1
|
{"id": "0ee1916a0cb2dc7d3add086b5f1092c3d4beb38a", "paper": {"paper_id": "0ee1916a0cb2dc7d3add086b5f1092c3d4beb38a", "key": "voc", "title": "The Pascal Visual Object Classes (VOC) Challenge", "year": 2009, "pdf": "https://doi.org/10.1007/s11263-009-0275-4", "address": "", "name": "VOC"}, "address": null, "additional_papers": [], "citations": [{"id": "9f4078773c8ea3f37951bf617dbce1d4b3795839", "title": "Leveraging Inexpensive Supervision Signals for Visual Learning", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/9f40/78773c8ea3f37951bf617dbce1d4b3795839.pdf"}, {"id": "0e2af97f07625cb3cf5e30f1c9d807124cbbc850", "title": "From Large Scale Image Categorization to Entry-Level Categories", "addresses": [{"address": "University of North Carolina at Chapel Hill", "lat": "35.91139710", "lng": "-79.05045290", "type": "edu"}], "year": 2013, "pdf": "http://www.cv-foundation.org/openaccess/content_iccv_2013/papers/Ordonez_From_Large_Scale_2013_ICCV_paper.pdf"}, {"id": "131e9edbe4b0322a467b7e8c35f6b0c0ca750e21", "title": "Contextual Action Recognition with R*CNN", "addresses": [{"address": "Microsoft", "lat": "47.64233180", "lng": "-122.13693020", "type": "company"}], "year": 2015, "pdf": "http://openaccess.thecvf.com/content_iccv_2015/papers/Gkioxari_Contextual_Action_Recognition_ICCV_2015_paper.pdf"}, {"id": "396aacab076a3607429f58ce442d5d57b5aaa794", "title": "Semantic Instance Annotation of Street Scenes by 3D to 2D Label Transfer", "addresses": [{"address": "University of Washington", "lat": "47.65432380", "lng": "-122.30800894", "type": "edu"}], "year": 2016, "pdf": "http://arxiv.org/pdf/1511.03240v2.pdf"}, {"id": "ef8de1bd92e9ee9d0d2dee73095d4d348dc54a98", "title": "Fine-grained Activity Recognition with Holistic and Pose based Features", "addresses": [{"address": "Max Planck Institute for Informatics", "lat": "49.25795660", "lng": "7.04577417", "type": "edu"}, {"address": "Stanford University", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu"}], "year": "2014", "pdf": "https://arxiv.org/pdf/1406.1881.pdf"}, {"id": "86c158ef6caaf247d5d14e07c5edded0147df8b7", "title": "Spatial Memory for Context Reasoning in Object Detection", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1704.04224.pdf"}, {"id": "18fe63c013983bea53be7d559ef36a1f385ca6ea", "title": "Supervision Beyond Human Annotations for Learning Visual Representations", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/18fe/63c013983bea53be7d559ef36a1f385ca6ea.pdf"}, {"id": "663cca096b98c8f0444608b188e464028ee34368", "title": "CASENet: Deep Category-Aware Semantic Edge Detection", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1705.09759.pdf"}, {"id": "f9d171019bfeb71733fe36f7fae14f342ca9e51c", "title": "Hough Forests Revisited: An Approach to Multiple Instance Tracking from Multiple Cameras", "addresses": [{"address": "Graz University of Technology", "lat": "47.05821000", "lng": "15.46019568", "type": "edu"}], "year": 2014, "pdf": "http://pdfs.semanticscholar.org/f9d1/71019bfeb71733fe36f7fae14f342ca9e51c.pdf"}, {"id": "f832fdf1fac092b4140bf81d38e6bc6af5c1ea65", "title": "Instance-Level Human Parsing via Part Grouping Network", "addresses": [{"address": "Sun Yat-Sen University", "lat": "23.09461185", "lng": "113.28788994", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1808.00157.pdf"}, {"id": "41be021880a916305c82199ddc2298eb271f6590", "title": "Benchmarks for Image Classification and Other High-dimensional Pattern Recognition Problems", "addresses": [{"address": "Purdue University", "lat": "40.43197220", "lng": "-86.92389368", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1806.05272.pdf"}, {"id": "fdcc1e66697a724bd2d0d2da368de04a7eaf9209", "title": "The Devil is in the Decoder", "addresses": [{"address": "University College London", "lat": "51.52316070", "lng": "-0.12820370", "type": "edu"}, {"address": "Google", "lat": "37.42199990", "lng": "-122.08405750", "type": "company"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1707.05847.pdf"}, {"id": "6e7a9779dee831658e973ee26ac8bfed2d6da033", "title": "Human Pose Estimation for Multiple Frames", "addresses": [{"address": "Stanford University", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu"}], "year": "2016", "pdf": "https://pdfs.semanticscholar.org/6e7a/9779dee831658e973ee26ac8bfed2d6da033.pdf"}, {"id": "29b3be93a60bbc5fe842826030853f99753b08bd", "title": "Hierarchical Scene Annotation", "addresses": [{"address": "California Institute of Technology", "lat": "34.13710185", "lng": "-118.12527487", "type": "edu"}], "year": "2013", "pdf": "https://pdfs.semanticscholar.org/6a94/c929f02e2ebd2477ca96d14334b311e9b829.pdf"}, {"id": "b88b83d2ffd30bf3bc3be3fb7492fd88f633b2fe", "title": "Subcategory-Aware Object Classification", "addresses": [{"address": "National University of Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu"}], "year": 2013, "pdf": "http://vigir.missouri.edu/~gdesouza/Research/Conference_CDs/IEEE_CVPR2013/data/Papers/4989a827.pdf"}, {"id": "241b86d3c71d14b8cc6044a425b047a0724cfdc9", "title": "Following Gaze in Video", "addresses": [{"address": "MIT", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu"}], "year": 2017, "pdf": "http://people.csail.mit.edu/recasens/docs/videogazefollow.pdf"}, {"id": "0d746111135c2e7f91443869003d05cde3044beb", "title": "Partial face detection for continuous authentication", "addresses": [{"address": "State University of New Jersey", "lat": "40.51865195", "lng": "-74.44099801", "type": "edu"}, {"address": "University of Maryland", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu"}], "year": 2016, "pdf": "https://doi.org/10.1109/ICIP.2016.7532908"}, {"id": "420c46d7cafcb841309f02ad04cf51cb1f190a48", "title": "Multi-Scale Context Aggregation by Dilated Convolutions", "addresses": [{"address": "Princeton University", "lat": "40.34829285", "lng": "-74.66308325", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/b2a5/e98409c7a6a5e005348c023ccad23f5cb5a9.pdf"}, {"id": "076fd6fd85b93858155a1c775f1897f83d52b4c2", "title": "Improving an Object Detector and Extracting Regions Using Superpixels", "addresses": [{"address": "University of Central Florida", "lat": "28.59899755", "lng": "-81.19712501", "type": "edu"}], "year": 2013, "pdf": "http://www.crcv.ucf.edu/papers/cvpr2013/CVPR13_final_guang.pdf"}, {"id": "ccd3dcbccae7d903608530bddf6381db8e723a7d", "title": "Unsupervised Domain Adaptation for Semantic Segmentation with GANs", "addresses": [{"address": "University of Maryland", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu"}, {"address": "GE Global Research Center", "lat": "42.82982480", "lng": "-73.87719385", "type": "edu"}], "year": "2017", "pdf": "https://pdfs.semanticscholar.org/ccd3/dcbccae7d903608530bddf6381db8e723a7d.pdf"}, {"id": "b2cd92d930ed9b8d3f9dfcfff733f8384aa93de8", "title": "HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition", "addresses": [{"address": "University of Maryland College Park", "lat": "38.99203005", "lng": "-76.94610290", "type": "edu"}, {"address": "University of Maryland", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/b2cd/92d930ed9b8d3f9dfcfff733f8384aa93de8.pdf"}, {"id": "08eaa845a72a2b78e08e58592d8785942fced649", "title": "What's in a Question: Using Visual Questions as a Form of Supervision", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": 2017, "pdf": "http://arxiv.org/abs/1704.03895"}, {"id": "d0ac9913a3b1784f94446db2f1fb4cf3afda151f", "title": "Exploiting Multi-modal Curriculum in Noisy Web Data for Large-scale Concept Learning", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/d0ac/9913a3b1784f94446db2f1fb4cf3afda151f.pdf"}, {"id": "3a3a4408432408b62e2dc22de7820a5a2f7bbe9e", "title": "No Spare Parts: Sharing Part Detectors for Image Categorization", "addresses": [{"address": "University of Amsterdam", "lat": "52.35536550", "lng": "4.95016440", "type": "edu"}, {"address": "Delft University of Technology", "lat": "51.99882735", "lng": "4.37396037", "type": "edu"}], "year": "2016", "pdf": "https://arxiv.org/pdf/1510.04908.pdf"}, {"id": "d4f1eb008eb80595bcfdac368e23ae9754e1e745", "title": "Unconstrained Face Detection and Open-Set Face Recognition Challenge", "addresses": [{"address": "University of Colorado, Colorado Springs", "lat": "38.89207560", "lng": "-104.79716389", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1708.02337.pdf"}, {"id": "33ba256d59aefe27735a30b51caf0554e5e3a1df", "title": "Early Active Learning via Robust Representation and Structured Sparsity", "addresses": [{"address": "University of Texas at Arlington", "lat": "32.72836830", "lng": "-97.11201835", "type": "edu"}], "year": 2013, "pdf": "http://pdfs.semanticscholar.org/33ba/256d59aefe27735a30b51caf0554e5e3a1df.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": [{"address": "Jilin University", "lat": "22.05356500", "lng": "113.39913285", "type": "edu"}, {"address": "North Carolina State University", "lat": "35.77184965", "lng": "-78.67408695", "type": "edu"}], "year": "2016", "pdf": "https://pdfs.semanticscholar.org/b740/7b2ea67b8c82246f013f4966c4cac1507e60.pdf"}, {"id": "3af130e2fd41143d5fc49503830bbd7bafd01f8b", "title": "How Do We Evaluate the Quality of Computational Editing Systems?", "addresses": [{"address": "University of Wisconsin Madison", "lat": "43.07982815", "lng": "-89.43066425", "type": "edu"}], "year": 2014, "pdf": "http://pdfs.semanticscholar.org/db76/002794c12e5febc30510de58b54bb9344ea9.pdf"}, {"id": "732e4016225280b485c557a119ec50cffb8fee98", "title": "Are all training examples equally valuable?", "addresses": [{"address": "MIT", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu"}], "year": 2013, "pdf": "http://pdfs.semanticscholar.org/732e/4016225280b485c557a119ec50cffb8fee98.pdf"}, {"id": "6341274aca0c2977c3e1575378f4f2126aa9b050", "title": "A multi-scale cascade fully convolutional network face detector", "addresses": [{"address": "University of Southern California", "lat": "34.02241490", "lng": "-118.28634407", "type": "edu"}], "year": 2016, "pdf": "http://arxiv.org/pdf/1609.03536v1.pdf"}, {"id": "9bd9050c53d90dfa86cb22501812afe6fc897406", "title": "Fine-Grained and Layered Object Recognition", "addresses": [{"address": "Xi'an Jiaotong University", "lat": "34.24749490", "lng": "108.97898751", "type": "edu"}, {"address": "Kyoto University", "lat": "35.02749960", "lng": "135.78154513", "type": "edu"}], "year": 2012, "pdf": "http://pdfs.semanticscholar.org/9bd9/050c53d90dfa86cb22501812afe6fc897406.pdf"}, {"id": "3e0a1884448bfd7f416c6a45dfcdfc9f2e617268", "title": "Understanding and Controlling User Linkability in Decentralized Learning", "addresses": [{"address": "Max Planck Institute for Informatics", "lat": "49.25795660", "lng": "7.04577417", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1805.05838.pdf"}, {"id": "108961c7366e36825ffed94ac9eab603e05b6bc6", "title": "Deep Visual-Semantic Alignments for Generating Image Descriptions", "addresses": [{"address": "Stanford University", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu"}], "year": 2015, "pdf": "http://arxiv.org/abs/1412.2306"}, {"id": "282cee05661a690aa525f21b47c6ee39fb26a7c2", "title": "Build a Robust Learning Feature Descriptor by Using a New Image Visualization Method for Indoor Scenario Recognition", "addresses": [{"address": "Beijing University of Posts and Telecommunications", "lat": "39.96014880", "lng": "116.35193921", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/282c/ee05661a690aa525f21b47c6ee39fb26a7c2.pdf"}, {"id": "121503705689f46546cade78ff62963574b4750b", "title": "We Don\u2019t Need No Bounding-Boxes: Training Object Class Detectors Using Only Human Verification", "addresses": [{"address": "University of Edinburgh", "lat": "55.94951105", "lng": "-3.19534913", "type": "edu"}], "year": "2016", "pdf": "https://arxiv.org/pdf/1602.08405.pdf"}, {"id": "df0e280cae018cebd5b16ad701ad101265c369fa", "title": "Deep Attributes from Context-Aware Regional Neural Codes", "addresses": [{"address": "Columbia University", "lat": "40.84198360", "lng": "-73.94368971", "type": "edu"}, {"address": "Beihang University", "lat": "39.98083330", "lng": "116.34101249", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/df0e/280cae018cebd5b16ad701ad101265c369fa.pdf"}, {"id": "30654fd93360a339e271d4b194b7f7463b2c5dac", "title": "COSTA: Co-Occurrence Statistics for Zero-Shot Classification", "addresses": [{"address": "University of Amsterdam", "lat": "52.35536550", "lng": "4.95016440", "type": "edu"}], "year": 2014, "pdf": "https://ivi.fnwi.uva.nl/isis/publications/2014/MensinkCVPR2014/MensinkCVPR2014.pdf"}, {"id": "02ae77f4c289426f18e83ce6e295d39538fb0fcc", "title": "Dependency Modeling for Information Fusion with Applications in Visual Recognition", "addresses": [{"address": "Hong Kong Baptist University", "lat": "22.38742010", "lng": "114.20822220", "type": "edu"}], "year": 2013, "pdf": "http://pdfs.semanticscholar.org/02ae/77f4c289426f18e83ce6e295d39538fb0fcc.pdf"}, {"id": "23a84a4a77b6662d553c9252331e6b7920053125", "title": "Latent Model Ensemble with Auto-localization", "addresses": [{"address": "Electrical and Computer Engineering", "lat": "33.58667840", "lng": "-101.87539204", "type": "edu"}, {"address": "University of Missouri", "lat": "38.92676100", "lng": "-92.29193783", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/ad28/34a42fccfe965f2039591e2ac26453273405.pdf"}, {"id": "b7c5f885114186284c51e863b58292583047a8b4", "title": "GAdaBoost: Accelerating Adaboost Feature Selection with Genetic Algorithms", "addresses": [{"address": "American University in Cairo", "lat": "30.04287695", "lng": "31.23664139", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/b7c5/f885114186284c51e863b58292583047a8b4.pdf"}, {"id": "009678c2034cf4a9924a78d533d2ec81303a946e", "title": "Connecting Gaze, Scene, and Attention: Generalized Attention Estimation via Joint Modeling of Gaze and Scene Saliency", "addresses": [{"address": "Georgia Institute of Technology", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1807.10437.pdf"}, {"id": "0ae80aa149764e91544bbe45b80bb50434e7bda9", "title": "Ambient Sound Provides Supervision for Visual Learning", "addresses": [{"address": "MIT", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/714c/21c575d2c02a51f2dd5250164f1269be44ca.pdf"}, {"id": "16161051ee13dd3d836a39a280df822bf6442c84", "title": "Learning Efficient Object Detection Models with Knowledge Distillation", "addresses": [{"address": "University of California, San Diego", "lat": "32.87935255", "lng": "-117.23110049", "type": "edu"}, {"address": "University of Missouri", "lat": "38.92676100", "lng": "-92.29193783", "type": "edu"}], "year": "2017", "pdf": "https://pdfs.semanticscholar.org/4bd3/f187f3e09483b1f0f92150a4a77409691b0f.pdf"}, {"id": "d6b1b0e60e1764982ef95d4ade8fcaa10bfb156a", "title": "A Sketch-based Approach for Multimedia Retrieval", "addresses": [{"address": "International Institute of Information Technology", "lat": "17.44549570", "lng": "78.34854698", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/d6b1/b0e60e1764982ef95d4ade8fcaa10bfb156a.pdf"}, {"id": "079e20d0d870a5bade46cc9b4338a3d637399654", "title": "Semantic Segmentation , Urban Navigation , and Research Directions", "addresses": [{"address": "Princeton University", "lat": "40.34829285", "lng": "-74.66308325", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/079e/20d0d870a5bade46cc9b4338a3d637399654.pdf"}, {"id": "9035e87ce49b67b751838c7346d36fe481260217", "title": "An Introduction to Random Forests for Multi-class Object Detection", "addresses": [{"address": "Katholieke Universiteit Leuven", "lat": "50.88306860", "lng": "4.70195030", "type": "edu"}], "year": 2011, "pdf": "http://pdfs.semanticscholar.org/9035/e87ce49b67b751838c7346d36fe481260217.pdf"}, {"id": "24065d385bae5579be07607a1f63eb79cebf8773", "title": "Incremental Learning of NCM Forests for Large-Scale Image Classification", "addresses": [{"address": "University of Bonn", "lat": "50.73381240", "lng": "7.10224650", "type": "edu"}], "year": 2014, "pdf": "http://doi.ieeecomputersociety.org/10.1109/CVPR.2014.467"}, {"id": "7fbf1885f27fb72d5e553c4a2147375f928465ee", "title": "Not All Pixels Are Equal: Difficulty-Aware Semantic Segmentation via Deep Layer Cascade", "addresses": [{"address": "Chinese University of Hong Kong", "lat": "22.42031295", "lng": "114.20788644", "type": "edu"}, {"address": "Shenzhen Institutes of Advanced Technology", "lat": "22.59805605", "lng": "113.98533784", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1704.01344.pdf"}, {"id": "a89e1fc2681a9a399cc5008ea34b5ec3fe7ca845", "title": "Improving Fast Segmentation With Teacher-Student Learning", "addresses": [{"address": "Sun Yat-Sen University", "lat": "23.09461185", "lng": "113.28788994", "type": "edu"}, {"address": "Nanyang Technological University", "lat": "1.34841040", "lng": "103.68297965", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1810.08476.pdf"}, {"id": "3434ba5677e5c98e82ee17a1f2d0ddef66d0b009", "title": "Interactive tracking and action retrieval to support human behavior analysis", "addresses": [{"address": "Georgia Institute of Technology", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/3434/ba5677e5c98e82ee17a1f2d0ddef66d0b009.pdf"}, {"id": "3676c29babe1563ee64a1149d2ae2f9f1369fe25", "title": "Visual saliency computation for image analysis", "addresses": [{"address": "Boston University", "lat": "42.35042530", "lng": "-71.10056114", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/3676/c29babe1563ee64a1149d2ae2f9f1369fe25.pdf"}, {"id": "a60540a8407fd117fd8e6857d4728e661f53dcc8", "title": "Deep Domain Generalization via Conditional Invariant Adversarial Networks", "addresses": [{"address": "University of Science and Technology of China", "lat": "31.83907195", "lng": "117.26420748", "type": "edu"}, {"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}, {"address": "University of Pittsburgh", "lat": "40.44415295", "lng": "-79.96243993", "type": "edu"}, {"address": "University of Sydney", "lat": "-33.88890695", "lng": "151.18943366", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/a605/40a8407fd117fd8e6857d4728e661f53dcc8.pdf"}, {"id": "4aa286914f17cd8cefa0320e41800a99c142a1cd", "title": "Leveraging Context to Support Automated Food Recognition in Restaurants", "addresses": [{"address": "Georgia Institute of Technology", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu"}], "year": 2015, "pdf": "http://www.vbettadapura.com/egocentric/food/Food-Bettadapura15.pdf"}, {"id": "4ab10174a4f98f7e2da7cf6ccfeb9bc64c8e7da8", "title": "Efficient Metric Learning for Real-World Face Recognition", "addresses": [{"address": "Graz University of Technology", "lat": "47.05821000", "lng": "15.46019568", "type": "edu"}], "year": 2013, "pdf": "http://pdfs.semanticscholar.org/4ab1/0174a4f98f7e2da7cf6ccfeb9bc64c8e7da8.pdf"}, {"id": "e64fa00da02cc774559db5be88bc2862afbfd432", "title": "Histogram of Oriented Normal Vectors for Object Recognition with a Depth Sensor", "addresses": [{"address": "University of Missouri", "lat": "38.92676100", "lng": "-92.29193783", "type": "edu"}], "year": 2012, "pdf": "http://pdfs.semanticscholar.org/e64f/a00da02cc774559db5be88bc2862afbfd432.pdf"}, {"id": "0f0a5d8a7a087204026a6b67000887dbf5b6a20f", "title": "Generating objects going well with the surroundings", "addresses": [{"address": "Seoul National University", "lat": "37.26728000", "lng": "126.98411510", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1807.02925.pdf"}, {"id": "14a3194bb454f1f2e3fc1452045ac18c69959368", "title": "Fast Object Detection Using Multistage Particle Window Deformable Part Model", "addresses": [{"address": "National Chung Cheng University", "lat": "23.56306355", "lng": "120.47510531", "type": "edu"}], "year": 2014, "pdf": "http://www.cs.ccu.edu.tw/~wtchu/papers/2014ISM-chu.pdf"}, {"id": "187480101af3fb195993da1e2c17d917df24eb23", "title": "Unsupervised Visual Representation Learning by Context Prediction", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}, {"address": "University of California, Berkeley", "lat": "37.86871260", "lng": "-122.25586815", "type": "edu"}], "year": 2015, "pdf": "http://arxiv.org/pdf/1505.05192v2.pdf"}, {"id": "3b5787604b619c273bf98232b0bd3bce5d4a34ee", "title": "Learning Discriminative Hidden Structural Parts for Visual Tracking", "addresses": [{"address": "Chinese Academy of Sciences", "lat": "40.00447950", "lng": "116.37023800", "type": "edu"}, {"address": "University of Chinese Academy of Sciences", "lat": "39.90828040", "lng": "116.24585270", "type": "edu"}], "year": 2014, "pdf": "http://pdfs.semanticscholar.org/3b57/87604b619c273bf98232b0bd3bce5d4a34ee.pdf"}, {"id": "95f4b88d4b0a725d786b34558b60af47f5442230", "title": "Reconfigurable Processor for Deep Learning in Autonomous Vehicles", "addresses": [{"address": "Tsinghua University", "lat": "40.00229045", "lng": "116.32098908", "type": "edu"}, {"address": "Stanford University", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu"}], "year": "2017", "pdf": "https://pdfs.semanticscholar.org/381e/7525bc8b9d47ae0343e471f5f1d5e6963bbe.pdf"}, {"id": "205e895e03969c96f3c482b0bd26308b16a12bd0", "title": "Image Captioning with an Intermediate Attributes Layer", "addresses": [{"address": "University of Adelaide", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu"}], "year": "2015", "pdf": "https://pdfs.semanticscholar.org/205e/895e03969c96f3c482b0bd26308b16a12bd0.pdf"}, {"id": "6bb19408458dbae075be7f1612b969b565b4767a", "title": "Approximate Log-Hilbert-Schmidt Distances between Covariance Operators for Image Classification", "addresses": [{"address": "Dartmouth College", "lat": "43.70479270", "lng": "-72.29259090", "type": "edu"}], "year": 2016, "pdf": "http://openaccess.thecvf.com/content_cvpr_2016/papers/Minh_Approximate_Log-Hilbert-Schmidt_Distances_CVPR_2016_paper.pdf"}, {"id": "719969807953d7ea8bda0397b1aadbaa6e205718", "title": "Automatic Dataset Augmentation", "addresses": [{"address": "Harbin Institute of Technology", "lat": "45.74139210", "lng": "126.62552755", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1708.08201.pdf"}, {"id": "bfea962697e9b445b89a865b465ae967dd55b4fe", "title": "Efficient object detection via structured learning and local classifiers", "addresses": [{"address": "Oxford Brookes University", "lat": "51.75552050", "lng": "-1.22615970", "type": "edu"}], "year": "2013", "pdf": "https://pdfs.semanticscholar.org/bfea/962697e9b445b89a865b465ae967dd55b4fe.pdf"}, {"id": "20b038c50cc7148dfb364e2de51cde120c907c9f", "title": "Integrated perception with recurrent multi-task neural networks", "addresses": [{"address": "University of Oxford", "lat": "51.75345380", "lng": "-1.25400997", "type": "edu"}], "year": "2016", "pdf": "https://arxiv.org/pdf/1606.01735.pdf"}, {"id": "0faeec0d1c51623a511adb779dabb1e721a6309b", "title": "Seeing is Worse than Believing: Reading People's Minds Better than Computer-Vision Methods Recognize Actions", "addresses": [{"address": "National University of Ireland Maynooth", "lat": "53.38469750", "lng": "-6.60039458", "type": "edu"}, {"address": "Princeton University", "lat": "40.34829285", "lng": "-74.66308325", "type": "edu"}, {"address": "Purdue University", "lat": "40.43197220", "lng": "-86.92389368", "type": "edu"}, {"address": "Rutgers University", "lat": "40.47913175", "lng": "-74.43168868", "type": "edu"}, {"address": "Stanford University", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu"}, {"address": "University of Michigan", "lat": "42.29421420", "lng": "-83.71003894", "type": "edu"}, {"address": "University of Texas at Arlington", "lat": "32.72836830", "lng": "-97.11201835", "type": "edu"}], "year": 2014, "pdf": "http://pdfs.semanticscholar.org/a075/782ea38167658fe28986755adddba7369b4f.pdf"}, {"id": "fdfd57d4721174eba288e501c0c120ad076cdca8", "title": "An Analysis of Action Recognition Datasets for Language and Vision Tasks", "addresses": [{"address": "University of Edinburgh", "lat": "55.94951105", "lng": "-3.19534913", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1704.07129.pdf"}, {"id": "a2af07176a38fe844b0e2fdf4abae65472628b38", "title": "Dog breed classification via landmarks", "addresses": [{"address": "University of Delaware", "lat": "39.68103280", "lng": "-75.75401840", "type": "edu"}], "year": 2014, "pdf": "https://doi.org/10.1109/ICIP.2014.7026060"}, {"id": "ef2e36daf429899bb48d80ce6804731c3f99bb85", "title": "Debnath, Banerjee, Namboodiri: Adapting Ransac-svm to Detect Outliers for Robust Classification", "addresses": [{"address": "Indian Institute of Technology Kanpur", "lat": "26.51318800", "lng": "80.23651945", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/f7bd/b4df0fb5b3ff9fa0ebfe7c2a9ddc34c09a5c.pdf"}, {"id": "9d422e2c318ab63e6b49c83053757b4636f8308b", "title": "Object localization in ImageNet by looking out of the window", "addresses": [{"address": "University of Edinburgh", "lat": "55.94951105", "lng": "-3.19534913", "type": "edu"}], "year": "2015", "pdf": "https://arxiv.org/pdf/1501.01181.pdf"}, {"id": "71f36c8e17a5c080fab31fce1ffea9551fc49e47", "title": "Predicting Failures of Vision Systems", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": 2014, "pdf": "http://openaccess.thecvf.com/content_cvpr_2014/papers/Zhang_Predicting_Failures_of_2014_CVPR_paper.pdf"}, {"id": "7caa3a74313f9a7a2dd5b4c2cd7f825d895d3794", "title": "Markov Chain Monte Carlo for Automated Face Image Analysis", "addresses": [{"address": "University of Basel", "lat": "47.56126510", "lng": "7.57529610", "type": "edu"}], "year": "2016", "pdf": "http://doi.org/10.1007/s11263-016-0967-5"}, {"id": "26c58e24687ccbe9737e41837aab74e4a499d259", "title": "Codemaps - Segment, Classify and Search Objects Locally", "addresses": [{"address": "University of Amsterdam", "lat": "52.35536550", "lng": "4.95016440", "type": "edu"}], "year": 2013, "pdf": "http://www.cv-foundation.org/openaccess/content_iccv_2013/papers/Li_Codemaps_-_Segment_2013_ICCV_paper.pdf"}, {"id": "1f9102f425f28552e477cf71af0846550f3f9ed9", "title": "Incremental Domain Adaptation of Deformable Part-based Models", "addresses": [{"address": "Universitat Aut\u00f2noma de Barcelona", "lat": "41.50078110", "lng": "2.11143663", "type": "edu"}], "year": 2014, "pdf": "http://pdfs.semanticscholar.org/63ba/ef71a57d9ea6764c2bc3907cb6596b7f294a.pdf"}, {"id": "50953b9a15aca6ef3351e613e7215abdcae1435e", "title": "Learning coarse-to-fine sparselets for efficient object detection and scene classification", "addresses": [{"address": "Northwestern Polytechnical University", "lat": "34.24691520", "lng": "108.91061982", "type": "edu"}], "year": 2015, "pdf": "http://www.cv-foundation.org/openaccess/content_cvpr_2015/ext/1B_007_ext.pdf"}, {"id": "a63104ad235f98bc5ee0b44fefbcdb49e32c205a", "title": "Has My Algorithm Succeeded? An Evaluator for Human Pose Estimators", "addresses": [{"address": "University of Oxford", "lat": "51.75345380", "lng": "-1.25400997", "type": "edu"}, {"address": "University of Edinburgh", "lat": "55.94951105", "lng": "-3.19534913", "type": "edu"}], "year": 2012, "pdf": "http://pdfs.semanticscholar.org/a631/04ad235f98bc5ee0b44fefbcdb49e32c205a.pdf"}, {"id": "f6e00d6430cbbaa64789d826d093f7f3e323b082", "title": "Visual Object Recognition", "addresses": [{"address": "RWTH Aachen University", "lat": "50.77917030", "lng": "6.06728733", "type": "edu"}, {"address": "University of Texas at Austin", "lat": "30.28415100", "lng": "-97.73195598", "type": "edu"}], "year": "2011", "pdf": "https://pdfs.semanticscholar.org/5255/490925aa1e01ac0b9a55e93ec8c82efc07b7.pdf"}, {"id": "ae5b2b449f59ae0f46f6a31ed4826d98241c394c", "title": "Accurate real-time people counting for crowded environments", "addresses": [{"address": "University of Florence", "lat": "43.77764260", "lng": "11.25976500", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/ae5b/2b449f59ae0f46f6a31ed4826d98241c394c.pdf"}, {"id": "0b9c5bfb4d8349bb3f6ddd6fb612b7f9657c93f8", "title": "Inverting and Visualizing Features for Object Detection", "addresses": [{"address": "MIT", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu"}], "year": 2012, "pdf": "http://pdfs.semanticscholar.org/0b9c/5bfb4d8349bb3f6ddd6fb612b7f9657c93f8.pdf"}, {"id": "2cd7821fcf5fae53a185624f7eeda007434ae037", "title": "Exploring the geo-dependence of human face appearance", "addresses": [{"address": "University of Kentucky", "lat": "38.03337420", "lng": "-84.50177580", "type": "edu"}], "year": 2014, "pdf": "http://cs.uky.edu/~jacobs/papers/islam2014faces.pdf"}, {"id": "45e616093a92e5f1e61a7c6037d5f637aa8964af", "title": "Fine-grained evaluation on face detection in the wild", "addresses": [{"address": "Chinese Academy of Sciences", "lat": "40.00447950", "lng": "116.37023800", "type": "edu"}], "year": 2015, "pdf": "http://www.cs.toronto.edu/~byang/papers/malf_fg15.pdf"}, {"id": "81825711c2aaa1b9d3ead1a300e71c4353a41382", "title": "End-to-end training of object class detectors for mean average precision", "addresses": [{"address": "University of Edinburgh", "lat": "55.94951105", "lng": "-3.19534913", "type": "edu"}], "year": "2016", "pdf": "https://arxiv.org/pdf/1607.03476.pdf"}, {"id": "488fff23542ff397cdb1ced64db2c96320afc560", "title": "Weakly supervised localization of novel objects using appearance transfer", "addresses": [{"address": "University of Manitoba", "lat": "49.80915360", "lng": "-97.13304179", "type": "edu"}], "year": 2015, "pdf": "http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/2B_106_ext.pdf"}, {"id": "02b1a5d4b113211198e9c66d51153eb63ca680e2", "title": "Scene Invariant Crowd Segmentation and Counting Using Scale-Normalized Histogram of Moving Gradients (HoMG)", "addresses": [{"address": "University of Waterloo", "lat": "43.47061295", "lng": "-80.54724732", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/02b1/a5d4b113211198e9c66d51153eb63ca680e2.pdf"}, {"id": "7d520f474f2fc59422d910b980f8485716ce0a3e", "title": "Designing Convolutional Neural Networks for Urban Scene Understanding", "addresses": [{"address": "Robotics Institute", "lat": "13.65450525", "lng": "100.49423171", "type": "edu"}, {"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": "2017", "pdf": "https://pdfs.semanticscholar.org/2128/4a9310a4b4c836b8dfb6af39c682b7348128.pdf"}, {"id": "50f6888d9a7edb746e43a78c682a57c7ef36765b", "title": "Near-duplicate keyframe retrieval by semi-supervised learning and nonrigid image matching", "addresses": [{"address": "Zhejiang University", "lat": "30.19331415", "lng": "120.11930822", "type": "edu"}, {"address": "Nanyang Technological University", "lat": "1.34841040", "lng": "103.68297965", "type": "edu"}, {"address": "Chinese University of Hong Kong", "lat": "22.42031295", "lng": "114.20788644", "type": "edu"}, {"address": "National University of Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu"}], "year": 2011, "pdf": "http://www.cse.cuhk.edu.hk/lyu/_media/paper/jkzhu_comccap.pdf?cache=cache&id=publications:journal2"}, {"id": "72a4390a6c3b2bc2c3e7d83fc1f99e65e6137573", "title": "Collective Activity Localization with Contextual Spatial Pyramid", "addresses": [{"address": "University of Tokyo", "lat": "35.90204480", "lng": "139.93622009", "type": "edu"}], "year": 2012, "pdf": "http://pdfs.semanticscholar.org/72a4/390a6c3b2bc2c3e7d83fc1f99e65e6137573.pdf"}, {"id": "d012f6d7fd45051adaff8da4ce0860de9f81d445", "title": "A Deep Multi-task Learning Approach to Skin Lesion Classification", "addresses": [{"address": "University of Rochester", "lat": "43.15769690", "lng": "-77.58829158", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1812.03527.pdf"}, {"id": "f678f31e7bb5eda34098b0fed608cfad5e372509", "title": "Discriminative Kernel Feature Extraction and Learning for Object Recognition and Detection", "addresses": [{"address": "Southeast University", "lat": "32.05752790", "lng": "118.78682252", "type": "edu"}], "year": "2015", "pdf": "https://pdfs.semanticscholar.org/f678/f31e7bb5eda34098b0fed608cfad5e372509.pdf"}, {"id": "07ba3c796244f76b5e6914246fd83b66d3b65c34", "title": "Real-time Human Detection based on Personness Estimation", "addresses": [{"address": "Yonsei University", "lat": "37.56004060", "lng": "126.93692480", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/07ba/3c796244f76b5e6914246fd83b66d3b65c34.pdf"}, {"id": "fe5c43aa19da5cbbf5a42e4697659875f7389b91", "title": "Tracking People in Broadcast Sports", "addresses": [{"address": "ETH Z\u00fcrich", "lat": "47.37645340", "lng": "8.54770931", "type": "edu"}], "year": 2010, "pdf": "http://pdfs.semanticscholar.org/fe5c/43aa19da5cbbf5a42e4697659875f7389b91.pdf"}]}
|
