmentations", "School of Engineering, University of California, Merced, CA", "University of California", "University of California", "Berkeley, CA, USA", "37.87189920", "-122.25853990", "edu", "", "United States", "2017"], ["Semantic Segmentation With Object Clique Potentials", "", "Chinese University of Hong Kong", "Chinese University of Hong Kong", "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "22.41626320", "114.21093180", "edu", "", "China", "2015"], ["Neural Module Networks", "", "University of California, Berkeley", "University of California, Berkeley", "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "37.86871260", "-122.25586815", "edu", "", "United States", "2016"], ["ImagineNet : Style Transfer from Fine Art to Graphical User Interfaces", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "United States", "2018"], ["Investigating the feature collection for semantic segmentation via single skip connection", "", "Ajou University", "Ajou University", "\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", "37.28300030", "127.04548469", "edu", "", "Korea", "2017"], ["Understanding and Controlling User Linkability in Decentralized Learning", "", "Max Planck Institute for Informatics", "Max Planck Institute for Informatics", "MPII, E1 4, Campus, Universit\u00e4t, Sankt Johann, Bezirk Mitte, Saarbr\u00fccken, Regionalverband Saarbr\u00fccken, Saarland, 66123, Deutschland", "49.25795660", "7.04577417", "edu", "", "Germany", "2018"], ["PolyMapper: Extracting City Maps using Polygons", "", "ETH Z\u00fcrich", "ETH Z\u00fcrich", "ETH Z\u00fcrich, 101, R\u00e4mistrasse, Hochschulen, Altstadt, Z\u00fcrich, Bezirk Z\u00fcrich, Z\u00fcrich, 8092, Schweiz/Suisse/Svizzera/Svizra", "47.37645340", "8.54770931", "edu", "", "Switzerland", "2018"], ["Weakly and Semi Supervised Human Body Part Parsing via Pose-Guided Knowledge Transfer", "", "University of California", "University of California", "Berkeley, CA, USA", "37.87189920", "-122.25853990", "edu", "", "United States", "2018"], ["A Fast Multi-Task CNN for Spatial Understanding of Traffic Scenes", "Institute of Control Theory and Systems Engineering, TU Dortmund University, Otto-Hahn-Str. 8, Dortmund, 44227, Germany", "TU Dortmund University", "Institute of Control Theory and Systems Engineering, TU Dortmund University, Otto-Hahn-Str. 8, Dortmund, 44227, Germany", "Emil-Figge-Stra\u00dfe 50, 44227 Dortmund, Germany", "51.49219020", "7.41413620", "edu", "", "Germany", "2018"], ["Resolving References to Objects in Photographs using the Words-As-Classifiers Model", "", "Bielefeld University", "Bielefeld University", "Fachhochschule Bielefeld FB Gestaltung, 3, Lampingstra\u00dfe, Mitte, Bielefeld, Regierungsbezirk Detmold, Nordrhein-Westfalen, 33615, Deutschland", "52.02804210", "8.51148270", "edu", "", "Germany", "2016"], ["Image Captioning with Word Level Attention", "Department of Computer Science & Technology, Tongji University, Shanghai, P. R. China", "Tongji University", "Tongji University", "\u540c\u6d4e\u5927\u5b66, 1239, \u56db\u5e73\u8def, \u6c5f\u6e7e, \u8679\u53e3\u533a, \u4e0a\u6d77\u5e02, 200092, \u4e2d\u56fd", "31.28473925", "121.49694909", "edu", "", "China", "2018"], ["Class Rectification Hard Mining for Imbalanced Deep Learning", "", "Queen Mary University of London", "Queen Mary University of London", "Queen Mary (University of London), Mile End Road, Globe Town, Mile End, London Borough of Tower Hamlets, London, Greater London, England, E1 4NS, UK", "51.52472720", "-0.03931035", "edu", "", "United Kingdom", "2017"], ["Learning deep structured network for weakly supervised change detection", "", "University of Western Australia", "University of Western Australia", "UWA, 35, Underwood Avenue, Daglish, Perth, Western Australia, 6009, Australia", "-31.95040445", "115.79790037", "edu", "", "Australia", "2017"], ["Towards semantic visual representation: augmenting image representation with natural language descriptors", "Indian Institute of Science, Bangalore, India", "Indian Institute of Science Bangalore", "Indian Institute of Science Bangalore", "IISc, Gulmohar Marg, RMV Stage II - 1st Block, Aramane Nagara Ward, West Zone, Bengaluru, Bangalore Urban, Karnataka, 560012, India", "13.02223470", "77.56718325", "edu", "", "India", "2016"], ["Sequence to Sequence -- Video to Text", "", "University of California, Berkeley", "University of California, Berkeley", "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "37.86871260", "-122.25586815", "edu", "", "United States", "2015"], ["Efficient Coarse-to-Fine Non-Local Module for the Detection of Small Objects.", "", "Weizmann Institute of Science", "Weizmann Institute of Science", "\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", "31.90784990", "34.81334092", "edu", "", "Israel", "2018"], ["Semantic Instance Annotation of Street Scenes by 3D to 2D Label Transfer", "", "University of Washington", "University of Washington", "University of Washington, Rainier Vista, Montlake, University District, Seattle, King County, Washington, 98195, USA", "47.65432380", "-122.30800894", "edu", "", "United States", "2016"], ["Active learning for structured probabilistic models with histogram approximation", "Virginia Tech, USA", "Virginia Tech", "Virginia Tech", "Blacksburg, VA 24061, USA", "37.22838430", "-80.42341670", "edu", "", "United States", "2015"], ["RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation", "", "University of Adelaide", "University of Adelaide", "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "-34.91892260", "138.60423668", "edu", "", "Australia", "2017"], ["Beyond caption to narrative: Video captioning with multiple sentences", "", "University of Tokyo", "University of Tokyo", "\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", "35.90204480", "139.93622009", "edu", "", "Japan", "2016"], ["Learning to Segment Every Thing", "", "University of California, Berkeley", "University of California, Berkeley", "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "37.86871260", "-122.25586815", "edu", "", "United States", "2018"], ["Fast Patch-based Style Transfer of Arbitrary Style.", "", "University of British Columbia", "University of British Columbia", "University of British Columbia, Eagles Drive, Hawthorn Place, University Endowment Lands, Metro Vancouver, British Columbia, V6T, Canada", "49.25839375", "-123.24658161", "edu", "", "Canada", "2016"], ["Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation", "", "Google", "Google, Inc.", "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "37.42199990", "-122.08405750", "company", "Google, Mountain View, CA", "United States", "2018"], ["Mining Object Parts from CNNs via Active Question-Answering", "", "University of California, Los Angeles", "University of California, Los Angeles", "200 UCLA, Medical Plaza Driveway Suite 540, Los Angeles, CA 90095, USA", "34.06877880", "-118.44500940", "edu", "", "United States", "2017"], ["A review of object detection based on convolutional neural network", "Fundamental Science on Communication Information Transmission and Fusion Technology Laboratory, Hangzhou 310018, China", "Fundamental Science on Communication Information Transmission and Fusion Technology Laboratory, Hangzhou 310018, China", "Fundamental Science on Communication Information Transmission and Fusion Technology Laboratory, Hangzhou 310018, China", "Jianggan, Hangzhou, Zhejiang, China, 310018", "30.31600970", "120.37394070", "edu", "", "China", "2017"], ["Online Real-Time Multiple Spatiotemporal Action Localisation and Prediction", "", "Oxford University", "Oxford University", "University College, Logic Lane, Grandpont, Oxford, Oxon, South East, England, OX1 4EX, UK", "51.75208490", "-1.25166460", "edu", "", "United Kingdom", "2017"], ["Procedural Generation of Videos to Train Deep Action Recognition Networks", "", "Toyota Research Institute", "Toyota Research Institute", "Toyota Research Institute, 4440, West El Camino Real, Los Altos, Santa Clara County, California, 94022, USA", "37.40253645", "-122.11655107", "edu", "", "United States", "2017"], ["High-Value Target Detection", "", "University of Tartu", "UNIVERSITY OF TARTU", "Paabel, University of Tartu, 17, \u00dclikooli, Kesklinn, Tartu linn, Tartu, Tartu linn, Tartu maakond, 53007, Eesti", "58.38131405", "26.72078081", "edu", "", "Estonia", "2018"], ["Looking Beyond a Clever Narrative: Visual Context and Attention are Primary Drivers of Affect in Video Advertisements", "", "University of Illinois, Urbana-Champaign", "University of Illinois, Urbana-Champaign", "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "40.11116745", "-88.22587665", "edu", "", "United States", "2018"], ["Counting Everyday Objects in Everyday Scenes", "", "Georgia Institute of Technology", "Georgia Institute of Technology", "Georgia Tech, Atlantic Drive Northwest, Bellwood, Rockdale, Atlanta, Fulton County, Georgia, 30318, USA", "33.77603300", "-84.39884086", "edu", "", "United States", "2017"], ["Bottle Detection in the Wild Using Low-Altitude Unmanned Aerial Vehicles", "Wuhan University, School of Electronic Information, Wuhan, 430072, China", "Wuhan University of Technology", "Wuhan University of Technology", "\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", "30.60903415", "114.35142840", "edu", "", "China", "2018"], ["Deep Learning Based Surveillance System for Open Critical Areas", "", "University of Florence", "University of Florence", "Piazza di San Marco, 4, 50121 Firenze FI, Italy", "43.77764260", "11.25976500", "edu", "", "Italy", "2018"], ["An efficient license plate recognition system using convolution neural networks", "Department of Electrical Engineering, National Taiwan Normal University, Taipei 106, Taiwan", "National Taiwan Normal University", "National Taiwan Normal University", "\u5e2b\u5927\u5206\u90e8, 88, \u6c40\u5dde\u8def\u56db\u6bb5, \u842c\u5e74\u91cc, \u6587\u5c71\u5340, \u81fa\u5317\u5e02, 11677, \u81fa\u7063", "25.00823205", "121.53577153", "edu", "", "Taiwan", "2018"], ["Online Adaptation of Convolutional Neural Networks for Video Object Segmentation", "", "RWTH Aachen University", "RWTH Aachen University", "RWTH Aachen, Mies-van-der-Rohe-Stra\u00dfe, K\u00f6nigsh\u00fcgel, Aachen-Mitte, Aachen, St\u00e4dteregion Aachen, Regierungsbezirk K\u00f6ln, Nordrhein-Westfalen, 52074, Deutschland", "50.77917030", "6.06728733", "edu", "", "Germany", "2017"], ["Improving Generalization via Scalable Neighborhood Component Analysis", "", "Microsoft Research Asia", "Microsoft Research Asia", "1 Memorial Dr, Cambridge, MA 02142, USA", "42.36142560", "-71.08120920", "company", "", "United States", "2018"], ["Attacking Visual Language Grounding with Adversarial Examples: A Case Study on Neural Image Captioning", "", "IBM Research, North Carolina", "IBM Research", "IBM, East Cornwallis Road, Research Triangle Park, Nelson, Durham County, North Carolina, 27709, USA", "35.90422720", "-78.85565763", "company", "", "United States", "2018"], ["Incremental Segmentation on Private Data without Catastrophic Forgetting", "", "Peking University", "Peking University", "\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", "39.99223790", "116.30393816", "edu", "", "China", "2018"], ["Intelligent Computing Methodologies", "Tongji University, Shanghai, China", "Tongji University", "Tongji University", "\u540c\u6d4e\u5927\u5b66, 1239, \u56db\u5e73\u8def, \u6c5f\u6e7e, \u8679\u53e3\u533a, \u4e0a\u6d77\u5e02, 200092, \u4e2d\u56fd", "31.28473925", "121.49694909", "edu", "", "China", "2018"], ["An Intriguing Influence of Visual Data in Learning a Representation", "", "Carnegie Mellon University", "Carnegie Mellon University", "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "37.41021930", "-122.05965487", "edu", "", "United States", "2018"], ["Multiview Supervision By Registration", "", "University of Minnesota", "University of Minnesota", "WeismanArt, 333, East River Parkway, Marcy-Holmes, Phillips, Minneapolis, Hennepin County, Minnesota, 55455, USA", "44.97308605", "-93.23708813", "edu", "", "United States", "2018"], ["On the Iterative Refinement of Densely Connected Representation Levels for Semantic Segmentation", "", "Computer Vision Center, Barcelona", "Computer Vision Center, Barcelona", "Campus UAB, Edifici O, s/n, 08193 Cerdanyola del Vall\u00e8s, Barcelona, Spain", "41.50089570", "2.11155300", "edu", "", "Spain", "2018"], ["Multi-evidence Filtering and Fusion for Multi-label Classification, Object Detection and Semantic Segmentation Based on Weakly Supervised Learning", "", "University of Hong Kong", "University of Hong Kong", "\u6d77\u6d0b\u79d1\u5b78\u7814\u7a76\u6240 The Swire Institute of Marine Science, \u9db4\u5480\u9053 Cape D'Aguilar Road, \u9db4\u5480\u4f4e\u96fb\u53f0 Cape D'Aguilar Low-Level Radio Station, \u77f3\u6fb3 Shek O, \u82bd\u83dc\u5751\u6751 Nga Choy Hang Tsuen, \u5357\u5340 Southern District, \u9999\u6e2f\u5cf6 Hong Kong Island, HK, \u4e2d\u56fd", "22.20814690", "114.25964115", "edu", "", "China", "2018"], ["DeepDiary: Automatic Caption Generation for Lifelogging Image Streams.", "", "Indiana University", "Indiana University", "Indiana University East, West Cart Road, Richmond, Wayne County, Indiana, 47374, USA", "39.86948105", "-84.87956905", "edu", "", "United States", "2016"], ["Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis", "", "University of Michigan", "University of Michigan", "University of Michigan, 500, Hayward Street, Ann Arbor, Washtenaw County, Michigan, 48109, USA", "42.29421420", "-83.71003894", "edu", "", "United States", "2018"], ["Progressive Visual Object Detection with Positive Training Examples Only", "Department of Signal Processing, Tampere University of Technology, Tampere, Finland", "Tampere University of Technology", "Tampere University of Technology", "TTY, 10, Korkeakoulunkatu, Finninm\u00e4ki, Hervanta, Tampere, Tampereen seutukunta, Pirkanmaa, L\u00e4nsi- ja Sis\u00e4-Suomen aluehallintovirasto, L\u00e4nsi-Suomi, Manner-Suomi, 33720, Suomi", "61.44964205", "23.85877462", "edu", "", "Finland", "2015"], ["Text-to-Image Generation Using Multi-Instance StackGan", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "United States", ""], ["Bundled Object Context for Referring Expressions", "Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, China", "Chinese Academy of Sciences", "Chinese Academy of Sciences", "\u4e2d\u56fd\u79d1\u5b66\u9662\u5fc3\u7406\u7814\u7a76\u6240, 16, \u6797\u8403\u8def, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100101, \u4e2d\u56fd", "40.00447950", "116.37023800", "edu", "", "China", "2018"], ["Quantifying the visual concreteness of words and topics in multimodal datasets", "", "Cornell University", "Cornell University", "Cornell University, Forest Home Drive, Forest Home, Tompkins County, New York, 14853, USA", "42.45055070", "-76.47835130", "edu", "", "United States", "2018"], ["A task in a suit and a tie: paraphrase generation with semantic augmentation", "", "University of Texas at Austin", "University of Texas at Austin", "University of Texas at Austin, 1, East 23rd Street, The Drag, Austin, Travis County, Texas, 78712, USA", "30.28415100", "-97.73195598", "edu", "", "United States", "2018"], ["Show, Adapt and Tell: Adversarial Training of Cross-Domain Image Captioner", "", "Microsoft Research Asia", "Microsoft Research Asia", "1 Memorial Dr, Cambridge, MA 02142, USA", "42.36142560", "-71.08120920", "company", "", "United States", "2017"], ["Learning Visual Classifiers using Human-centric Annotations", "", "Microsoft", "Microsoft Corporation, Redmond, WA, USA", "One Microsoft Way, Redmond, WA 98052, USA", "47.64233180", "-122.13693020", "company", "", "United States", "2015"], ["FoveaNet: Perspective-Aware Urban Scene Parsing", "", "Tsinghua University", "Tsinghua University", "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "40.00229045", "116.32098908", "edu", "", "China", "2017"], ["Exploiting Saliency for Object Segmentation from Image Level Labels", "", "University of Amsterdam", "University of Amsterdam", "Institute for Logic, Language and Computation (ILLC), 107, Science Park, Oost-Watergraafsmeer, Amsterdam, Oost, Amsterdam, Noord-Holland, Nederland, 1098XG, Nederland", "52.35536550", "4.95016440", "edu", "", "Netherlands", "2017"], ["A Structured Model For Action Detection", "", "Carnegie Mellon University", "Carnegie Mellon University", "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "37.41021930", "-122.05965487", "edu", "", "United States", "2018"], ["RepMet: Representative-based metric learning for classification and one-shot object detection", "", "Technion", "Technion", "Haifa, 3200003, Israel", "32.77677830", "35.02312710", "edu", "", "Israel", "2018"], ["What is the Role of Recurrent Neural Networks (RNNs) in an Image Caption Generator?", "", "University of Malta", "University of Malta", "University of Malta, Ring Road, Japanese Garden, L-Imsida, Malta, MSD 9027, Malta", "35.90232260", "14.48341890", "edu", "", "Malta", "2017"], ["Batch-normalized recurrent highway networks", "", "Rochester Institute of Technology", "Rochester Institute of Technology", "Rochester Institute of Technology (RIT), 1, Lomb Memorial Drive, Bailey, Henrietta Town, Monroe County, New York, 14623, USA", "43.08250655", "-77.67121663", "edu", "", "United States", "2017"], ["Weakly Supervised Semantic Segmentation Using Web-Crawled Videos", "", "DGIST", "DGIST", "South Korea, Daegu, Dalseong-gun, Yuga-myeon, \ud14c\ud06c\ub178\uc911\uc559\ub300\ub85c 333", "35.70528600", "128.45710200", "edu", "", "South Korea", "2017"], ["Talking about other people: an endless range of possibilities", "", "University of Copenhagen", "University of Copenhagen", "K\u00f8benhavns Universitet, Krystalgade, K\u00f8dbyen, Vesterbro, K\u00f8benhavn, K\u00f8benhavns Kommune, Region Hovedstaden, 1165, Danmark", "55.68015020", "12.57232700", "edu", "", "Denmark", "2018"], ["What Actions are Needed for Understanding Human Actions in Videos?", "", "Carnegie Mellon University", "Carnegie Mellon University", "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "37.41021930", "-122.05965487", "edu", "", "United States", "2017"], ["Kobe University , NICT and University of Siegen at TRECVID 2017 AVS Task", "", "Kobe University", "Kobe University", "\u795e\u6238\u5927\u5b66, \u7058\u4e09\u7530\u7dda, \u7058\u533a, \u795e\u6238\u5e02, \u5175\u5eab\u770c, \u8fd1\u757f\u5730\u65b9, 657-00027, \u65e5\u672c", "34.72757140", "135.23710000", "edu", "", "Japan", "2018"], ["DeepSign: Deep Learning based Traffic Sign Recognition", "The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China", "Chinese Academy of Sciences", "Chinese Academy of Sciences", "\u4e2d\u56fd\u79d1\u5b66\u9662\u5fc3\u7406\u7814\u7a76\u6240, 16, \u6797\u8403\u8def, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100101, \u4e2d\u56fd", "40.00447950", "116.37023800", "edu", "", "China", "2018"]]}
\ No newline at end of file +{"id": "5e0f8c355a37a5a89351c02f174e7a5ddcb98683", "paper": {"key": "coco", "name": "COCO", "title": "Microsoft COCO: Common Objects in Context", "year": "2014"}, "address": {}, "citations": [{"id": "2abae43b4a7fd85473bd6c906a0fcfc403968e87", "title": "Generating Natural Video Descriptions via Multimodal Processing", "addresses": [{"name": "Carnegie Mellon University Silicon Valley", "source_name": "CARNEGIE MELLON UNIVERSITY", "street_adddress": "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/92d3/f3ec8beec1d038727044fbbf4f70406116e1.pdf"]}, {"id": "322a7dad274f440a92548faa8f2b2be666b2d01f", "title": "Pyramid Scene 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"}, {"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/1612.01105.pdf"]}, {"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": []}, {"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"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1701.02870.pdf"]}, {"id": "874082164d9ab9fced08b9890c009b91a2e846f1", "title": "Understanding Convolution for Semantic Segmentation", "addresses": [{"name": "TuSimple", "source_name": "TuSimple", "street_adddress": "9191 Towne Centre Dr STE 600, San Diego, CA 92122, USA", "lat": "32.87344550", "lng": "-117.20656360", "type": "edu", "country": ""}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1702.08502.pdf"]}, {"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": []}, {"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": []}, {"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"]}, {"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"]}, {"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"]}, {"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"]}, {"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"]}, {"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"]}, {"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"]}, {"id": "0bd949f948f8f7afc0578d23d065b36c5c03c509", "title": "Regional Gating Neural Networks for Multi-label Image Classification", "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"}, {"name": "Shanghai, China", "source_name": "Shanghai, China", "street_adddress": "Shanghai, China", "lat": "31.23039040", "lng": "121.47370210", "type": "edu", "country": ""}, {"name": "Beijing, China", "source_name": "Beijing, China", "street_adddress": "Beijing, China", "lat": "39.90419990", "lng": "116.40739630", "type": "edu", "country": "China"}, {"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": "2016", "pdf": ["https://pdfs.semanticscholar.org/0bd9/49f948f8f7afc0578d23d065b36c5c03c509.pdf"]}, {"id": "4f0b8f730273e9f11b2bfad2415485414b96299f", "title": "BDD100K: A Diverse Driving Video Database with Scalable Annotation Tooling", "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": "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"]}, {"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"]}, {"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"]}, {"id": "faccce1a55c0c0ac767b74782c862a3eed0d1065", "title": "SIGNet: Semantic Instance Aided Unsupervised 3D Geometry Perception", "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": "2018", "pdf": ["https://arxiv.org/pdf/1812.05642.pdf"]}, {"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"]}, {"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": []}, {"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"]}, {"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"]}, {"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": ["https://arxiv.org/pdf/1611.01484.pdf"]}, {"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"]}, {"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"]}, {"id": "2d79d338c114ece1d97cde1aa06ab4cf17d38254", "title": "iLab-20M: A Large-Scale Controlled Object Dataset to Investigate Deep Learning", "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"}, {"name": "Amirkabir University of Technology", "source_name": "Amirkabir University of Technology", "street_adddress": "\u062f\u0627\u0646\u0634\u06af\u0627\u0647 \u0635\u0646\u0639\u062a\u06cc \u0627\u0645\u06cc\u0631\u06a9\u0628\u06cc\u0631, \u0648\u0644\u06cc \u0639\u0635\u0631, \u0645\u06cc\u062f\u0627\u0646 \u0648\u0644\u06cc\u0639\u0635\u0631, \u0645\u0646\u0637\u0642\u0647 \u06f6 \u0634\u0647\u0631 \u062a\u0647\u0631\u0627\u0646, \u062a\u0647\u0631\u0627\u0646, \u0628\u062e\u0634 \u0645\u0631\u06a9\u0632\u06cc \u0634\u0647\u0631\u0633\u062a\u0627\u0646 \u062a\u0647\u0631\u0627\u0646, \u0634\u0647\u0631\u0633\u062a\u0627\u0646 \u062a\u0647\u0631\u0627\u0646, \u0627\u0633\u062a\u0627\u0646 \u062a\u0647\u0631\u0627\u0646, \u0646\u0628\u0634 \u0628\u0631\u0627\u062f\u0631\u0627\u0646 \u0645\u0638\u0641\u0631, \u200f\u0627\u06cc\u0631\u0627\u0646\u200e", "lat": "35.70451400", "lng": "51.40972058", "type": "edu", "country": "Iran"}], "year": "2016", "pdf": ["http://crcv-web.eecs.ucf.edu/papers/cvpr2016/Borji_CVPR2016.pdf", "http://crcv.ucf.edu/papers/cvpr2016/Borji_CVPR2016.pdf", "http://ilab.usc.edu/publications/doc/Borji_etal16cvpr.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Borji_iLab-20M_A_Large-Scale_CVPR_2016_paper.pdf"]}, {"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"]}, {"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"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1709.07914.pdf"]}, {"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"]}, {"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": []}, {"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"]}, {"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"]}, {"id": "630120d6cb9744f00d572d55701f90aff1951710", "title": "Analysing object detectors from the perspective of co-occurring object categories", "addresses": [{"name": "Budapest, Hungary", "source_name": "Budapest, Hungary", "street_adddress": "Budapest, Hungary", "lat": "47.49791200", "lng": "19.04023500", "type": "edu", "country": ""}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.08132.pdf"]}, {"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": ""}, {"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"]}, {"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": ""}, {"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"]}, {"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": []}, {"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"]}, {"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": []}, {"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"]}, {"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"]}, {"id": "9405a9180139f23f4dd9d90aa4e86944b35b8c88", "title": "Weakly-Supervised Visual Grounding of Phrases with Linguistic Structures", "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"}, {"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://arxiv.org/pdf/1705.01371.pdf"]}, {"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"]}, {"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"]}, {"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": []}, {"id": "24bb79815967f5d1a333d32d25830542646babce", "title": "Cross-media Multi-level Alignment with Relation 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": ["https://arxiv.org/pdf/1804.09539.pdf"]}, {"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": []}, {"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"]}, {"id": "3e4d8bd8cb917db9bad1ed4382ccb266ab5fa411", "title": "Toward Efficient Simultaneous Detection and Segmentation", "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": []}, {"id": "eb7e0dfc61f3f9993a39316ccaaa263059b3a108", "title": "Spatially Adaptive Computation Time for Residual Networks", "addresses": [{"name": "Carnegie Mellon University Silicon Valley", "source_name": "CARNEGIE MELLON UNIVERSITY", "street_adddress": "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "lat": "37.41021930", "lng": "-122.05965487", "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"]}, {"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": []}, {"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"]}, {"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": []}, {"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"]}, {"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"]}, {"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"]}, {"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": []}, {"id": "ba5fcc1a691ecb0e7bc917eb1c00b5fd01701fab", "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"]}, {"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"}, {"name": "Singapore", "source_name": "Singapore", "street_adddress": "Singapore", "lat": "1.35208300", "lng": "103.81983600", "type": "edu", "country": "Singapore"}], "year": "2018", "pdf": []}, {"id": "0678a8abea82793993cd89383319da75f6dc4be3", "title": "ProNet: Learning to Propose Object-Specific Boxes for Cascaded Neural 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/1511.03776.pdf"]}, {"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"]}, {"id": "0489a21c77d1646ea3af48d678c3ad9645eef2a9", "title": "Large-Scale Sparse Learning From Noisy Tags for Semantic Segmentation", "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": "2016", "pdf": []}, {"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": []}, {"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": "Nankai University", "street_adddress": "94 Weijin Rd, Nankai Qu, China, 300071", "lat": "39.10394430", "lng": "117.17422320", "type": "edu", "country": ""}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1612.06530.pdf"]}, {"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": []}, {"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": []}, {"id": "f4af49a1ead3c81cc5d023878cb67c5646dd8a04", "title": "Learning a Recurrent Visual Representation for Image Caption Generation", "addresses": [{"name": "Carnegie Mellon University Silicon Valley", "source_name": "CARNEGIE MELLON UNIVERSITY", "street_adddress": "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "lat": "37.41021930", "lng": "-122.05965487", "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"]}, {"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": []}, {"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"]}, {"id": "1837decb49fb6fc68a6085e797faefb591fecb8a", "title": "Learning Transferrable Knowledge for Semantic Segmentation with Deep Convolutional Neural Network", "addresses": [{"name": "POSTECH, Pohang, Korea", "source_name": "POSTECH, Pohang, Korea", "street_adddress": "77 Cheongam-ro, Hyogok-dong, Nam-gu, Pohang, Gyeongsangbuk-do, South Korea", "lat": "36.01388570", "lng": "129.32318360", "type": "edu", "country": ""}, {"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": "2016", "pdf": ["https://arxiv.org/pdf/1512.07928.pdf"]}, {"id": "3b8a3b4ed02a15b2ba329727596b704889123a39", "title": "Deep affordance learning for single- and multiple-instance object detection", "addresses": [{"name": "Singapore", "source_name": "Singapore", "street_adddress": "Singapore", "lat": "1.35208300", "lng": "103.81983600", "type": "edu", "country": "Singapore"}], "year": "2017", "pdf": ["https://oar.a-star.edu.sg/jspui/bitstream/123456789/2242/1/1570379510(2).pdf"]}, {"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"]}, {"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"]}, {"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": []}, {"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"]}, {"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"]}, {"id": "48048f2fe3705d7d645450f31696045bf3c8312e", "title": "BubbleView: an alternative to eye-tracking for crowdsourcing image importance", "addresses": [{"name": "MIT CSAIL", "source_name": "MIT CSAIL", "street_adddress": "32 Vassar St, Cambridge, MA 02139, USA", "lat": "42.36194070", "lng": "-71.09043780", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/4804/8f2fe3705d7d645450f31696045bf3c8312e.pdf"]}, {"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"]}, {"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"]}, {"id": "2c761495cf3dd320e229586f80f868be12360d4e", "title": "Revisiting Unreasonable Effectiveness of Data in Deep Learning Era", "addresses": [{"name": "Carnegie Mellon University Silicon Valley", "source_name": "CARNEGIE MELLON UNIVERSITY", "street_adddress": "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.02968.pdf"]}, {"id": "ca0823ea938736ec3286a5fd3bbc0b3d830b4fb5", "title": "Semantic Amodal Segmentation", "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/1509.01329.pdf"]}, {"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"]}, {"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"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.08107.pdf"]}, {"id": "1c3f3866dec10f858193b4eb34dfc1cdcff0cb45", "title": "Employing Weak Annotations for Medical Image Analysis Problems", "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"}, {"name": "Nagoya University", "source_name": "Nagoya University", "street_adddress": "SuperDARN (Hokkaido West), \u592a\u8f9b\u7b2c1\u652f\u7dda\u6797\u9053, \u9678\u5225\u753a, \u8db3\u5bc4\u90e1, \u5341\u52dd\u7dcf\u5408\u632f\u8208\u5c40, \u5317\u6d77\u9053, \u5317\u6d77\u9053\u5730\u65b9, \u65e5\u672c", "lat": "43.53750985", "lng": "143.60768225", "type": "edu", "country": "Japan"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.06297.pdf"]}, {"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": []}, {"id": "3bb02eabd178aa5ab4ea4fe778b01356b70f51ab", "title": "Deep Priority Hashing", "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/1809.01238.pdf"]}, {"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"]}, {"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"]}, {"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": []}, {"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"]}, {"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"]}, {"id": "0d725e4fea8bbaf332d6a8d424ebecbd547a3851", "title": "Maximum Classifier Discrepancy for Unsupervised Domain Adaptation", "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/1712.02560.pdf"]}, {"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"]}, {"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": "Singapore", "source_name": "Singapore", "street_adddress": "Singapore", "lat": "1.35208300", "lng": "103.81983600", "type": "edu", "country": "Singapore"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.08652.pdf"]}, {"id": "85fbc94c8bc8e003006913c4df61ebd593b71192", "title": "Efficient Video Object Segmentation via Network Modulation", "addresses": [{"name": "Northwestern University", "source_name": "Northwestern University", "street_adddress": "Northwestern University, Northwestern Place, Downtown, Evanston, Cook County, Illinois, 60208, USA", "lat": "42.05511640", "lng": "-87.67581113", "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/1802.01218.pdf"]}, {"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"]}, {"id": "8f7e881d1f63c3a0367266eb65d8238453f01fdd", "title": "Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi-Supervised Semantic Segmentation", "addresses": [{"name": "IBM Thomas J. Watson Research Center", "source_name": "IBM Thomas J. Watson Research Center", "street_adddress": "IBM Yorktown research lab, Adams Road, Millwood, Town of New Castle, Westchester County, New York, 10562, USA", "lat": "41.21002475", "lng": "-73.80407056", "type": "company", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.04574.pdf"]}, {"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": []}, {"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"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.06049.pdf"]}, {"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": ""}], "year": "2018", "pdf": []}, {"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"]}, {"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": []}, {"id": "4558338873556d01fd290de6ddc55721c633a1ad", "title": "Training Constrained Deconvolutional Networks for Road Scene Semantic Segmentation", "addresses": [{"name": "Computer Vision Center, UAB, Barcelona, Spain", "source_name": "Computer Vision Center, UAB, Barcelona, Spain", "street_adddress": "Campus UAB, Edifici O, s/n, 08193 Cerdanyola del Vall\u00e8s, Barcelona, Spain", "lat": "41.50089570", "lng": "2.11155300", "type": "edu", "country": ""}, {"name": "Cambridge University", "source_name": "Cambridge University", "street_adddress": "University, Cambridge Road, Old Portsmouth, Portsmouth, South East, England, PO1 2HB, UK", "lat": "50.79440260", "lng": "-1.09717480", "type": "edu", "country": "United Kingdom"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1604.01545.pdf"]}, {"id": "685f65efc49479536e0df0974d18bed36a3190ea", "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"]}, {"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"]}, {"id": "ff637a63d1286705b357a7d4b2bc543158d2ee0b", "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": ["https://pdfs.semanticscholar.org/ff63/7a63d1286705b357a7d4b2bc543158d2ee0b.pdf"]}, {"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": ""}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.02654.pdf"]}, {"id": "cf2ab0e639c19877596036603a3000ce7a1deb35", "title": "Self-supervised Learning of Motion Capture", "addresses": [{"name": "Carnegie Mellon University Silicon Valley", "source_name": "CARNEGIE MELLON UNIVERSITY", "street_adddress": "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "lat": "37.41021930", "lng": "-122.05965487", "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"]}, {"id": "2231f44be9a8472a46d8e8a628b4e52b9a8f44e0", "title": "Visual Dialog", "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/1611.08669.pdf"]}, {"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"]}, {"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"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.02568.pdf"]}, {"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"]}, {"id": "72d7c465ef199a9670b3da7a318b0227f5cc3229", "title": "Visual Referring Expression Recognition: What Do Systems Actually Learn?", "addresses": [{"name": "Carnegie Mellon University Silicon Valley", "source_name": "CARNEGIE MELLON UNIVERSITY", "street_adddress": "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.11818.pdf"]}, {"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"]}, {"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"}, {"name": "University of California", "source_name": "University of California", "street_adddress": "Berkeley, CA, USA", "lat": "37.87189920", "lng": "-122.25853990", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1604.03517.pdf"]}, {"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"]}, {"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"]}, {"id": "d7221695df4de3f34d5e4a877b71c14bc88760d2", "title": "Proposal Incorporating Structural Bias into Neural Networks", "addresses": [{"name": "Carnegie Mellon University Silicon Valley", "source_name": "CARNEGIE MELLON UNIVERSITY", "street_adddress": "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/d722/1695df4de3f34d5e4a877b71c14bc88760d2.pdf"]}, {"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"]}, {"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": ""}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.00545.pdf"]}, {"id": "1695d0112d2e2c6df8bbe1d6abe18a457eba90dc", "title": "Classification of Crash and Near-Crash Events from Dashcam Videos and Telematics", "addresses": [{"name": "Verizon Connect Research, via Paisiello 16-20, Florence, 50144, 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": []}, {"id": "074ac448d68f0bbb5a39d45bd82190972e9fba52", "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"]}, {"id": "5de5848dc3fc35e40420ffec70a407e4770e3a8d", "title": "WebVision Database: Visual Learning and Understanding from Web Data", "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": "2017", "pdf": ["https://arxiv.org/pdf/1708.02862.pdf"]}, {"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"}, {"name": "Shanghai, China", "source_name": "Shanghai, China", "street_adddress": "Shanghai, China", "lat": "31.23039040", "lng": "121.47370210", "type": "edu", "country": ""}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.00977.pdf"]}, {"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"]}, {"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"]}, {"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"]}, {"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"]}, {"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"]}, {"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"]}, {"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": []}, {"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"]}, {"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"]}, {"id": "857fb344977e5181bf5a99593ceba09a158d412c", "title": "VCI 2 R at the NTCIR-13 Lifelog-2 Lifelog Semantic Access Task", "addresses": [{"name": "Singapore", "source_name": "Singapore", "street_adddress": "Singapore", "lat": "1.35208300", "lng": "103.81983600", "type": "edu", "country": "Singapore"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/857f/b344977e5181bf5a99593ceba09a158d412c.pdf"]}, {"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"]}, {"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"]}, {"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"]}, {"id": "cf80b4f78e639504cbf056f29bc1efecf31b1bb2", "title": "Joint Flow: Temporal Flow Fields for Multi Person 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://arxiv.org/pdf/1805.04596.pdf"]}, {"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"]}, {"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"]}, {"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"]}, {"id": "284af686292a6119129b410413831f8d2363fcc6", "title": "Learning Representation for Scene Understanding: Epitomes, CRFs, and CNNs", "addresses": [{"name": "University of California", "source_name": "University of California", "street_adddress": "Berkeley, CA, USA", "lat": "37.87189920", "lng": "-122.25853990", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/284a/f686292a6119129b410413831f8d2363fcc6.pdf"]}, {"id": "2fe2cfd98e232f1396f01881853ed6b3d5e37d65", "title": "Taskonomy: Disentangling Task Transfer Learning", "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": "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/1804.08328.pdf"]}, {"id": "c4fe488c0cff49e1ed6de1425ede27900005fd87", "title": "Multi-scale Location-Aware Kernel Representation for Object Detection", "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"}, {"name": "Dalian University of Technology", "source_name": "Dalian University of Technology", "street_adddress": "\u5927\u8fde\u7406\u5de5\u5927\u5b66, \u7ea2\u51cc\u8def, \u7518\u4e95\u5b50\u533a, \u51cc\u6c34\u9547, \u7518\u4e95\u5b50\u533a / Ganjingzi, \u5927\u8fde\u5e02 / Dalian, \u8fbd\u5b81\u7701, 116023, \u4e2d\u56fd", "lat": "38.88140235", "lng": "121.52281098", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.00428.pdf"]}, {"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"]}, {"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"]}, {"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"]}, {"id": "1bfc74bad04b407d1792a70d73a3f5dc0be0506d", "title": "Cross-Dataset Adaptation for Visual Question Answering", "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://arxiv.org/pdf/1806.03726.pdf"]}, {"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"]}, {"id": "c96c0b6af744ce5f469db47968e331926ff47e3b", "title": "Priming Neural Networks", "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"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.05918.pdf"]}, {"id": "49ad27dd5bd9ca682e86bcaf3abf1cda2cd9de54", "title": "Neural Baby Talk", "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": ["https://arxiv.org/pdf/1803.09845.pdf"]}, {"id": "e73696016b43314a7bef6015dacbe702af472d96", "title": "End-to-End Recovery of Human Shape and Pose", "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": "2018", "pdf": ["https://arxiv.org/pdf/1712.06584.pdf"]}, {"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"]}, {"id": "ed173a39f4cd980eef319116b6ba39cec1b37c42", "title": "Associative Embedding: End-to-End Learning for Joint Detection and Grouping", "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": "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://arxiv.org/pdf/1611.05424.pdf"]}, {"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"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1701.01077.pdf"]}, {"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"]}, {"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": []}, {"id": "ae3d92c64806e54d1a4b98792894b7693d12e3d8", "title": "Personalized Serious Games for Cognitive Intervention with Lifelog Visual Analytics", "addresses": [{"name": "Institute for Infocomm Research, A*STAR, Singapore, Singapore", "source_name": "Institute for Infocomm Research, A*STAR, Singapore, Singapore", "street_adddress": "1 Fusionopolis Way, #21-01 Connexis, Singapore 138632", "lat": "1.29889260", "lng": "103.78731070", "type": "edu", "country": "Singapore"}, {"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": "Singapore Bioimaging Consortium, A*STAR, Singapore, Singapore", "source_name": "Singapore Bioimaging Consortium, A*STAR, Singapore, Singapore", "street_adddress": "11 Biopolis Way, Singapore 138667", "lat": "1.30452010", "lng": "103.79165150", "type": "edu", "country": "Singapore"}], "year": "2018", "pdf": []}, {"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": []}, {"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"]}, {"id": "4946ba10a4d5a7d0a38372f23e6622bd347ae273", "title": "Describing Common Human Visual Actions in Images", "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": "2015", "pdf": ["https://arxiv.org/pdf/1506.02203.pdf"]}, {"id": "88b9b003c488f1fd76c82ca9311a24c070fef2c8", "title": "Person Retrieval in Surveillance Video using Height, Color and Gender", "addresses": [{"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": ["https://arxiv.org/pdf/1810.05080.pdf"]}, {"id": "2e7d5e653256bb30c3e591cc65acb126a10c97c4", "title": "A Robot Localization Framework Using CNNs for Object Detection and Pose Estimation", "addresses": [{"name": "Otto von Guericke University", "source_name": "Otto von Guericke University", "street_adddress": "Otto-von-Guericke-Universit\u00e4t Magdeburg, 2, Universit\u00e4tsplatz, Kr\u00f6kentorviertel/Breiter Weg NA, Alte Neustadt, Magdeburg, Sachsen-Anhalt, 39106, Deutschland", "lat": "52.14005065", "lng": "11.64471248", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.01665.pdf"]}, {"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"]}, {"id": "1b0ef7ccad215c682a784d1aec4988b675d779b9", "title": "Image Captioning With Visual-Semantic Double 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": []}, {"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"]}, {"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"]}, {"id": "0e36ada8cb9c91f07c9dcaf196d036564e117536", "title": "Much Ado About Time: Exhaustive Annotation of Temporal Data", "addresses": [{"name": "Carnegie Mellon University Silicon Valley", "source_name": "CARNEGIE MELLON UNIVERSITY", "street_adddress": "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1607.07429.pdf"]}, {"id": "c733e4a14b51623120da9b4571b4409bc99ab0cd", "title": "Mainstream: Dynamic Stem-Sharing for Multi-Tenant Video Processing", "addresses": [{"name": "Carnegie Mellon University Silicon Valley", "source_name": "CARNEGIE MELLON UNIVERSITY", "street_adddress": "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/2d64/9992d78efd47b22c9a4dcb52386a951b54ea.pdf"]}, {"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": []}, {"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": "Columbus, OH 43210, USA", "lat": "40.01419050", "lng": "-83.03091430", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.06208.pdf"]}, {"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": []}, {"id": "acd26d5b85e979d73101ac790bfdedf17bfe8ed1", "title": "Learning from PhotoShop Operation Videos : the PSOV Dataset", "addresses": [{"name": "University of California", "source_name": "University of California", "street_adddress": "Berkeley, CA, USA", "lat": "37.87189920", "lng": "-122.25853990", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/acd2/6d5b85e979d73101ac790bfdedf17bfe8ed1.pdf"]}, {"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": []}, {"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"]}, {"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": []}, {"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"]}, {"id": "bcc603abdb9bc7dbd79803d14e5ad63ccb26051b", "title": "A Data Driven Approach for Compound Figure Separation Using Convolutional Neural Networks", "addresses": [{"name": "Indiana University", "source_name": "Indiana University", "street_adddress": "Indiana University East, West Cart Road, Richmond, Wayne County, Indiana, 47374, USA", "lat": "39.86948105", "lng": "-84.87956905", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.05105.pdf"]}, {"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"]}, {"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"]}, {"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"]}, {"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"]}, {"id": "d2b2cb1d5cc1aa30cf5be7bcb0494198934caabb", "title": "A Restricted Visual Turing Test for Deep Scene and Event Understanding", "addresses": [{"name": "University of California, Los Angeles", "source_name": "University of California, Los Angeles", "street_adddress": "200 UCLA, Medical Plaza Driveway Suite 540, Los Angeles, CA 90095, USA", "lat": "34.06877880", "lng": "-118.44500940", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1512.01715.pdf"]}, {"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"]}, {"id": "3233e80170115db43d0fe6663c84a9bda03f2d6b", "title": "Similarity Reasoning over Semantic Context\u2013graphs", "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": "2015", "pdf": ["https://pdfs.semanticscholar.org/3233/e80170115db43d0fe6663c84a9bda03f2d6b.pdf"]}, {"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"]}, {"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"]}, {"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"]}, {"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": []}, {"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"]}, {"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"]}, {"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"]}, {"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"]}, {"id": "f8599ad5332cdf2c9919988ba300bb4b438b5834", "title": "Transitive Invariance for Self-Supervised Visual Representation Learning", "addresses": [{"name": "Carnegie Mellon University Silicon Valley", "source_name": "CARNEGIE MELLON UNIVERSITY", "street_adddress": "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.02901.pdf"]}, {"id": "397085122a5cade71ef6c19f657c609f0a4f7473", "title": "Using Segmentation to Predict the Absence of Occluded Parts", "addresses": [{"name": "University of California", "source_name": "University of California", "street_adddress": "Berkeley, CA, USA", "lat": "37.87189920", "lng": "-122.25853990", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/db11/4901d09a07ab66bffa6986bc81303e133ae1.pdf"]}, {"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"]}, {"id": "404ac62d19a2677ad0266041882244d943e7033e", "title": "Application of a Hybrid Model Based on a Convolutional Auto-Encoder and Convolutional Neural Network in Object-Oriented Remote Sensing Classification", "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://pdfs.semanticscholar.org/404a/c62d19a2677ad0266041882244d943e7033e.pdf"]}, {"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 Silicon Valley", "source_name": "CARNEGIE MELLON UNIVERSITY", "street_adddress": "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "lat": "37.41021930", "lng": "-122.05965487", "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"]}, {"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": []}, {"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": []}, {"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 Silicon Valley", "source_name": "CARNEGIE MELLON UNIVERSITY", "street_adddress": "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu", "country": "United States"}], "year": "2017", "pdf": []}, {"id": "2fa1f1fc566a0b770b1f39ed5ca1e602a28a5636", "title": "Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks", "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": "2016", "pdf": ["https://arxiv.org/pdf/1512.04143.pdf"]}, {"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": []}, {"id": "85e283564fca1d1cf4d142647561901a26f144c6", "title": "On the Origin of Deep Learning On the Origin of Deep Learning", "addresses": [{"name": "Carnegie Mellon University Silicon Valley", "source_name": "CARNEGIE MELLON UNIVERSITY", "street_adddress": "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/85e2/83564fca1d1cf4d142647561901a26f144c6.pdf"]}, {"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": []}, {"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"]}, {"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": []}, {"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"]}, {"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"]}, {"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": []}, {"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"]}, {"id": "2be8e06bc3a4662d0e4f5bcfea45631b8beca4d0", "title": "Watch and learn: Semi-supervised learning of object detectors from videos", "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": "2015", "pdf": ["https://arxiv.org/pdf/1505.05769.pdf"]}, {"id": "943c372336ced4b28e15e02fe8db1f4b23bf6835", "title": "Advanced Deep-Learning Techniques for Salient and Category-Specific Object Detection: A Survey", "addresses": [{"name": "Carnegie Mellon University Silicon Valley", "source_name": "CARNEGIE MELLON UNIVERSITY", "street_adddress": "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "lat": "37.41021930", "lng": "-122.05965487", "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": []}, {"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 Thomas J. Watson Research Center", "source_name": "IBM Thomas J. Watson Research Center", "street_adddress": "IBM Yorktown research lab, Adams Road, Millwood, Town of New Castle, Westchester County, New York, 10562, USA", "lat": "41.21002475", "lng": "-73.80407056", "type": "company", "country": "United States"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/5fed/ae3bccf86052ed725e5925bb4ef47f9389c1.pdf"]}, {"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": []}, {"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": []}, {"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"]}, {"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"]}, {"id": "b9566216ec1e5dcd02e3a222987f1934e44c773e", "title": "Neuron-level Selective Context Aggregation for Scene Segmentation", "addresses": [{"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"]}, {"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": []}, {"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": ""}], "year": "2018", "pdf": []}, {"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": ""}, {"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"]}, {"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 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/1812.03407.pdf"]}, {"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"]}, {"id": "ee7c4f765e3743b324ee2d74f056a01f7e54320d", "title": "Weakly Supervised Salient Object Detection Using Image Labels", "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/1803.06503.pdf"]}, {"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"]}, {"id": "af55a25cdd3a2c138e755d5206b35457c1f5760b", "title": "DistInit: Learning Video Representations without a Single Labeled Video", "addresses": [{"name": "Carnegie Mellon University Silicon Valley", "source_name": "CARNEGIE MELLON UNIVERSITY", "street_adddress": "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu", "country": "United States"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.09244.pdf"]}, {"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"]}, {"id": "08ff22f76a567fcbc1afec6bfbf957a560cfadc7", "title": "Exploring Person Context and Local Scene Context for Object Detection.", "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://arxiv.org/pdf/1511.08177.pdf"]}, {"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"]}, {"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"]}, {"id": "2d00f7b9591718134b9cb095ced36b7c9babc439", "title": "Contextual Memory Trees", "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"}, {"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/1807.06473.pdf"]}, {"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"]}, {"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"]}, {"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"]}, {"id": "e6d8ebfd88ee333deccce32b09ee41d271af6dc4", "title": "Grasp2Vec: Learning Object Representations from Self-Supervised Grasping", "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": "2018", "pdf": ["https://arxiv.org/pdf/1811.06964.pdf"]}, {"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"]}, {"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"]}, {"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"]}, {"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": []}, {"id": "efcaeb699b4e841453f1948140430421c2422a85", "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"]}, {"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"]}, {"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"]}, {"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"]}, {"id": "68a513b1ac290a69f95869600c751dca25e9495b", "title": "Explicit Bias Discovery in Visual Question Answering Models", "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/1811.07789.pdf"]}, {"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"]}, {"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"]}, {"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"]}, {"id": "2675a66b3f8743cf0551f284244af4f24537c19b", "title": "Learning Visually Grounded Sentence Representations", "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": "2018", "pdf": ["https://arxiv.org/pdf/1707.06320.pdf"]}, {"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"]}, {"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"]}, {"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"]}, {"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"]}, {"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"]}, {"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"]}, {"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"]}, {"id": "05fa794c2d13190bef03bf33fb9ebbb612f514c0", "title": "POL-LWIR Vehicle Detection: Convolutional Neural Networks Meet Polarised Infrared Sensors", "addresses": [{"name": "Heriot-Watt University", "source_name": "Heriot-Watt University", "street_adddress": "Heriot-Watt University - Edinburgh Campus, Third Gait, Currie, Gogarbank, City of Edinburgh, Scotland, EH14 4AS, UK", "lat": "55.91029135", "lng": "-3.32345777", "type": "edu", "country": "United Kingdom"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.02576.pdf"]}, {"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"]}, {"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"]}, {"id": "d408e80d0c5db9fa856a02d42657959a530174fd", "title": "Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation", "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": "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": "Princeton University", "source_name": "Princeton University", "street_adddress": "Lot 9, University Place, Princeton Township, Mercer County, New Jersey, 08540, USA", "lat": "40.34829285", "lng": "-74.66308325", "type": "edu", "country": "United States"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.02970.pdf"]}, {"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"]}, {"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"]}, {"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"]}, {"id": "fed58c1faf9af15e1215e47a432f84b840f42857", "title": "Input Reconstruction Side and top down view Part Segmentation Input Reconstruction Side and top down view Part 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": "2017", "pdf": ["https://pdfs.semanticscholar.org/fed5/8c1faf9af15e1215e47a432f84b840f42857.pdf"]}, {"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"]}, {"id": "c33a00a5dd8064fe0084a90a4670b36c5c36569b", "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://pdfs.semanticscholar.org/c33a/00a5dd8064fe0084a90a4670b36c5c36569b.pdf"]}, {"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"]}, {"id": "3af16b0c1265cc9c8969f9c16ce65185297a2bfc", "title": "Regularizing Deep Networks by Modeling and Predicting Label Structure", "addresses": [{"name": "Toyota Technological Institute at Chicago", "source_name": "Toyota Technological Institute at Chicago", "street_adddress": "6045 S Kenwood Ave, Chicago, IL 60637, USA", "lat": "41.78469820", "lng": "-87.59258480", "type": "company", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.02009.pdf"]}, {"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"]}, {"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"]}, {"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": []}, {"id": "b5ebfb763053d3a66e6a4f36ed443dc4ab5ac877", "title": "Unsupervised Learning of Important Objects from First-Person Videos", "addresses": [{"name": "University of Pennsylvania", "source_name": "University of Pennsylvania", "street_adddress": "Penn Museum, 3260, South Street, University City, Philadelphia, Philadelphia County, Pennsylvania, 19104, USA", "lat": "39.94923440", "lng": "-75.19198985", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1611.05335.pdf"]}, {"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"]}, {"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"]}, {"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": []}, {"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": []}, {"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"]}, {"id": "fb28c33b29763a53abe99cb7ee6c1a86bc32a27c", "title": "Learning to Interpret Satellite Images Using Wikipedia", "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/1809.10236.pdf"]}, {"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"]}, {"id": "cbc3ebf2809edcaa04e252d25f4373c924f4136b", "title": "CNN+CNN: Convolutional Decoders for Image Captioning", "addresses": [{"name": "City University of Hong Kong", "source_name": "City University of Hong Kong", "street_adddress": "\u9999\u6e2f\u57ce\u5e02\u5927\u5b78 City University of Hong Kong, \u9054\u5eb7\u8def Tat Hong Avenue, \u5927\u7aa9\u576a Tai Wo Ping, \u6df1\u6c34\u57d7\u5340 Sham Shui Po District, \u4e5d\u9f8d Kowloon, HK, KIL 3348, \u4e2d\u56fd", "lat": "22.34000115", "lng": "114.16970291", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.09019.pdf"]}, {"id": "f4865cd9d6a2b26cf6656a399ca7c3cc1668d556", "title": "Neurons Merging Layer: Towards Progressive Redundancy Reduction for Deep Supervised Hashing", "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/1809.02302.pdf"]}, {"id": "7bfa04eb7ba2830a682a15206370abec49cffd2a", "title": "Learning Semantic Segmentation from Synthetic Data: A Geometrically Guided Input-Output Adaptation Approach", "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/1812.05040.pdf"]}, {"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"]}, {"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"]}, {"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"]}, {"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"]}, {"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"]}, {"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": []}, {"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"]}, {"id": "9528e2e8c20517ab916f803c0371abb4f0ed488b", "title": "Shallow and Deep Convolutional Networks for Saliency Prediction", "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"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1603.00845.pdf"]}, {"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"]}, {"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"]}, {"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"]}, {"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"]}, {"id": "ce142b327974580b297fb84c2c1c799f838bdda5", "title": "VADRA: Visual Adversarial Domain Randomization and Augmentation", "addresses": [{"name": "Carnegie Mellon University Silicon Valley", "source_name": "CARNEGIE MELLON UNIVERSITY", "street_adddress": "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.00491.pdf"]}, {"id": "b7d2ed1fb47fcef9aa3822e6e90e248b64bf9d21", "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 America", "source_name": "NEC Labs America", "street_adddress": "4 Independence Way #200, Princeton, NJ 08540, USA", "lat": "40.35981820", "lng": "-74.59502250", "type": "company", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.04340.pdf"]}, {"id": "fbaceba60619d9f76f7acf6e639669cd6150049e", "title": "Automatic Semantic Content Removal by Learning to Neglect.", "addresses": [{"name": "University of California", "source_name": "University of California", "street_adddress": "Berkeley, CA, USA", "lat": "37.87189920", "lng": "-122.25853990", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.07696.pdf"]}, {"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": []}, {"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"]}, {"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": []}, {"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"]}, {"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": "University of California, Los Angeles", "source_name": "University of California, Los Angeles", "street_adddress": "200 UCLA, Medical Plaza Driveway Suite 540, Los Angeles, CA 90095, USA", "lat": "34.06877880", "lng": "-118.44500940", "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"]}, {"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"]}, {"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": []}, {"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"]}, {"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"]}, {"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"]}, {"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"]}, {"id": "8b6493a65285fb72252221e7ef8ad1091bd96b32", "title": "TRAFFIC ANALYSIS USING VISUAL OBJECT DETECTION AND TRACKING", "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": "2017", "pdf": ["https://pdfs.semanticscholar.org/8b64/93a65285fb72252221e7ef8ad1091bd96b32.pdf"]}, {"id": "7acd36ba0b59849d49bfc01cef11d18d2bcad76f", "title": "Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells.", "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/1810.10804.pdf"]}, {"id": "dec04588b73efb1192d1778b2b818842ccd242e7", "title": "Image captioning based on deep reinforcement learning", "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": "Beijing, China", "source_name": "Beijing, China", "street_adddress": "Beijing, China", "lat": "39.90419990", "lng": "116.40739630", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.04835.pdf"]}, {"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"]}, {"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"]}, {"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"]}, {"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"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/5576/1bdf5cbbff5fbede8ee9d0573d1561a9254b.pdf"]}, {"id": "0d75052f1d7350fa035a35566555ce7b65d1cd2f", "title": "Oracle Performance for Visual 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": "2016", "pdf": ["https://arxiv.org/pdf/1511.04590.pdf"]}, {"id": "2c3e7392b865b228f5d56ab025cd3123554be5e1", "title": "Linguistic Unit Discovery from Multi-Modal Inputs in Unwritten Languages: Summary of the \u201cSpeaking Rosetta\u201d JSALT 2017 Workshop", "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/1802.05092.pdf"]}, {"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"]}, {"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"]}, {"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"]}, {"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"]}, {"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"]}, {"id": "e346aef68ae6df61b83fdeaa71ded9ba0282325e", "title": "Partially-Supervised Image Captioning", "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/1806.06004.pdf"]}, {"id": "1536579229a334640735725e0b886f8d03aca1e8", "title": "Rank of Experts: Detection Network Ensemble", "addresses": [{"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"]}, {"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"]}, {"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"]}, {"id": "031d4a3940011f6be69a7e24f1a04980482ee477", "title": "FastMask: Segment Multi-scale Object Candidates in One Shot", "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": "2017", "pdf": ["https://arxiv.org/pdf/1612.08843.pdf"]}, {"id": "7291d63fd9300ee40883201c9d2c4698787d0eaf", "title": "Beyond Pixels: A Comprehensive Survey from Bottom-up to Semantic Image Segmentation and Cosegmentation", "addresses": [{"name": "A*STAR, Singapore", "source_name": "Institute for Infocomm Research, 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": "2016", "pdf": ["https://arxiv.org/pdf/1502.00717.pdf"]}, {"id": "2a3e19d7c54cba3805115497c69069dd5a91da65", "title": "Looking at Hands in Autonomous Vehicles: A ConvNet Approach using Part Affinity Fields", "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": "2018", "pdf": ["https://arxiv.org/pdf/1804.01176.pdf"]}, {"id": "d99ec70dac11292c63b7726c58c24dfacddb2889", "title": "Learning visual attribute from image and text \u2217", "addresses": [{"name": "Tohoku University", "source_name": "Tohoku University", "street_adddress": "Tohoku University, \u4e94\u6a4b\u901a, \u9752\u8449\u533a, \u4ed9\u53f0\u5e02, \u5bae\u57ce\u770c, \u6771\u5317\u5730\u65b9, 980-0811, \u65e5\u672c", "lat": "38.25309450", "lng": "140.87365930", "type": "edu", "country": "Japan"}], "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/d99e/c70dac11292c63b7726c58c24dfacddb2889.pdf"]}, {"id": "f8403bf4e3060487cbc8acceb1fb256a4f1cfc76", "title": "Adopting Abstract Images for Semantic Scene Understanding", "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://www.cc.gatech.edu/~parikh/Publications/ZitnickVedantamParikh_clipart_PAMI2015.pdf"]}, {"id": "927a032b758f9ae6ec8f035d794e820b50f4e83d", "title": "Indirect deep structured learning for 3D human body shape and pose prediction.", "addresses": [{"name": "University of Cambridge", "source_name": "University of Cambridge", "street_adddress": "Clifford Allbutt Lecture Theatre, Robinson Way, Romsey, Cambridge, Cambridgeshire, East of England, England, CB2 0QH, UK", "lat": "52.17638955", "lng": "0.14308882", "type": "edu", "country": "United Kingdom"}], "year": "2017", "pdf": ["http://mi.eng.cam.ac.uk/~cipolla/archive/Publications/inproceedings/2017-BMVC-3D-body-indirect.pdf", "http://mi.eng.cam.ac.uk/~ib255/files/Indirect-deep-structured-learning-BMVC2017.pdf", "https://www.dropbox.com/s/wrx7dzegq3wim04/0722.pdf?dl=1"]}, {"id": "f5eb411217f729ad7ae84bfd4aeb3dedb850206a", "title": "Tackling Low Resolution for Better Scene Understanding", "addresses": [{"name": "International Institute of Information Technology", "source_name": "International Institute of Information Technology", "street_adddress": "International Institute of Information Technology, Hyderabad, Campus Road, Ward 105 Gachibowli, Greater Hyderabad Municipal Corporation West Zone, Hyderabad, Rangareddy District, Telangana, 500032, India", "lat": "17.44549570", "lng": "78.34854698", "type": "edu", "country": "India"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/f5eb/411217f729ad7ae84bfd4aeb3dedb850206a.pdf"]}, {"id": "69c36275ddf2ea95ea4ac39b4d41079c13827281", "title": "Add English to image Chinese 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": "2017", "pdf": []}, {"id": "5087ab9091033f4f6b66cb24d347df6e6fc6f0ec", "title": "Deep Generative Models for Weakly-Supervised Multi-Label Classification", "addresses": [{"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"}, {"name": "Carnegie Mellon University Silicon Valley", "source_name": "CARNEGIE MELLON UNIVERSITY", "street_adddress": "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/5087/ab9091033f4f6b66cb24d347df6e6fc6f0ec.pdf"]}, {"id": "880760777e3671593ba50b7a17b0d30b655fc86d", "title": "Visual Question Answering : Datasets , Methods , Challenges and Oppurtunities", "addresses": [{"name": "Princeton University", "source_name": "Princeton University", "street_adddress": "Lot 9, University Place, Princeton Township, Mercer County, New Jersey, 08540, USA", "lat": "40.34829285", "lng": "-74.66308325", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/8807/60777e3671593ba50b7a17b0d30b655fc86d.pdf"]}, {"id": "a0d8f3429d442920f2ee37c151006a4d802f90dc", "title": "Learning 3D 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": ["http://www.cs.sfu.ca/~haoz/pubs/zeinab_sgp16_scene.pdf"]}, {"id": "58628e64e61bd2776a2a7258012eabe3c79ca90c", "title": "Active Grounding of Visual Situations", "addresses": [{"name": "Portland State University", "source_name": "Portland State University", "street_adddress": "Portland State University, Southwest Park Avenue, University District, Portland Downtown, Portland, Multnomah County, Oregon, 97201, USA", "lat": "45.51181205", "lng": "-122.68492999", "type": "edu", "country": "United States"}, {"name": "Santa Fe Institute", "source_name": "Santa Fe Institute", "street_adddress": "Santa Fe Institute, Hyde Park Road, Santa Fe, Santa Fe County, New Mexico, 87501, USA", "lat": "35.70028780", "lng": "-105.90864847", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/5862/8e64e61bd2776a2a7258012eabe3c79ca90c.pdf"]}, {"id": "dab8b00e5619ceec615b179265cd6d315a97911d", "title": "A two-stage training deep neural network for small pedestrian detection", "addresses": [{"name": "Teikyo University", "source_name": "Teikyo University", "street_adddress": "Japan, \u3012173-8605 Tokyo, \u677f\u6a4b\u533a\u52a0\u8cc0\uff12\u4e01\u76ee\uff11\uff11\u2212\uff11", "lat": "35.75927460", "lng": "139.71450290", "type": "edu", "country": "Japan"}], "year": "2017", "pdf": []}, {"id": "0ad1fefa54f69d9efa0112f2e60c19841d5e9346", "title": "ABC-CNN: An Attention Based Convolutional Neural Network for Visual Question Answering", "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": "2015", "pdf": ["https://arxiv.org/pdf/1511.05960.pdf"]}, {"id": "80335a84eadccbff0ac8e0c8ed7eec6de289d756", "title": "A New Deep Learning-Based Food Recognition System for Dietary Assessment on An Edge Computing Service Infrastructure", "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": "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": "2018", "pdf": ["https://csdl.computer.org/cms/Computer.org/transactions/feature/tsc_featured.pdf"]}, {"id": "60464c4bd94a14b63898e322f9ea651830e54ae0", "title": "Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers", "addresses": [{"name": "The Pennsylvania State University", "source_name": "The 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/1802.00124.pdf"]}, {"id": "43eee49e372e5299608a79f8491fcf40998028df", "title": "Complex event processing for content-based text, image, and video retrieval", "addresses": [{"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": "edu", "country": ""}, {"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": ""}, {"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": "edu", "country": ""}, {"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"]}, {"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"]}, {"id": "72282287f25c5419dc6fd9e89ec9d86d660dc0b5", "title": "A Rotation Invariant Latent Factor Model for Moveme Discovery from Static Poses", "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": "2016", "pdf": ["https://arxiv.org/pdf/1609.07495.pdf"]}, {"id": "67fdf4f9eccdf295baf1cbd8b33250d29a334daf", "title": "Bidirectional Long-Short Term Memory for Video Description", "addresses": [{"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": "2016", "pdf": ["https://arxiv.org/pdf/1606.04631.pdf"]}, {"id": "428818a9edfb547431be6d7ec165c6af576c83d5", "title": "Recurrent Topic-Transition GAN for Visual Paragraph Generation", "addresses": [{"name": "Carnegie Mellon University Silicon Valley", "source_name": "CARNEGIE MELLON UNIVERSITY", "street_adddress": "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "lat": "37.41021930", "lng": "-122.05965487", "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"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.07022.pdf"]}, {"id": "01c44701017b492592a53bd100096aaa55a6b8e4", "title": "Beyond Forward Shortcuts: Fully Convolutional Master-Slave Networks (MSNets) with Backward Skip Connections for Semantic Segmentation", "addresses": [{"name": "Singapore", "source_name": "Singapore", "street_adddress": "Singapore", "lat": "1.35208300", "lng": "103.81983600", "type": "edu", "country": "Singapore"}, {"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/1707.05537.pdf"]}, {"id": "8b2d224c8b69191c02dce750257c39d46b1c4a7b", "title": "A Reinforcement Learning Framework for Natural Question Generation using Bi-discriminators", "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://pdfs.semanticscholar.org/8b2d/224c8b69191c02dce750257c39d46b1c4a7b.pdf"]}, {"id": "9bac3639b2671dcdbdbbd36e8e9022d7334a3796", "title": "VSE++: Improving Visual-Semantic Embeddings with Hard Negatives", "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/1707.05612.pdf"]}, {"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"]}, {"id": "6e46d8aa63db3285417c8ebb65340b5045ca106f", "title": "Accelerating Machine Learning Inference with 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": "Princeton University &Microsoft", "source_name": "Princeton University &Microsoft, Princeton, NJ, USA", "street_adddress": "Princeton, NJ 08544, USA", "lat": "40.34398880", "lng": "-74.65144810", "type": "edu", "country": "United States"}], "year": "2018", "pdf": []}, {"id": "58ee208dce1f06724bb443b4cfe0aa30d6cc9d30", "title": "Actor-Critic Sequence Training for Image Captioning", "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"}, {"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/1706.09601.pdf"]}, {"id": "430cfa330b32633f6022ffdea0102bbd58a2fa49", "title": "Neural Image Captioning for Intelligent Vehicle-to-Passenger Communication", "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": "2017", "pdf": ["https://pdfs.semanticscholar.org/430c/fa330b32633f6022ffdea0102bbd58a2fa49.pdf"]}, {"id": "9507e5c59c45e68b964fdaf40e39569dcc754be3", "title": "Hybrid Supervised-unsupervised Image Topic Visualization with Convolutional Neural Network and LDA", "addresses": [{"name": "Indiana University", "source_name": "Indiana University", "street_adddress": "Indiana University East, West Cart Road, Richmond, Wayne County, Indiana, 47374, USA", "lat": "39.86948105", "lng": "-84.87956905", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/9507/e5c59c45e68b964fdaf40e39569dcc754be3.pdf"]}, {"id": "f3443545ea696872ccc62f0207ea25a6ea54f942", "title": "Image captioning in Turkish with subword units", "addresses": [{"name": "Bilgisayar M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc, Hacettepe \u00dcniversitesi, Ankara, T\u00fcrkiye", "source_name": "Bilgisayar M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc, Hacettepe \u00dcniversitesi, Ankara, T\u00fcrkiye", "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"}], "year": "2018", "pdf": []}, {"id": "e22336dc29306ccd938c9a2ae06e3919321dcb8d", "title": "Cross-linguistic differences and similarities in image descriptions", "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/1707.01736.pdf"]}, {"id": "4c81212a1ecca6b160631fea7f2a6cbff6f74012", "title": "Comixify: Transform video into a comics", "addresses": [{"name": "Warsaw University of Technology", "source_name": "Warsaw University of Technology", "street_adddress": "Politechnika Warszawska, 1, Plac Politechniki, VIII, \u015ar\u00f3dmie\u015bcie, Warszawa, mazowieckie, 00-661, RP", "lat": "52.22165395", "lng": "21.00735776", "type": "edu", "country": "Poland"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.03473.pdf"]}, {"id": "64dac451ccb1b998f4dff1d35ccdd3936ea49e33", "title": "Fine-grained Video Retrieval using Query Phrases \u2014 Waseda_Meisei TRECVID 2017 AVS System \u2014", "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": []}, {"id": "d6a799e64879290efb2a5c1b4f490737f0b1ab98", "title": "DSOD: Learning Deeply Supervised Object Detectors from Scratch", "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": "2017", "pdf": ["https://arxiv.org/pdf/1708.01241.pdf"]}, {"id": "226e0c7189b48c5beb40e18e55f81199ab7a7409", "title": "Exploiting Negative Evidence for Deep Latent Structured Models", "addresses": [{"name": "CEDRIC-Conservatoire National des Arts et M\u00e9tiers, Paris, France", "source_name": "CEDRIC-Conservatoire National des Arts et M\u00e9tiers, Paris, France", "street_adddress": "32 Rue du Faubourg Saint-Martin, 75010 Paris, France", "lat": "48.87008750", "lng": "2.35638710", "type": "edu", "country": "France"}], "year": "2018", "pdf": ["http://cedric.cnam.fr/~thomen/papers/Durand_PAMI_2018.pdf", "http://webia.lip6.fr/~durandt/pdfs/2018_TPAMI/Durand_ResNetWELDON_TPAMI_2018_supp.pdf"]}, {"id": "284fd4ebf1e875e3d456bbb82aadb0f543c13964", "title": "Detecting Animals in Infrared Images from Camera-Traps", "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"}, {"name": "Research, MVTec Software GmbH, Munich, Germany", "source_name": "Research, MVTec Software GmbH, Munich, Germany", "street_adddress": "Arnulfstra\u00dfe 205, 80634 M\u00fcnchen, Germany", "lat": "48.14952580", "lng": "11.52082560", "type": "edu", "country": "Germany"}], "year": "2018", "pdf": []}, {"id": "218e460a06b941a94cb4ead066b5d4b8a40f4704", "title": "PIRC Net : Using Proposal Indexing, Relationships and Context for Phrase Grounding", "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://arxiv.org/pdf/1812.03213.pdf"]}, {"id": "6e6538b709d111b9fb3437fe6ccea81577dde24d", "title": "Learning Unsupervised Visual Grounding Through Semantic Self-Supervision.", "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": "Carnegie Mellon University Silicon Valley", "source_name": "CARNEGIE MELLON UNIVERSITY", "street_adddress": "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.06506.pdf"]}, {"id": "edd28097745ade85c3acd1d8bcba0b17cccb682e", "title": "Title Multi-Object Classification and Unsupervised Scene Understanding Using Deep Learning Features and Latent Tree Probabilistic Models Permalink", "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": ""}, {"name": "University of California", "source_name": "University of California", "street_adddress": "Berkeley, CA, USA", "lat": "37.87189920", "lng": "-122.25853990", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/edd2/8097745ade85c3acd1d8bcba0b17cccb682e.pdf"]}, {"id": "35502af359aa60ae8047df172e29503cfb29c3f9", "title": "Recurrent Pixel Embedding for Instance Grouping", "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": ""}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1712.08273.pdf"]}, {"id": "c033bafe915ddea9757f302557e0dc32110476de", "title": "Distorting Neural Representations to Generate Highly Transferable Adversarial Examples", "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/1811.09020.pdf"]}, {"id": "8588e784033bcbeddad88d45decfd3af2017ad3e", "title": "Neural Motifs: Scene Graph Parsing with Global Context", "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": "Carnegie Mellon University Silicon Valley", "source_name": "CARNEGIE MELLON UNIVERSITY", "street_adddress": "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.06640.pdf"]}, {"id": "f780e752a18b6a023b687a537351641f637a12c3", "title": "Artistic Image Generation from Sketch by Using Conditional Adversarial Network and Style Feature Transform", "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://pdfs.semanticscholar.org/f780/e752a18b6a023b687a537351641f637a12c3.pdf"]}, {"id": "15caf136368f918f62508f963a2eb0424f07df5f", "title": "C-WSL: Count-Guided Weakly Supervised Localization", "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/1711.05282.pdf"]}, {"id": "17c09a49b7837f22653c1e7a09ca3d10a2c9bf13", "title": "Non-local RoI for Cross-Object Perception", "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": "Academia Sinica, Taiwan", "source_name": "Academia Sinica, Taiwan", "street_adddress": "No. 128\u865f, Section 2, Academia Rd, Nangang District, Taipei City, Taiwan 11529", "lat": "25.04218520", "lng": "121.61454770", "type": "edu", "country": "Taiwan"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.10002.pdf"]}, {"id": "3e68a593bfa678a05cc16b2ad12fbd98be58a06e", "title": "Learning from Multiview Correlations in Open-Domain Videos", "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": ""}, {"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": "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": "2018", "pdf": ["https://arxiv.org/pdf/1811.08890.pdf"]}, {"id": "471635c61fffa75cd09121b14e4da155c667c5bf", "title": "Exploring the Design Space of Deep Convolutional Neural Networks at Large Scale", "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/1612.06519.pdf"]}, {"id": "f1b2212650d59d8c4ebcf25eec89987016c83678", "title": "BING++: A Fast High Quality Object Proposal Generator at 100fps", "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"}, {"name": "Nankai University", "source_name": "Nankai University", "street_adddress": "94 Weijin Rd, Nankai Qu, China, 300071", "lat": "39.10394430", "lng": "117.17422320", "type": "edu", "country": ""}], "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/f1b2/212650d59d8c4ebcf25eec89987016c83678.pdf"]}, {"id": "12e6d91f2deb937c0ab1dcdb4fcabc61ace40cc4", "title": "Actor-Action Semantic Segmentation with Region Masks", "addresses": [{"name": "Singapore", "source_name": "Singapore", "street_adddress": "Singapore", "lat": "1.35208300", "lng": "103.81983600", "type": "edu", "country": "Singapore"}, {"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/1807.08430.pdf"]}, {"id": "0d371fcd99e321257a1b7f87a436c6cc5b8b7557", "title": "Stability Based Filter Pruning for Accelerating Deep CNNs", "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": "2018", "pdf": ["https://arxiv.org/pdf/1811.08321.pdf"]}, {"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"]}, {"id": "f3a1246d3a0c7de004db9ef9f312bcedb5e22532", "title": "Self-Supervised Adversarial Hashing Networks for Cross-Modal Retrieval", "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"}, {"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/1804.01223.pdf"]}, {"id": "126848747d6af541c5934ec95997decf33c28ea7", "title": "Active Transfer Learning with Zero-Shot Priors: Reusing Past Datasets for Future Tasks", "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": "2015", "pdf": ["https://arxiv.org/pdf/1510.01544.pdf"]}, {"id": "a1eb455fa852fb3ee14eb0907a7db9081a42b3a7", "title": "Question Part Relevance and Editing for Cooperative and Context-Aware VQA (C2VQA)", "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": "Universit\u00e0 di Salerno, Dipartimento di Informatica, Fisciano, Italy", "source_name": "Universit\u00e0 di Salerno, Dipartimento di Informatica, 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": "2017", "pdf": []}, {"id": "b3b467961ba66264bb73ffe00b1830d7874ae8ce", "title": "Finding Tiny Faces", "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 Silicon Valley", "source_name": "CARNEGIE MELLON UNIVERSITY", "street_adddress": "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1612.04402.pdf"]}, {"id": "4f71709f08a451fceaaeaf6b3c814d137c8941e1", "title": "Multiview Cross-supervision for Semantic Segmentation", "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://arxiv.org/pdf/1812.01738.pdf"]}, {"id": "2e26e4e92f48732f074e4bafcbbdf1314191d325", "title": "Asymmetric Deep Supervised Hashing", "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": ["https://arxiv.org/pdf/1707.08325.pdf"]}, {"id": "10a36dea0167511b66deca65fdca978aa9afdb11", "title": "Simple Baseline for Visual Question Answering", "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://arxiv.org/pdf/1512.02167.pdf"]}, {"id": "844bfcee3bc559960ae7a2b1fd68fcf7a926dc5a", "title": "SPICE: Semantic Propositional Image Caption Evaluation", "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": "Macquarie University", "source_name": "Macquarie University, Sydney, Australia", "street_adddress": "Balaclava Rd, Macquarie Park NSW 2109, Australia", "lat": "-33.77382370", "lng": "151.11264980", "type": "edu", "country": "Australia"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1607.08822.pdf"]}, {"id": "243b82ad6f062c77cb1ad8e5fc56f5fa6f34fc15", "title": "Image Captioning with Text-Based Visual 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": "2018", "pdf": []}, {"id": "bc9c8831183b9b4e6cd78cefed7ec04d8096499f", "title": "CBAM: Convolutional Block Attention Module", "addresses": [{"name": "Korea Advanced Institute of Science and Technology", "source_name": "Korea Advanced Institute of Science and Technology", "street_adddress": "\uce74\uc774\uc2a4\ud2b8, 291, \ub300\ud559\ub85c, \uc628\ucc9c2\ub3d9, \uc628\ucc9c\ub3d9, \uc720\uc131\uad6c, \ub300\uc804, 34141, \ub300\ud55c\ubbfc\uad6d", "lat": "36.36971910", "lng": "127.36253700", "type": "edu", "country": "South Korea"}, {"name": "Adobe Research, San Jose, CA, USA", "source_name": "Adobe Research, San Jose, CA, USA", "street_adddress": "San Jose, CA, USA", "lat": "37.33820820", "lng": "-121.88632860", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.06521.pdf"]}, {"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"]}, {"id": "dca8ad055f33ddc2015e870b3ee331a6de524399", "title": "Semantic soft segmentation", "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"}, {"name": "MIT CSAIL", "source_name": "MIT CSAIL", "street_adddress": "32 Vassar St, Cambridge, MA 02139, USA", "lat": "42.36194070", "lng": "-71.09043780", "type": "edu", "country": "United States"}, {"name": "MIT CSAIL and ETH Z\u00fcrich, Switzerland", "source_name": "MIT CSAIL and ETH Z\u00fcrich, Switzerland", "street_adddress": "32 Vassar St, Cambridge, MA 02139, USA", "lat": "42.36194070", "lng": "-71.09043780", "type": "edu", "country": "United States"}], "year": "2018", "pdf": []}, {"id": "079e20d0d870a5bade46cc9b4338a3d637399654", "title": "Semantic Segmentation , Urban Navigation , and Research Directions", "addresses": [{"name": "Princeton University", "source_name": "Princeton University", "street_adddress": "Lot 9, University Place, Princeton Township, Mercer County, New Jersey, 08540, USA", "lat": "40.34829285", "lng": "-74.66308325", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/079e/20d0d870a5bade46cc9b4338a3d637399654.pdf"]}, {"id": "950de0d355f770b7f36511ee5dfde59602c21b0b", "title": "Implementation of human-robot VQA interaction system with dynamic memory networks", "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": []}, {"id": "61060bea27a3410260988540b627ccc5ba131822", "title": "Adversarial Cross-Modal Retrieval", "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"}, {"name": "University of Electronic Science and Technology of China", "source_name": "University of Electronic Science and Technology of China", "street_adddress": "Columbus, OH 43210, USA", "lat": "40.01419050", "lng": "-83.03091430", "type": "edu", "country": "United States"}], "year": "2017", "pdf": []}, {"id": "dbbfb8ab9355d00ec3b2a9be12747e2e20458bb5", "title": "Data Analysis Project : Using Knowledge Graphs for Image Classification", "addresses": [{"name": "Carnegie Mellon University Silicon Valley", "source_name": "CARNEGIE MELLON UNIVERSITY", "street_adddress": "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/dbbf/b8ab9355d00ec3b2a9be12747e2e20458bb5.pdf"]}, {"id": "0bdc753237de316929e69c83a7df208a80d4e3cd", "title": "Structure Inference Net: Object Detection Using Scene-Level Context and Instance-Level Relationships", "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/1807.00119.pdf"]}, {"id": "02b9a5af997595938ff11ee422b816d1e8dafc5b", "title": "Statistical Iterative CBCT Reconstruction Based on Neural Network", "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": []}, {"id": "8c6d1ad5ef6bccb921b8f26e8ac718721cb037a5", "title": "Fusion Scheme for Semantic and Instance-level Segmentation", "addresses": [{"name": "Technical University of Cluj-Napoca", "source_name": "Technical University of Cluj-Napoca", "street_adddress": "Strada Memorandumului 28, Cluj-Napoca 400114, Romania", "lat": "46.76929900", "lng": "23.58561300", "type": "edu", "country": "Romania"}], "year": "2018", "pdf": ["https://deepvision.data61.csiro.au/papers/11.pdf"]}, {"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"]}, {"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"]}, {"id": "a843bc90343ceeb25b59f6e54de3663e363f5fd3", "title": "Learning to predict where to look in interactive environments using deep recurrent q-learning", "addresses": [{"name": "National University of Ireland", "source_name": "National University of Ireland, Galway", "street_adddress": "University Rd, Galway, Ireland", "lat": "53.27702430", "lng": "-9.06148640", "type": "edu", "country": "Ireland"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1612.05753.pdf"]}, {"id": "270e5266a1f6e76954dedbc2caf6ff61a5fbf8d0", "title": "EmotioNet Challenge: Recognition of facial expressions of emotion in the wild", "addresses": [{"name": "Ohio State University", "source_name": "The Ohio State University", "street_adddress": "The Ohio State University, Woody Hayes Drive, Columbus, Franklin County, Ohio, 43210, USA", "lat": "40.00471095", "lng": "-83.02859368", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.01210.pdf"]}, {"id": "4078c37c39dc5c7c65a5494651ba6dd443cf9269", "title": "EMPIRICAL PERFORMANCE UPPER BOUNDS FOR IM- AGE 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": "2016", "pdf": ["https://pdfs.semanticscholar.org/4078/c37c39dc5c7c65a5494651ba6dd443cf9269.pdf"]}, {"id": "be5c16a3db2efd50ce361bda76837c019eaf40ab", "title": "Automatic Annotation of Object Instances by Region-Based Recurrent Neural Networks", "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": "2018", "pdf": []}, {"id": "b86b0a3494c2e2d4a3f4c9a18f1e4fec542bb57d", "title": "Perceptual Material Attributes Arise in Local Material Recognition", "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://pdfs.semanticscholar.org/b86b/0a3494c2e2d4a3f4c9a18f1e4fec542bb57d.pdf"]}, {"id": "287c5be2610e1c61798851feb32b88c424acfbf9", "title": "Hierarchical 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://pdfs.semanticscholar.org/287c/5be2610e1c61798851feb32b88c424acfbf9.pdf"]}, {"id": "08100a843de77ee84c0aabbc18cddb1adbd71cd6", "title": "Intelligent Film Assistant for Personalized Video Creation on Mobile Devices", "addresses": [{"name": "Vienna University of Technology", "source_name": "Vienna University of Technology", "street_adddress": "TU Wien, Hauptgeb\u00e4ude, Hoftrakt, Freihausviertel, KG Wieden, Wieden, Wien, 1040, \u00d6sterreich", "lat": "48.19853965", "lng": "16.36986168", "type": "edu", "country": "Austria"}, {"name": "University of Applied Sciences", "source_name": "National Kaohsiung, University of Applied Sciences, Kaohsiung, Taiwan. jspan@cc.kuas.edu.tw", "street_adddress": "No. 415\u865f, Jiangong Road, Sanmin District, Kaohsiung City, Taiwan 807", "lat": "22.64894580", "lng": "120.32831570", "type": "edu", "country": "Taiwan"}], "year": "2017", "pdf": []}, {"id": "6fc8c988dd841c6c4f5e96b1b1458b6aa564b2de", "title": "Crowd Counting via Scale-Adaptive Convolutional Neural Network", "addresses": [{"name": "Shanghai Jiaotong University", "source_name": "Shanghai Jiaotong University", "street_adddress": "China, Shanghai, Minhang, \u4e1c\u5ddd\u8def \u90ae\u653f\u7f16\u7801: 200240", "lat": "31.02522010", "lng": "121.43377840", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.04433.pdf"]}, {"id": "38d0dd93755b83b2390815fda926866f7ec624ce", "title": "Action Machine: Rethinking Action Recognition in Trimmed Videos", "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/1812.05770.pdf"]}, {"id": "3df6130707e103073f742b0d8a83a0889003f5b2", "title": "S4Net: Single Stage Salient-Instance 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": "Nankai University", "source_name": "Nankai University", "street_adddress": "94 Weijin Rd, Nankai Qu, China, 300071", "lat": "39.10394430", "lng": "117.17422320", "type": "edu", "country": ""}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1711.07618.pdf"]}, {"id": "975af82c9ce82a1fad760d58ba0a661217689aa9", "title": "Answerer in Questioner's Mind for Goal-Oriented Visual Dialogue", "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://pdfs.semanticscholar.org/2e02/70ca3154a092a8382248fb7810e3ace85670.pdf"]}, {"id": "258dda85eadcd2081d1e0131826aceac7f1e2415", "title": "Beyond Manual Annotations for Learning Visual Representations", "addresses": [{"name": "Carnegie Mellon University Silicon Valley", "source_name": "CARNEGIE MELLON UNIVERSITY", "street_adddress": "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu", "country": "United States"}, {"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://pdfs.semanticscholar.org/e62d/40940a2711c7adca2857110272fb34d70576.pdf"]}, {"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"]}, {"id": "8cdd241b474bf7b0632162403ac2a3c4799252ad", "title": "Best of Both Worlds: Transferring Knowledge from Discriminative Learning to a Generative Visual Dialog Model", "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/1706.01554.pdf"]}, {"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": "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"]}, {"id": "f678ca5a6bab62f78c26ab9e7f85876c68952173", "title": "Leveraging Motion Priors in Videos for Improving Human Segmentation", "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"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.11436.pdf"]}, {"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"]}, {"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"]}, {"id": "a22691f5f44862fc8ccf6581c5a0f40b97535c2b", "title": "Gibson Env: Real-World Perception for Embodied Agents", "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": "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/1808.10654.pdf"]}, {"id": "fa93e027e795e98405dc72f123aadebafc5d80d8", "title": "Explaining the Ambiguity of Object Detection and 6D Pose from Visual Data", "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/1812.00287.pdf"]}, {"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"]}, {"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"]}, {"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"]}, {"id": "67e5eaa07cdf79b09eaf5b38ea99a01272f94752", "title": "Beyond Grids : Learning Graph Representations for Visual Recognition", "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": "Carnegie Mellon University Silicon Valley", "source_name": "CARNEGIE MELLON UNIVERSITY", "street_adddress": "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/67e5/eaa07cdf79b09eaf5b38ea99a01272f94752.pdf"]}, {"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"}], "year": "2018", "pdf": []}, {"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": ""}, {"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"]}, {"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 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": "2017", "pdf": ["https://pdfs.semanticscholar.org/ccd3/dcbccae7d903608530bddf6381db8e723a7d.pdf"]}, {"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 Thomas J. Watson Research Center", "source_name": "IBM Thomas J. Watson Research Center", "street_adddress": "IBM Yorktown research lab, Adams Road, Millwood, Town of New Castle, Westchester County, New York, 10562, USA", "lat": "41.21002475", "lng": "-73.80407056", "type": "company", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.02965.pdf"]}, {"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"]}, {"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"]}, {"id": "29b737cdb317e47e7cc219b438ea38e8fdceb45c", "title": "Approximate Distribution Matching for Sequence-to-Sequence Learning", "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"}, {"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/1808.08003.pdf"]}, {"id": "514dd3e2e9fa732359b85ce4dd7d9437ef86cc99", "title": "Webly Supervised Learning of Convolutional Networks", "addresses": [{"name": "Carnegie Mellon University Silicon Valley", "source_name": "CARNEGIE MELLON UNIVERSITY", "street_adddress": "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu", "country": "United States"}], "year": "2015", "pdf": ["https://arxiv.org/pdf/1505.01554.pdf"]}, {"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": []}, {"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": "Columbus, OH 43210, USA", "lat": "40.01419050", "lng": "-83.03091430", "type": "edu", "country": "United States"}], "year": "2018", "pdf": []}, {"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"]}, {"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"]}, {"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"]}, {"id": "92a5af98c47bce7208d043c7c418633cd537701c", "title": "Improving Image Captioning by Leveraging Knowledge Graphs", "addresses": [{"name": "The Pennsylvania State University", "source_name": "The Pennsylvania State University", "street_adddress": "Old Main, State College, PA 16801, USA", "lat": "40.79821330", "lng": "-77.85990840", "type": "edu", "country": "United States"}], "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.08942.pdf"]}, {"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"]}, {"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"]}, {"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 (ETRI), Republic of Korea", "street_adddress": "South Korea", "lat": "35.90775700", "lng": "127.76692200", "type": "edu", "country": "South Korea"}], "year": "2018", "pdf": []}, {"id": "6fbd67c047fdcec3ec157173b4dd28b44cdb3589", "title": "A Multi-Stream Convolutional Neural Network Framework for Group Activity Recognition", "addresses": [{"name": "Amirkabir University of Technology", "source_name": "Amirkabir University of Technology", "street_adddress": "\u062f\u0627\u0646\u0634\u06af\u0627\u0647 \u0635\u0646\u0639\u062a\u06cc \u0627\u0645\u06cc\u0631\u06a9\u0628\u06cc\u0631, \u0648\u0644\u06cc \u0639\u0635\u0631, \u0645\u06cc\u062f\u0627\u0646 \u0648\u0644\u06cc\u0639\u0635\u0631, \u0645\u0646\u0637\u0642\u0647 \u06f6 \u0634\u0647\u0631 \u062a\u0647\u0631\u0627\u0646, \u062a\u0647\u0631\u0627\u0646, \u0628\u062e\u0634 \u0645\u0631\u06a9\u0632\u06cc \u0634\u0647\u0631\u0633\u062a\u0627\u0646 \u062a\u0647\u0631\u0627\u0646, \u0634\u0647\u0631\u0633\u062a\u0627\u0646 \u062a\u0647\u0631\u0627\u0646, \u0627\u0633\u062a\u0627\u0646 \u062a\u0647\u0631\u0627\u0646, \u0646\u0628\u0634 \u0628\u0631\u0627\u062f\u0631\u0627\u0646 \u0645\u0638\u0641\u0631, \u200f\u0627\u06cc\u0631\u0627\u0646\u200e", "lat": "35.70451400", "lng": "51.40972058", "type": "edu", "country": "Iran"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.10328.pdf"]}, {"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"]}, {"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": []}, {"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"]}, {"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": []}, {"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"]}, {"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": []}, {"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"]}, {"id": "d86ad6265ac6e5555d55f6fe677f6e34bceca67a", "title": "Decoupled Novel Object Captioner", "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": "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": ["https://arxiv.org/pdf/1804.03803.pdf"]}, {"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"]}, {"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"]}, {"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": []}, {"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"]}, {"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"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/db0a/4af734dab1854c2e8dfe499fe0e353226e45.pdf"]}, {"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"]}, {"id": "7fd358a0eba775fe9d87f165cb2074fa8fa762e0", "title": "Spatial-Aware Object Embeddings for Zero-Shot Localization and Classification of Actions", "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": "2017", "pdf": ["https://arxiv.org/pdf/1707.09145.pdf"]}, {"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"]}, {"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"]}, {"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"]}, {"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"]}, {"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"]}, {"id": "12847a91be77db332944fa45b7e379b89e135e27", "title": "Bird Species Classification using Transfer Learning with Multistage Training", "addresses": [{"name": "Jadavpur University", "source_name": "Jadavpur University", "street_adddress": "Jadavpur University, Chingrighata Flyover, Basani Devi Colony, Kolkata, H\u0101ora, West Bengal, 700098, India", "lat": "22.56115370", "lng": "88.41310194", "type": "edu", "country": "India"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.04250.pdf"]}, {"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"]}, {"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"]}, {"id": "89884c2b045cfa10ee0bb0795ee75195d4b37ace", "title": "Self-Contained Stylization via Steganography for Reverse and Serial Style Transfer", "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": "2018", "pdf": ["https://arxiv.org/pdf/1812.03910.pdf"]}, {"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"]}, {"id": "631a1571d1a073369ec7c98e196de07e263ae130", "title": "Describing Natural Images Containing Novel Objects with Knowledge Guided Assitance", "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"}, {"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": "2017", "pdf": ["https://arxiv.org/pdf/1710.06303.pdf"]}, {"id": "55e4cf29055d1556baf72cd17d2bdb692c8554c0", "title": "Do deep features retrieve X ? : A tool for quick inspection of deep visual similarities", "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": "2015", "pdf": ["https://pdfs.semanticscholar.org/fc8f/fedb156fdfa3636d7e868ff2ca359c7fd1f0.pdf"]}, {"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"]}, {"id": "518f3cb2c9f2481cdce7741c5a821c26378b75e9", "title": "The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition", "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/1511.06789.pdf"]}, {"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"}], "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"]}, {"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"]}, {"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"]}, {"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"]}, {"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"]}, {"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"]}, {"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"]}, {"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": ""}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.10860.pdf"]}, {"id": "b0d343ad82eb4060f016ff39289eacb222c45632", "title": "Transferable Semi-Supervised Semantic Segmentation", "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": "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": "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/1711.06828.pdf"]}, {"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"]}, {"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"]}, {"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"]}, {"id": "08162395a4b47236bf64d1ec5a286d3d207e91e2", "title": "Active learning and discovery of object categories in the presence of unnameable instances", "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": "2015", "pdf": ["http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/2B_109.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/2B_109_ext.pdf"]}, {"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"]}, {"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": []}, {"id": "29cbbed59a47566851deb63602a34c08e9ad3645", "title": "Improving Multi-Person Pose Estimation using Label Correction", "addresses": [{"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": ["https://arxiv.org/pdf/1811.03331.pdf"]}, {"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"]}, {"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"]}, {"id": "1c0d70587340adc412c6e2afd71012d563c1e724", "title": "Could we create a training set for image captioning using automatic translation?", "addresses": [{"name": "Hacettepe Universitesi", "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"]}, {"id": "fa5ab04ebf64de3bd57bd0729ce9ca3440258acc", "title": "Unprecedented Usage of Pre-trained CNNs on Beauty Product", "addresses": [{"name": "University of Malaya", "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": []}, {"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"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1612.00370.pdf"]}, {"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": []}, {"id": "42c1111c9cbb74b2755f58c6e9e84e7d1d11cc6e", "title": "Object Recognition Based on Amounts of Unlabeled Data", "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"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1603.07957.pdf"]}, {"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"]}, {"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"]}, {"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"]}, {"id": "34d294ded4bdbab9d76ec959fa1c8a34703f0200", "title": "Material Recognition from Local Appearance in Global Context", "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/1611.09394.pdf"]}, {"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": []}, {"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 Silicon Valley", "source_name": "CARNEGIE MELLON UNIVERSITY", "street_adddress": "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "lat": "37.41021930", "lng": "-122.05965487", "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"]}, {"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"]}, {"id": "3bb4f2013d99eaf2afc182fa482bd0f2d63f2d82", "title": "Visual Question Answering with Memory-Augmented 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/1707.04968.pdf"]}, {"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": []}, {"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"]}, {"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"]}, {"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": []}, {"id": "95f74ce5a69fdcd2abda908724d2ab4977e72100", "title": "Using Syntax to Ground Referring Expressions in Natural Images", "addresses": [{"name": "Carnegie Mellon University Silicon Valley", "source_name": "CARNEGIE MELLON UNIVERSITY", "street_adddress": "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.10547.pdf"]}, {"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"]}, {"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"]}, {"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"}, {"name": "University of California", "source_name": "University of California", "street_adddress": "Berkeley, CA, USA", "lat": "37.87189920", "lng": "-122.25853990", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["http://faculty.ucmerced.edu/mhyang/papers/pami16_segmentation_evaluation.pdf", "http://faculty.ucmerced.edu/mhyang/papers/pami17_segmentation_evaluation.pdf"]}, {"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"]}, {"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"]}, {"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"]}, {"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"]}, {"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"]}, {"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"]}, {"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"}, {"name": "University of California", "source_name": "University of California", "street_adddress": "Berkeley, CA, USA", "lat": "37.87189920", "lng": "-122.25853990", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.04310.pdf"]}, {"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": []}, {"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"]}, {"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": []}, {"id": "8216ec4e94537de667510a7ef2ea051622fffb36", "title": "Class Rectification Hard Mining for Imbalanced Deep Learning", "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": "2017", "pdf": ["https://arxiv.org/pdf/1712.03162.pdf"]}, {"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": ""}, {"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"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1606.02009.pdf"]}, {"id": "e34b0815f02b4dd5c8ba95f48b5833f9cdd4215b", "title": "Towards semantic visual representation: augmenting image representation with natural language descriptors", "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": "2016", "pdf": []}, {"id": "06cad81a163e345828c0804f42252177049dd1bc", "title": "Sequence to Sequence -- Video to Text", "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"}, {"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"}, {"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://arxiv.org/pdf/1505.00487.pdf"]}, {"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"]}, {"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"]}, {"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"]}, {"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"]}, {"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"]}, {"id": "ccd99008d942b890cecd308a31ba61240eac9e54", "title": "Learning to Segment Every Thing", "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": "2018", "pdf": ["https://arxiv.org/pdf/1711.10370.pdf"]}, {"id": "6a18355b3b8c0f9deae09f2a86d939e64de5143b", "title": "Fast Patch-based Style Transfer of Arbitrary Style.", "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://arxiv.org/pdf/1612.04337.pdf"]}, {"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"]}, {"id": "043432efc33fb01cc12f11fe8ce411f41b450c16", "title": "Mining Object Parts from CNNs via Active Question-Answering", "addresses": [{"name": "University of California, Los Angeles", "source_name": "University of California, Los Angeles", "street_adddress": "200 UCLA, Medical Plaza Driveway Suite 540, Los Angeles, CA 90095, USA", "lat": "34.06877880", "lng": "-118.44500940", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.03173.pdf"]}, {"id": "663a60841c3e703d7c18cf78f0657efee6aebb9d", "title": "A review of object detection based on convolutional neural network", "addresses": [{"name": "Fundamental Science on Communication Information Transmission and Fusion Technology Laboratory, Hangzhou 310018, China", "source_name": "Fundamental Science on Communication Information Transmission and Fusion Technology Laboratory, Hangzhou 310018, China", "street_adddress": "Jianggan, Hangzhou, Zhejiang, China, 310018", "lat": "30.31600970", "lng": "120.37394070", "type": "edu", "country": "China"}], "year": "2017", "pdf": []}, {"id": "170a5f5da9ac9187f1c88f21a88d35db38b4111a", "title": "Online Real-Time Multiple Spatiotemporal Action Localisation and Prediction", "addresses": [{"name": "Oxford Brookes University", "source_name": "Oxford Brookes University", "street_adddress": "Oxford Brookes University, Headington Road, Headington, Oxford, Oxon, South East, England, OX3 0BL, UK", "lat": "51.75552050", "lng": "-1.22615970", "type": "edu", "country": "United Kingdom"}, {"name": "Oxford University", "source_name": "Oxford University", "street_adddress": "University College, Logic Lane, Grandpont, Oxford, Oxon, South East, England, OX1 4EX, UK", "lat": "51.75208490", "lng": "-1.25166460", "type": "edu", "country": "United Kingdom"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1611.08563.pdf"]}, {"id": "ce450e4849490924488664b44769b4ca57f1bc1a", "title": "Procedural Generation of Videos to Train Deep Action Recognition Networks", "addresses": [{"name": "Toyota Research Institute", "source_name": "Toyota Research Institute", "street_adddress": "Toyota Research Institute, 4440, West El Camino Real, Los Altos, Santa Clara County, California, 94022, USA", "lat": "37.40253645", "lng": "-122.11655107", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1612.00881.pdf"]}, {"id": "c919a9f61656cdcd3a26076057ee006c48e8f609", "title": "High-Value Target Detection", "addresses": [{"name": "University of Tartu", "source_name": "UNIVERSITY OF TARTU", "street_adddress": "Paabel, University of Tartu, 17, \u00dclikooli, Kesklinn, Tartu linn, Tartu, Tartu linn, Tartu maakond, 53007, Eesti", "lat": "58.38131405", "lng": "26.72078081", "type": "edu", "country": "Estonia"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/c919/a9f61656cdcd3a26076057ee006c48e8f609.pdf"]}, {"id": "f05ea1ba8179595c8540bd26d5bc8f6efff78c82", "title": "Looking Beyond a Clever Narrative: Visual Context and Attention are Primary Drivers of Affect in Video Advertisements", "addresses": [{"name": "International Institute of Information Technology", "source_name": "International Institute of Information Technology", "street_adddress": "International Institute of Information Technology, Hyderabad, Campus Road, Ward 105 Gachibowli, Greater Hyderabad Municipal Corporation West Zone, Hyderabad, Rangareddy District, Telangana, 500032, India", "lat": "17.44549570", "lng": "78.34854698", "type": "edu", "country": "India"}, {"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"}, {"name": "Hyderabad, India", "source_name": "Hyderabad, India", "street_adddress": "Hyderabad, Telangana, India", "lat": "17.38504400", "lng": "78.48667100", "type": "edu", "country": "India"}, {"name": "Singapore", "source_name": "Singapore", "street_adddress": "Singapore", "lat": "1.35208300", "lng": "103.81983600", "type": "edu", "country": "Singapore"}, {"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": "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/1808.04610.pdf"]}, {"id": "3d0660e18c17db305b9764bb86b21a429241309e", "title": "Counting Everyday Objects in Everyday Scenes", "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/1604.03505.pdf"]}, {"id": "9d0ac8e084fd6ac32528aa480f71fab4b4f5d3a1", "title": "Bottle Detection in the Wild Using Low-Altitude Unmanned Aerial Vehicles", "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": []}, {"id": "b92f984f328851a5572e38ee816ebdcc515f2a0a", "title": "Deep Learning Based Surveillance System for Open Critical Areas", "addresses": [{"name": "University of Florence", "source_name": "University of Florence", "street_adddress": "Piazza di San Marco, 4, 50121 Firenze FI, Italy", "lat": "43.77764260", "lng": "11.25976500", "type": "edu", "country": "Italy"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/b92f/984f328851a5572e38ee816ebdcc515f2a0a.pdf"]}, {"id": "518999fbc7d2ced2b83f0a9bdb06e06184e00b2a", "title": "An efficient license plate recognition system using convolution neural networks", "addresses": [{"name": "National Taiwan Normal University", "source_name": "National Taiwan Normal University", "street_adddress": "\u5e2b\u5927\u5206\u90e8, 88, \u6c40\u5dde\u8def\u56db\u6bb5, \u842c\u5e74\u91cc, \u6587\u5c71\u5340, \u81fa\u5317\u5e02, 11677, \u81fa\u7063", "lat": "25.00823205", "lng": "121.53577153", "type": "edu", "country": "Taiwan"}], "year": "2018", "pdf": []}, {"id": "ccb9ffa26b28dffc4f7d613821d1a9f0d60ea3f4", "title": "Online Adaptation of Convolutional Neural Networks 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": "2017", "pdf": ["https://arxiv.org/pdf/1706.09364.pdf"]}, {"id": "871001c87c2c1b4059576ca5dcb95ab61afd3c9a", "title": "Improving Generalization via Scalable Neighborhood Component Analysis", "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/1808.04699.pdf"]}, {"id": "77685c77a1fa39890006fe13f43738aac49a2c51", "title": "Attacking Visual Language Grounding with Adversarial Examples: A Case Study on Neural Image Captioning", "addresses": [{"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"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1712.02051.pdf"]}, {"id": "f3ab1f95a3d7db15cb7c94cac0de015101e60326", "title": "Incremental Segmentation on Private Data without Catastrophic Forgetting", "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": ["https://pdfs.semanticscholar.org/f3ab/1f95a3d7db15cb7c94cac0de015101e60326.pdf"]}, {"id": "35251b35fa2ecf72c332e6492d1c587669fcfe94", "title": "Intelligent Computing Methodologies", "addresses": [{"name": "Inha University", "source_name": "Intelligent Technology Laboratory, Inha University, Incheon, Korea", "street_adddress": "100 Inha-ro, Yonghyeon 1(il).4(sa)-dong, Nam-gu, Incheon, South Korea", "lat": "37.45002210", "lng": "126.65348800", "type": "edu", "country": "South Korea"}, {"name": "Liverpool John Moores University", "source_name": "Liverpool John Moores University", "street_adddress": "John Lennon Art and Design Building, Duckinfield Street, Knowledge Quarter, Liverpool, North West England, England, L3 5YD, UK", "lat": "53.40507470", "lng": "-2.97030029", "type": "edu", "country": "United Kingdom"}, {"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": []}, {"id": "fa43b7ee7dbd821745a3046328544fd8d39d3961", "title": "An Intriguing Influence of Visual Data in Learning a Representation", "addresses": [{"name": "Carnegie Mellon University Silicon Valley", "source_name": "CARNEGIE MELLON UNIVERSITY", "street_adddress": "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/fa43/b7ee7dbd821745a3046328544fd8d39d3961.pdf"]}, {"id": "6779b1ebdae5e3af812ce075611f2cb00073af82", "title": "Multiview Supervision By Registration", "addresses": [{"name": "University of Pennsylvania", "source_name": "University of Pennsylvania", "street_adddress": "Penn Museum, 3260, South Street, University City, Philadelphia, Philadelphia County, Pennsylvania, 19104, USA", "lat": "39.94923440", "lng": "-75.19198985", "type": "edu", "country": "United States"}, {"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://arxiv.org/pdf/1811.11251.pdf"]}, {"id": "8b3288421ee4fa7f9ff45ddc6adbf04698c4b8ba", "title": "On the Iterative Refinement of Densely Connected Representation Levels for Semantic Segmentation", "addresses": [{"name": "Computer Vision Center, Barcelona", "source_name": "Computer Vision Center, Barcelona", "street_adddress": "Campus UAB, Edifici O, s/n, 08193 Cerdanyola del Vall\u00e8s, Barcelona, Spain", "lat": "41.50089570", "lng": "2.11155300", "type": "edu", "country": "Spain"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.11332.pdf"]}, {"id": "43fd4ebcd576eed33d85e9c5eeebe483c285c3bc", "title": "Multi-evidence Filtering and Fusion for Multi-label Classification, Object Detection and Semantic Segmentation Based on Weakly Supervised Learning", "addresses": [{"name": "University of Hong Kong", "source_name": "University of Hong Kong", "street_adddress": "\u6d77\u6d0b\u79d1\u5b78\u7814\u7a76\u6240 The Swire Institute of Marine Science, \u9db4\u5480\u9053 Cape D'Aguilar Road, \u9db4\u5480\u4f4e\u96fb\u53f0 Cape D'Aguilar Low-Level Radio Station, \u77f3\u6fb3 Shek O, \u82bd\u83dc\u5751\u6751 Nga Choy Hang Tsuen, \u5357\u5340 Southern District, \u9999\u6e2f\u5cf6 Hong Kong Island, HK, \u4e2d\u56fd", "lat": "22.20814690", "lng": "114.25964115", "type": "edu", "country": "China"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.09129.pdf"]}, {"id": "9bdc406ad9e9fc0ce356e6d0e53780534f418849", "title": "DeepDiary: Automatic Caption Generation for Lifelogging Image Streams.", "addresses": [{"name": "Indiana University", "source_name": "Indiana University", "street_adddress": "Indiana University East, West Cart Road, Richmond, Wayne County, Indiana, 47374, USA", "lat": "39.86948105", "lng": "-84.87956905", "type": "edu", "country": "United States"}], "year": "2016", "pdf": ["https://arxiv.org/pdf/1608.03819.pdf"]}, {"id": "61d18c4c58661ded9a949a671574f76a0303c772", "title": "Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis", "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/1801.05091.pdf"]}, {"id": "d91c04b567909fbc9995c1b60800aba584606a72", "title": "Progressive Visual Object Detection with Positive Training Examples Only", "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"}], "year": "2015", "pdf": ["http://vision.cs.tut.fi/data/publications/scia2015_progressive_detection.pdf"]}, {"id": "3067885f8f7d6d09a376ab4c5c83eb3fa5e5141a", "title": "Text-to-Image Generation Using Multi-Instance StackGan", "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": "", "pdf": ["https://pdfs.semanticscholar.org/3067/885f8f7d6d09a376ab4c5c83eb3fa5e5141a.pdf"]}, {"id": "8a17310abb249ce8fce8f409709b5395da32e0a6", "title": "Bundled Object Context for Referring Expressions", "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": "2018", "pdf": ["http://vipl.ict.ac.cn/homepage/jsq/publication/2018-Li-TMM-Bundled%20Object%20Context%20for%20Referring%20Expressions.pdf"]}, {"id": "d02bf4082850a667bf0b7b6205df1cf9c1899233", "title": "Quantifying the visual concreteness of words and topics in multimodal datasets", "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/1804.06786.pdf"]}, {"id": "2b4e48d6a0f7c612acc8748bc0dccacde2174c1d", "title": "A task in a suit and a tie: paraphrase generation with semantic augmentation", "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://arxiv.org/pdf/1811.00119.pdf"]}, {"id": "828a7b3122ebd5b8b0c617902bc04ac5a6c60240", "title": "Show, Adapt and Tell: Adversarial Training of Cross-Domain Image Captioner", "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/1705.00930.pdf"]}, {"id": "9bbc952adb3e3c6091d45d800e806d3373a52bac", "title": "Learning Visual Classifiers using Human-centric Annotations", "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://pdfs.semanticscholar.org/9bbc/952adb3e3c6091d45d800e806d3373a52bac.pdf"]}, {"id": "8a1294d2093b7f339e3d33da46e008aca3528893", "title": "FoveaNet: Perspective-Aware Urban Scene Parsing", "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://arxiv.org/pdf/1708.02421.pdf"]}, {"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"]}, {"id": "4dab9b254f31ff72e1a32651b2bfe337d3d8fd5b", "title": "A Structured Model For Action Detection", "addresses": [{"name": "Carnegie Mellon University Silicon Valley", "source_name": "CARNEGIE MELLON UNIVERSITY", "street_adddress": "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu", "country": "United States"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.03544.pdf"]}, {"id": "285f0885385d6214363bb986ad23bcfd3abe84f6", "title": "RepMet: Representative-based metric learning for classification and one-shot object detection", "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": "Technion", "source_name": "Technion", "street_adddress": "Haifa, 3200003, Israel", "lat": "32.77677830", "lng": "35.02312710", "type": "edu", "country": "Israel"}], "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.04728.pdf"]}, {"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"]}, {"id": "ee597ce2a63912b162d2a152c391d166fa1c4733", "title": "Batch-normalized recurrent highway 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": "2017", "pdf": ["https://arxiv.org/pdf/1809.10271.pdf"]}, {"id": "e5346a581ade62e1ac4b272d26d340fe78b58faa", "title": "Weakly Supervised Semantic Segmentation Using Web-Crawled Videos", "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": ["https://arxiv.org/pdf/1701.00352.pdf"]}, {"id": "25c087a7b86c2f5528d702942bf3a29e81267cb1", "title": "Talking about other people: an endless range of possibilities", "addresses": [{"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://pdfs.semanticscholar.org/25c0/87a7b86c2f5528d702942bf3a29e81267cb1.pdf"]}, {"id": "45f858f9e8d7713f60f52618e54089ba68dfcd6d", "title": "What Actions are Needed for Understanding Human Actions in Videos?", "addresses": [{"name": "Carnegie Mellon University Silicon Valley", "source_name": "CARNEGIE MELLON UNIVERSITY", "street_adddress": "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu", "country": "United States"}], "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.02696.pdf"]}, {"id": "b133b2d7df9b848253b9d75e2ca5c68e21eba008", "title": "Kobe University , NICT and University of Siegen at TRECVID 2017 AVS Task", "addresses": [{"name": "Kobe University", "source_name": "Kobe University", "street_adddress": "\u795e\u6238\u5927\u5b66, \u7058\u4e09\u7530\u7dda, \u7058\u533a, \u795e\u6238\u5e02, \u5175\u5eab\u770c, \u8fd1\u757f\u5730\u65b9, 657-00027, \u65e5\u672c", "lat": "34.72757140", "lng": "135.23710000", "type": "edu", "country": "Japan"}], "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/c2c1/ab9eac2907e15618d80f5ce0c9b60f2c36cc.pdf"]}, {"id": "121fc9a276f4646efba43b7469050542274171d3", "title": "DeepSign: Deep Learning based Traffic Sign Recognition", "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": "2018", "pdf": []}]}
\ No newline at end of file |