1
|
{"id": "b5f2846a506fc417e7da43f6a7679146d99c5e96", "paper": {"paperId": "b5f2846a506fc417e7da43f6a7679146d99c5e96", "key": "ucf_101", "title": "UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild", "journal": "CoRR", "address": "", "country": "", "address_type": "", "lat": "", "lng": "", "pdf_link": "https://arxiv.org/pdf/1212.0402.pdf", "report_link": "papers/b5f2846a506fc417e7da43f6a7679146d99c5e96.html", "citation_count": 999, "citations_geocoded": 615, "citations_unknown": 384, "citations_empty": 73, "citations_pdf": 716, "citations_doi": 283, "name": "UCF101"}, "address": null, "citations": [["Exploiting spatial-temporal context for trajectory based action video retrieval", "School of Information Technologies, The University of Sydney, NSW, Australia", "University of Sydney", "University of Sydney", "USyd, Fisher Road, Camperdown, Sydney, NSW, 2006, Australia", "-33.88890695", "151.18943366", "edu", "", "Australia", "2017"], ["Learning Temporal Embeddings for Complex Video Analysis", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "United States", "2015"], ["Beyond Frame-level CNN: Saliency-Aware 3-D CNN With LSTM for Video Action Recognition", "University of Trento, Trento, Italy", "University of Trento", "University of Trento", "University of Trento, Via Giuseppe Verdi, Piedicastello, Trento, Territorio Val d'Adige, TN, TAA, 38122, Italia", "46.06588360", "11.11598940", "edu", "", "Italy", "2017"], ["Global Temporal Representation Based CNNs for Infrared Action Recognition", "School of Telecommunications Engineering, Xidian University, Xi\u2019an, China", "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"], ["Two-Stream convolutional nets for action recognition in untrimmed video", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "United States", "2015"], ["Actions ~ Transformations", "", "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"], ["A Review of Human Action Recognition in Video", "Science and Technology Department, Communication University of China, Beijing, China", "Communication University of China", "Communication University of China", "\u4e2d\u56fd\u4f20\u5a92\u5927\u5b66, \u671d\u9633\u8def, \u5b9a\u798f\u5e84, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100024, \u4e2d\u56fd", "39.91199955", "116.55189141", "edu", "", "China", "2018"], ["Representing Videos based on Scene Layouts for Recognizing Agent-in-Place Actions", "", "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"], ["TS-LSTM and temporal-inception: Exploiting spatiotemporal dynamics for activity recognition", "", "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", "2019"], ["Adaptive Exponential Smoothing for Online Filtering of Pixel Prediction Maps", "", "Nanyang Technological University", "Nanyang Technological University", "NTU, Faculty Avenue, Jurong West, Southwest, 637460, Singapore", "1.34841040", "103.68297965", "edu", "", "Singapore", "2015"], ["Towards Good Practices for Very Deep Two-Stream ConvNets", "", "Shenzhen Institutes of Advanced Technology", "Shenzhen Institutes of Advanced Technology", "\u4e2d\u56fd\u79d1\u5b66\u9662\u6df1\u5733\u5148\u8fdb\u6280\u672f\u7814\u7a76\u9662, 1068, \u79d1\u7814\u8def, \u6df1\u5733\u5927\u5b66\u57ce, \u4e09\u5751\u6751, \u5357\u5c71\u533a, \u6df1\u5733\u5e02, \u5e7f\u4e1c\u7701, 518000, \u4e2d\u56fd", "22.59805605", "113.98533784", "edu", "", "China", "2015"], ["Learning the Synthesizability of Dynamic Texture Samples", "", "ETH Zurich", "ETH Zurich", "R\u00e4mistrasse 101, 8092 Z\u00fcrich, Switzerland", "47.37631300", "8.54766990", "edu", "", "Switzerland", "2018"], ["Real-Time Action Recognition With Deeply Transferred Motion Vector CNNs", "Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China", "Shenzhen Institutes of Advanced Technology", "Shenzhen Institutes of Advanced Technology", "\u4e2d\u56fd\u79d1\u5b66\u9662\u6df1\u5733\u5148\u8fdb\u6280\u672f\u7814\u7a76\u9662, 1068, \u79d1\u7814\u8def, \u6df1\u5733\u5927\u5b66\u57ce, \u4e09\u5751\u6751, \u5357\u5c71\u533a, \u6df1\u5733\u5e02, \u5e7f\u4e1c\u7701, 518000, \u4e2d\u56fd", "22.59805605", "113.98533784", "edu", "", "China", "2018"], ["Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs", "", "Columbia University", "Columbia University", "Columbia University Medical Center, 630, West 168th Street, Washington Heights, Manhattan, Manhattan Community Board 12, New York County, NYC, New York, 10031, USA", "40.84198360", "-73.94368971", "edu", "", "United States", "2016"], ["Representing Sets of Instances for Visual Recognition", "", "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", "2016"], ["Featureless: Bypassing feature extraction in action categorization", "", "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"], ["Pose-Based Two-Stream Relational Networks for Action Recognition in 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"], ["Recognizing Actions in Wearable-Camera Videos by Training Classifiers on Fixed-Camera Videos", "University of South Carolina, Columbia, SC, USA", "University of South Carolina", "University of South Carolina", "University of South Carolina, Wheat Street, Columbia, Richland County, South Carolina, 29205, USA", "33.99282980", "-81.02685168", "edu", "", "United States", "2018"], ["ActionVLAD: Learning Spatio-Temporal Aggregation for Action Classification", "", "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", "2017"], ["Multimodal Representation of Advertisements Using Segment-level Autoencoders", "University of Southern California, Los Angeles, CA, USA", "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"], ["Liquid Pouring Monitoring via Rich Sensory Inputs", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "United States", "2018"], ["Sparse 3D convolutional neural networks", "", "University of Warwick", "University of Warwick", "University of Warwick, University Road, Kirby Corner, Cannon Park, Coventry, West Midlands Combined Authority, West Midlands, England, CV4 7AL, UK", "52.37931310", "-1.56042520", "edu", "", "United Kingdom", "2015"], ["Recognizing Micro-Actions and Reactions from Paired Egocentric Videos", "", "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"], ["Review of Action Recognition and Detection Methods", "", "York University", "York University", "York University, Keele Campus, Campus Walk, North York, Toronto, Ontario, M3J 2S5, Canada", "43.77439110", "-79.50481085", "edu", "", "Canada", "2016"], ["Towards Scalable Visual Navigation of Micro Aerial Vehicles", "", "Carnegie Mellon University Silicon Valley", "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"], ["They are Not Equally Reliable: Semantic Event Search Using Differentiated Concept Classifiers", "", "Carnegie Mellon University Silicon Valley", "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"], ["Automatic Understanding of Image and 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", "2017"], ["A spatiotemporal model with visual attention for video classification", "", "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"], ["Secure Access Control and Large Scale Robust Representation for Online Multimedia Event Detection", "", "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", "2014"], ["Gradient Boundary Histograms for Action Recognition", "", "University of Ottawa", "University of Ottawa", "University of Ottawa, 1, Stewart Street, Byward Market, Lowertown, Rideau-Vanier, Ottawa, Ontario, K1N 6N5, Canada", "45.42580475", "-75.68740118", "edu", "", "Canada", "2015"], ["Common Action Discovery and Localization in Unconstrained Videos", "", "Nanyang Technological University", "Nanyang Technological University", "NTU, Faculty Avenue, Jurong West, Southwest, 637460, Singapore", "1.34841040", "103.68297965", "edu", "", "Singapore", "2017"], ["A Spatio-temporal Feature Based on Triangulation of Dense SURF", "", "University of Electro-Communications", "The University of Electro-Communications", "\u96fb\u6c17\u901a\u4fe1\u5927\u5b66, \u7532\u5dde\u8857\u9053, \u8abf\u5e03\u5e02, \u6771\u4eac\u90fd, \u95a2\u6771\u5730\u65b9, 182-0026, \u65e5\u672c", "35.65729570", "139.54255868", "edu", "", "Japan", "2013"], ["Video Classification via Relational Feature Encoding Networks", "Sun Yat-sen University & Sensetime, Guangzhou, China", "Sun Yat-sen University & Sensetime", "Sun Yat-sen University & Sensetime, Guangzhou, China", "135 Xingang W Rd, BinJiang Lu, Haizhu Qu, Guangzhou Shi, Guangdong Sheng, China", "23.09653840", "113.29888300", "edu", "", "China", "2017"], ["Visual Pattern Discovery and Recognition", "Nanyang Technological University, Singapore, Singapore", "Nanyang Technological University", "Nanyang Technological University", "NTU, Faculty Avenue, Jurong West, Southwest, 637460, Singapore", "1.34841040", "103.68297965", "edu", "", "Singapore", "2017"], ["Let's Dance: Learning From Online Dance Videos", "", "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"], ["Domain Adaptation in Computer Vision Applications", "Naver Labs Europe, Meylan, France", "Naver Labs Europe, Meylan, France", "Naver Labs Europe, Meylan, France", "6 Chemin de Maupertuis, 38240 Meylan, France", "45.21739890", "5.79213490", "edu", "", "France", "2017"], ["Residue boundary histograms for action recognition in the compressed domain", "The University of New South Wales, Australia", "University of New South Wales", "University of New South Wales", "UNSW, International Square, UNSW, Kensington, Bay Gardens, Sydney, Randwick, NSW, 2033, Australia", "-33.91758275", "151.23124025", "edu", "", "Australia", "2015"], ["Informed Democracy: Voting-based Novelty Detection for Action Recognition", "", "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", "2018"], ["Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification", "", "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"], ["Webly-Supervised Video Recognition by Mutually Voting for Relevant Web Images and Web Video Frames", "", "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", "2016"], ["Temporal Variance Analysis for Action Recognition", "School of Engineering, The University of Edinburgh, Edinburgh, U.K.", "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", "2015"], ["DeepMon: Mobile GPU-based Deep Learning Framework for Continuous Vision Applications", "Singapore Management University, Singapore, Singapore", "Singapore Management University", "Singapore Management University", "Singapore Management University, Fort Canning Tunnel, Clarke Quay, City Hall, Singapore, Central, 178895, Singapore", "1.29500195", "103.84909214", "edu", "", "Singapore", "2017"], ["Beyond Gaussian Pyramid: Multi-skip Feature Stacking for action recognition", "", "Carnegie Mellon University Silicon Valley", "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"], ["Online Action Tube Detection via Resolving the Spatio-temporal Context Pattern", "Peking University, Shenzhen, 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"], ["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"], ["Deep Action- and Context-Aware Sequence Learning for Activity Recognition and Anticipation", "", "Australian National University", "Australian National University", "Canberra ACT 0200, Australia", "-35.27769990", "149.11852700", "edu", "", "Australia", "2016"], ["A Joint Sequence Fusion Model for Video Question Answering and Retrieval", "", "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"], ["A Two-Layer Representation For Large-Scale Action Recognition", "", "University of California", "University of California", "Berkeley, CA, USA", "37.87189920", "-122.25853990", "edu", "", "United States", "2013"], ["Video Jigsaw: Unsupervised Learning of Spatiotemporal Context for Video Action Recognition", "", "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"], ["Scalable Online Annotation & Object Localisation For Broadcast Media Production", "", "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", "2016"], ["Recent advances in video-based human action recognition using deep learning: A review", "School of Software, University of Technology Sydney, New South Wales, Australia", "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", "2017"], ["Fast action detection with web camera", "Chongqing Key Laboratory of Signal and Information Processing, Chongqing University of Posts and Telecommunications, Chongqing, China", "Chongqing University of Posts and Telecommunications", "Chongqing University of Posts and Telecommunications", "\u91cd\u5e86\u90ae\u7535\u5927\u5b66, \u5d07\u6587\u8def, \u6e1d\u4e2d\u533a, \u9ec4\u6877\u57ad, \u91cd\u5e86\u5e02\u4e2d\u5fc3, \u5357\u5cb8\u533a (Nan'an), \u91cd\u5e86\u5e02, 400065, \u4e2d\u56fd", "29.53570460", "106.60482474", "edu", "", "China", "2015"], ["Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study", "", "Texas A&M University", "Texas A&M University", "Texas A&M University, Horticulture Street, Park West, College Station, Brazos County, Texas, 77841, USA", "30.61083650", "-96.35212800", "edu", "", "United States", "2018"], ["Supervised Recurrent Hashing for Large Scale Video Retrieval", "Shanghai Jiao Tong University, Shanghai, 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", "2016"], ["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"], ["Sparse Deep Transfer Learning for Convolutional Neural Network", "", "Shenzhen Institutes of Advanced Technology", "Shenzhen Institutes of Advanced Technology", "\u4e2d\u56fd\u79d1\u5b66\u9662\u6df1\u5733\u5148\u8fdb\u6280\u672f\u7814\u7a76\u9662, 1068, \u79d1\u7814\u8def, \u6df1\u5733\u5927\u5b66\u57ce, \u4e09\u5751\u6751, \u5357\u5c71\u533a, \u6df1\u5733\u5e02, \u5e7f\u4e1c\u7701, 518000, \u4e2d\u56fd", "22.59805605", "113.98533784", "edu", "", "China", "2017"], ["Automatic Construction of Action Datasets Using Web Videos with Density-Based Cluster Analysis and Outlier Detection", "", "University of Electro-Communications", "The University of Electro-Communications", "\u96fb\u6c17\u901a\u4fe1\u5927\u5b66, \u7532\u5dde\u8857\u9053, \u8abf\u5e03\u5e02, \u6771\u4eac\u90fd, \u95a2\u6771\u5730\u65b9, 182-0026, \u65e5\u672c", "35.65729570", "139.54255868", "edu", "", "Japan", "2015"], ["Deep Alternative Neural Network: Exploring Contexts as Early as Possible for Action Recognition", "", "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"], ["Human Action Adverb Recognition: ADHA Dataset and A Three-Stream Hybrid Model", "", "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"], ["Content-Aware Proactive Caching for Backhaul Offloading in Cellular Network", "Singapore University of Technology and Design, Singapore", "Singapore University of Technology and Design", "Singapore University of Technology and Design", "Singapore University of Technology and Design, Simpang Bedok, Changi Business Park, Southeast, 486041, Singapore", "1.34021600", "103.96508900", "edu", "", "Singapore", "2018"], ["What will Happen Next? Forecasting Player Moves in Sports Videos", "", "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"], ["Semantic Pooling for Complex Event Analysis in Untrimmed Videos", "Machine Learning Department, Carnegie Mellon University, Pittsburgh, PA", "Carnegie Mellon University Silicon Valley", "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"], ["MLtuner: System Support for Automatic Machine Learning Tuning", "", "Carnegie Mellon University Silicon Valley", "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"], ["Learning local feature aggregation functions with backpropagation", "", "Aristotle University of Thessaloniki", "Aristotle University of Thessaloniki", "\u0391\u03c1\u03b9\u03c3\u03c4\u03bf\u03c4\u03ad\u03bb\u03b5\u03b9\u03bf \u03a0\u03b1\u03bd\u03b5\u03c0\u03b9\u03c3\u03c4\u03ae\u03bc\u03b9\u03bf \u0398\u03b5\u03c3\u03c3\u03b1\u03bb\u03bf\u03bd\u03af\u03ba\u03b7\u03c2, \u0395\u03b3\u03bd\u03b1\u03c4\u03af\u03b1, \u03a3\u03b1\u03c1\u03ac\u03bd\u03c4\u03b1 \u0395\u03ba\u03ba\u03bb\u03b7\u03c3\u03af\u03b5\u03c2, \u0395\u03c5\u03b1\u03b3\u03b3\u03b5\u03bb\u03af\u03c3\u03c4\u03c1\u03b9\u03b1, \u0398\u03b5\u03c3\u03c3\u03b1\u03bb\u03bf\u03bd\u03af\u03ba\u03b7, \u0394\u03ae\u03bc\u03bf\u03c2 \u0398\u03b5\u03c3\u03c3\u03b1\u03bb\u03bf\u03bd\u03af\u03ba\u03b7\u03c2, \u03a0\u03b5\u03c1\u03b9\u03c6\u03b5\u03c1\u03b5\u03b9\u03b1\u03ba\u03ae \u0395\u03bd\u03cc\u03c4\u03b7\u03c4\u03b1 \u0398\u03b5\u03c3\u03c3\u03b1\u03bb\u03bf\u03bd\u03af\u03ba\u03b7\u03c2, \u03a0\u03b5\u03c1\u03b9\u03c6\u03ad\u03c1\u03b5\u03b9\u03b1 \u039a\u03b5\u03bd\u03c4\u03c1\u03b9\u03ba\u03ae\u03c2 \u039c\u03b1\u03ba\u03b5\u03b4\u03bf\u03bd\u03af\u03b1\u03c2, \u039c\u03b1\u03ba\u03b5\u03b4\u03bf\u03bd\u03af\u03b1 - \u0398\u03c1\u03ac\u03ba\u03b7, 54124, \u0395\u03bb\u03bb\u03ac\u03b4\u03b1", "40.62984145", "22.95889350", "edu", "", "Greece", "2017"], ["Video Forecasting with Forward-Backward-Net: Delving Deeper into Spatiotemporal Consistency", "York University, Toronto, ON, Canada", "York University", "York University", "York University, Keele Campus, Campus Walk, North York, Toronto, Ontario, M3J 2S5, Canada", "43.77439110", "-79.50481085", "edu", "", "Canada", "2018"], ["MMA: a multi-view and multi-modality benchmark dataset for human action recognition", "Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology, Tianjin University of Technology, Tianjin, China", "Tianjin University of Technology", "Tianjin University of Technology, China", "Xiqing, China", "39.06100400", "117.14202300", "edu", "", "China", "2018"], ["Fusing Multi-Stream Deep Networks for Video Classification", "", "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", "2015"], ["Non-local NetVLAD Encoding for Video Classification", "", "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"], ["Pose Guided Human Video Generation", "", "Carnegie Mellon University Silicon Valley", "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"], ["Large-Scale YouTube-8M Video Understanding with Deep Neural Networks", "", "Institute for System Programming, Moscow", "Institute for System Programming", "\u0418\u0421\u041f \u0420\u0410\u041d, 25, \u0443\u043b\u0438\u0446\u0430 \u0410\u043b\u0435\u043a\u0441\u0430\u043d\u0434\u0440\u0430 \u0421\u043e\u043b\u0436\u0435\u043d\u0438\u0446\u044b\u043d\u0430, \u0428\u0432\u0438\u0432\u0430\u044f \u0433\u043e\u0440\u043a\u0430, \u0422\u0430\u0433\u0430\u043d\u0441\u043a\u0438\u0439 \u0440\u0430\u0439\u043e\u043d, \u0426\u0435\u043d\u0442\u0440\u0430\u043b\u044c\u043d\u044b\u0439 \u0430\u0434\u043c\u0438\u043d\u0438\u0441\u0442\u0440\u0430\u0442\u0438\u0432\u043d\u044b\u0439 \u043e\u043a\u0440\u0443\u0433, \u041c\u043e\u0441\u043a\u0432\u0430, \u0426\u0424\u041e, 109004, \u0420\u0424", "55.74498810", "37.66450421", "edu", "", "Russia", "2017"], ["An Uncertain Future: Forecasting from Static Images using Variational Autoencoders", "", "Carnegie Mellon University", "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "40.44416190", "-79.94272826", "edu", "", "United States", "2016"], ["Exploring multimodal video representation for action recognition", "Hasso Plattner Institute, University of Potsdam, Prof.-Dr.-Helmert-Str. 2-3, 14482, Germany", "University of Potsdam", "Hasso Plattner Institute, University of Potsdam, Prof.-Dr.-Helmert-Str. 2-3, 14482, Germany", "Prof.-Dr.-Helmert-Stra\u00dfe 2-3, 14482 Potsdam, Germany", "52.39399650", "13.13336570", "edu", "", "Germany", "2016"], ["Data driven adaptation for QoS aware embedded vision systems", "Computer Science and Engineering, Pennsylvania State University, PA, USA SiliconScapes, LLC, PA, USA", "Pennsylvania State University", "Pennsylvania State University", "Old Main, State College, PA 16801, USA", "40.79821330", "-77.85990840", "edu", "", "United States", "2014"], ["Temporal Attentive Network for Action Recognition", "School of Information and Electronics, Beijing Institute of Technology, 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"], ["Semi-Supervised Image-to-Video Adaptation for Video Action Recognition", "School of Computer Science and Technology, Tianjin University, Tianjin, China", "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"], ["Action Recognition With Coarse-to-Fine Deep Feature Integration and Asynchronous Fusion", "", "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"], ["Squeeze-and-Excitation on Spatial and Temporal Deep Feature Space for Action Recognition", "", "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"], ["Joint classification of actions with matrix completion", "Vision Lab, School of Engineering and Physical Sciences, Heriot-Watt University, Edinburgh, United Kingdom", "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", "2015"], ["Harvesting Motion Patterns in Still Images from the Internet", "", "University of California", "University of California", "Berkeley, CA, USA", "37.87189920", "-122.25853990", "edu", "", "United States", "2014"], ["Teaching Machines to Understand Baseball Games: Large-Scale Baseball Video Database for Multiple Video Understanding Tasks", "", "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", "2018"], ["Efficient Online Spatio-Temporal Filtering for Video Event 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"], ["End-to-end Video-level Representation Learning for Action Recognition", "", "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"], ["Multimodal Keyless Attention Fusion 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"], ["Graph Distillation for Action Detection with Privileged Information", "", "Google", "Google, Inc.", "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "37.42199990", "-122.08405750", "company", "Google, Mountain View, CA", "United States", "2017"], ["The 2013 SESAME Multimedia Event Detection and Recounting System", "", "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", "2014"], ["PersonRank: Detecting Important People in Images", "", "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"], ["Handcrafted Local Features are Convolutional Neural Networks", "", "Carnegie Mellon University Silicon Valley", "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"], ["Deep Discriminative Model for Video Classification", "", "University of Oulu", "University of Oulu", "Oulun yliopisto, Biologintie, Linnanmaa, Oulu, Oulun seutukunta, Pohjois-Pohjanmaa, Pohjois-Suomen aluehallintovirasto, Pohjois-Suomi, Manner-Suomi, 90540, Suomi", "65.05921570", "25.46632601", "edu", "", "Finland", "2018"], ["Hybrid Super Vector with Improved Dense Trajectories for Action Recognition", "", "Chinese University of Hong Kong", "Chinese University of Hong Kong", "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "22.41626320", "114.21093180", "edu", "", "China", "2013"], ["Temporal Localization of Fine-Grained Actions in Videos by Domain Transfer from Web Images", "", "Google", "Google, Inc.", "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "37.42199990", "-122.08405750", "company", "Google, Mountain View, CA", "United States", "2015"], ["Deep Action Parsing in Videos With Large-Scale Synthesized Data", "Inception Institute of Artificial Intelligence, Abu Dhabi, United Arab Emirates", "Inception Institute of Artificial Intelligence, Abu Dhabi, UAE", "Inception Institute of Artificial Intelligence, Abu Dhabi, UAE", "Abu Dhabi - United Arab Emirates", "24.45388400", "54.37734380", "company", "", "United Arab Emirates", "2018"], ["CSVideoNet: A Real-Time End-to-End Learning Framework for High-Frame-Rate Video Compressive Sensing", "", "Arizona State University", "Arizona State University", "Arizona State University Polytechnic campus, East Texas Avenue, Mesa, Maricopa County, Arizona, 85212, USA", "33.30715065", "-111.67653157", "edu", "", "United States", "2018"], ["Continuous Video to Simple Signals for Swimming Stroke Detection with Convolutional Neural Networks", "", "Australian Institute of Sport", "Australian Institute of Sport", "Australian Institute of Sport, Glenn McGrath Street, Bruce, Belconnen, Australian Capital Territory, 2617, Australia", "-35.24737535", "149.10445427", "edu", "", "Australia", "2017"], ["Gated Transfer Network for Transfer Learning", "", "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", "2018"], ["Collaborative Multifeature Fusion for Transductive Spectral Learning", "School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore", "Nanyang Technological University", "Nanyang Technological University", "NTU, Faculty Avenue, Jurong West, Southwest, 637460, Singapore", "1.34841040", "103.68297965", "edu", "", "Singapore", "2015"], ["Eigen Evolution Pooling for Human Action Recognition", "", "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", "2017"], ["Learning Representative Deep Features for Image Set Analysis", "National Laboratory of Pattern Recognition, CAS Center for Excellence in Brain Science and Intelligence Technology, 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", "2015"], ["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"], ["Detect-and-Track: Efficient Pose Estimation in Videos", "", "Facebook", "Facebook", "250 Bryant St, Mountain View, CA 94041, USA", "37.39367170", "-122.08072620", "company", "Facebook, Mountain View, CA", "United States", "2017"], ["Interaction-aware Spatio-temporal Pyramid Attention Networks for Action Classification", "", "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"], ["Actor-Action Semantic Segmentation with Grouping Process Models", "", "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"], ["T-RECS: Training for Rate-Invariant Embeddings by Controlling Speed for Action Recognition", "", "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"], ["Keep it accurate and diverse: Enhancing action recognition performance by ensemble learning", "", "University of Barcelona", "University of Barcelona", "Universitat de Barcelona, Carrer de la Diputaci\u00f3, l'Antiga Esquerra de l'Eixample, Eixample, Barcelona, BCN, CAT, 08013, Espa\u00f1a", "41.38689130", "2.16352385", "edu", "", "Spain", "2015"], ["Efficient object feature selection for action recognition", "Nanyang Technological University, Singapore", "Nanyang Technological University", "Nanyang Technological University", "NTU, Faculty Avenue, Jurong West, Southwest, 637460, Singapore", "1.34841040", "103.68297965", "edu", "", "Singapore", "2016"], ["Scenes-Objects-Actions: A Multi-task, Multi-label Video Dataset", "", "Dartmouth College", "Dartmouth College", "Dartmouth College, Tuck Mall, Hanover, Grafton County, New Hampshire, 03755, USA", "43.70479270", "-72.29259090", "edu", "", "United States", "2018"], ["Attention Clusters: Purely Attention Based Local Feature Integration 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", "2017"], ["An Ensemble of VGG Networks for Video-Based Facial Expression Recognition", "Beijing Key Laboratory of Human-Computer Interaction, Institute of Software, Chinese Academy of Sciences, University of 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"], ["Good Practices for Learning to Recognize Actions Using FV and VLAD", "National Key Laboratory for Novel Software Technology, 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", "2016"], ["Exploring Fisher vector and deep networks for action spotting", "", "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"], ["The Many Shades of Negativity", "University of Trento, Trento, Italy", "University of Trento", "University of Trento", "University of Trento, Via Giuseppe Verdi, Piedicastello, Trento, Territorio Val d'Adige, TN, TAA, 38122, Italia", "46.06588360", "11.11598940", "edu", "", "Italy", "2017"], ["Evaluation of LC-KSVD on UCF 101 Action Dataset", "", "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", ""], ["3D convolutional neural network with multi-model framework for action recognition", "The Graduate Center, USA", "The Graduate Center, USA", "The Graduate Center, USA", "365 5th Ave, New York, NY 10016, USA", "40.74844900", "-73.98349160", "edu", "", "United States", "2017"], ["Confidence-based Deep Multimodal Fusion for Activity Recognition", "School of Integrated Technology, Yonsei University. Incheon, 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", "2018"], ["Dual Viewpoint Passenger State Classification Using 3D CNNs", "School of Engineering, University of Warwick, Coventry, UK", "University of Warwick", "University of Warwick", "University of Warwick, University Road, Kirby Corner, Cannon Park, Coventry, West Midlands Combined Authority, West Midlands, England, CV4 7AL, UK", "52.37931310", "-1.56042520", "edu", "", "United Kingdom", "2018"], ["SLAC: A Sparsely Labeled Dataset for Action Classification and Localization", "", "MIT", "Massachusetts Institute", "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "42.35839610", "-71.09567788", "edu", "", "United States", "2017"], ["Unsupervised Alignment of Actions in Video with Text Descriptions", "", "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", "2016"], ["Convolutional neural networks for the analysis of broadcasted tennis games", "", "University of Crete", "University of Crete", "House of Europe, \u039c\u03b1\u03ba\u03b5\u03b4\u03bf\u03bd\u03af\u03b1\u03c2, \u03a1\u03ad\u03b8\u03c5\u03bc\u03bd\u03bf, \u0394\u03ae\u03bc\u03bf\u03c2 \u03a1\u03b5\u03b8\u03cd\u03bc\u03bd\u03b7\u03c2, \u03a0\u03b5\u03c1\u03b9\u03c6\u03b5\u03c1\u03b5\u03b9\u03b1\u03ba\u03ae \u0395\u03bd\u03cc\u03c4\u03b7\u03c4\u03b1 \u03a1\u03b5\u03b8\u03cd\u03bc\u03bd\u03bf\u03c5, \u03a0\u03b5\u03c1\u03b9\u03c6\u03ad\u03c1\u03b5\u03b9\u03b1 \u039a\u03c1\u03ae\u03c4\u03b7\u03c2, \u039a\u03c1\u03ae\u03c4\u03b7, 930100, \u0395\u03bb\u03bb\u03ac\u03b4\u03b1", "35.37130240", "24.47544080", "edu", "", "Greece", "2018"], ["Fast Supervised LDA for Discovering Micro-Events in Large-Scale Video Datasets", "", "Aristotle University of Thessaloniki", "Aristotle University of Thessaloniki", "\u0391\u03c1\u03b9\u03c3\u03c4\u03bf\u03c4\u03ad\u03bb\u03b5\u03b9\u03bf \u03a0\u03b1\u03bd\u03b5\u03c0\u03b9\u03c3\u03c4\u03ae\u03bc\u03b9\u03bf \u0398\u03b5\u03c3\u03c3\u03b1\u03bb\u03bf\u03bd\u03af\u03ba\u03b7\u03c2, \u0395\u03b3\u03bd\u03b1\u03c4\u03af\u03b1, \u03a3\u03b1\u03c1\u03ac\u03bd\u03c4\u03b1 \u0395\u03ba\u03ba\u03bb\u03b7\u03c3\u03af\u03b5\u03c2, \u0395\u03c5\u03b1\u03b3\u03b3\u03b5\u03bb\u03af\u03c3\u03c4\u03c1\u03b9\u03b1, \u0398\u03b5\u03c3\u03c3\u03b1\u03bb\u03bf\u03bd\u03af\u03ba\u03b7, \u0394\u03ae\u03bc\u03bf\u03c2 \u0398\u03b5\u03c3\u03c3\u03b1\u03bb\u03bf\u03bd\u03af\u03ba\u03b7\u03c2, \u03a0\u03b5\u03c1\u03b9\u03c6\u03b5\u03c1\u03b5\u03b9\u03b1\u03ba\u03ae \u0395\u03bd\u03cc\u03c4\u03b7\u03c4\u03b1 \u0398\u03b5\u03c3\u03c3\u03b1\u03bb\u03bf\u03bd\u03af\u03ba\u03b7\u03c2, \u03a0\u03b5\u03c1\u03b9\u03c6\u03ad\u03c1\u03b5\u03b9\u03b1 \u039a\u03b5\u03bd\u03c4\u03c1\u03b9\u03ba\u03ae\u03c2 \u039c\u03b1\u03ba\u03b5\u03b4\u03bf\u03bd\u03af\u03b1\u03c2, \u039c\u03b1\u03ba\u03b5\u03b4\u03bf\u03bd\u03af\u03b1 - \u0398\u03c1\u03ac\u03ba\u03b7, 54124, \u0395\u03bb\u03bb\u03ac\u03b4\u03b1", "40.62984145", "22.95889350", "edu", "", "Greece", "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"], ["Video Fill In the Blank Using LR/RL LSTMs with Spatial-Temporal Attentions", "", "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", "2017"], ["Improving human action recognitionby temporal attention", "Institute for Computational and Mathematical Engineering, Stanford University", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "United States", "2017"], ["Unsupervised Video Hashing via Deep Neural Network", "School of Computer Science and Engineering, Nanjing University of Science and Technology, 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"], ["One-shot Action Localization by Learning Sequence Matching Network", "", "Australian National University", "Australian National University", "Canberra ACT 0200, Australia", "-35.27769990", "149.11852700", "edu", "", "Australia", ""], ["Temporal action localization with two-stream segment-based RNN", "Key Laboratory of System Control and Information Processing MOE, Department of Automation, Shanghai Jiao Tong University", "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", "2017"], ["Open-Domain Audio-Visual Speech Recognition: A Deep Learning Approach", "", "Carnegie Mellon University Silicon Valley", "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"], ["Learning Person Trajectory Representations for Team Activity Analysis", "", "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"], ["Joint Normalization and Dimensionality Reduction on Grassmannian: A Generalized Perspective", "Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, 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"], ["Recurrent Residual Module for Fast Inference in Videos", "", "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"], ["Exploring Temporal Preservation Networks for Precise Temporal Action Localization", "", "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", "2018"], ["A Pursuit of Temporal Accuracy in General Activity Detection", "", "Computer Vision Laboratory, ETH Zurich, Switzerland", "Computer Vision Laboratory, ETH Zurich, Switzerland", "Sternwartstrasse 7, 8092 Z\u00fcrich, Switzerland", "47.37723980", "8.55216180", "edu", "", "Malaysia", "2017"], ["Video Segmentation by Non-Local Consensus voting", "", "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", "2014"], ["Harnessing the Deep Net Object Models for Enhancing Human Action Recognition", "", "Australian National University", "Australian National University", "Canberra ACT 0200, Australia", "-35.27769990", "149.11852700", "edu", "", "Australia", "2015"], ["Spatio-Temporal Action Detection with Cascade Proposal and Location Anticipation", "", "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"], ["MiCT: Mixed 3D/2D Convolutional Tube for Human Action Recognition", "", "Microsoft Research Asia", "Microsoft Research Asia", "1 Memorial Dr, Cambridge, MA 02142, USA", "42.36142560", "-71.08120920", "company", "", "United States", ""], ["Late fusion and calibration for multimedia event detection using few examples", "University of Southern California, Los Angeles, USA", "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", "2014"], ["TraMNet - Transition Matrix Network for Efficient Action Tube Proposals", "", "Oxford Brookes University", "Oxford Brookes University", "Oxford Brookes University, Headington Road, Headington, Oxford, Oxon, South East, England, OX3 0BL, UK", "51.75552050", "-1.22615970", "edu", "", "United Kingdom", "2018"], ["Gaze-Assisted Multi-Stream Deep Neural Network for Action Recognition", "School of Electronic Engineering, 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"], ["Dynamically encoded actions based on spacetime saliency", "", "York University", "York University", "York University, Keele Campus, Campus Walk, North York, Toronto, Ontario, M3J 2S5, Canada", "43.77439110", "-79.50481085", "edu", "", "Canada", "2015"], ["Adding New Tasks to a Single Network with Weight Trasformations using Binary Masks", "", "Sapienza University of Rome", "Sapienza University of Rome", "Piazzale Aldo Moro, 5, 00185 Roma RM, Italy", "41.90376260", "12.51443840", "edu", "", "Italy", "2018"], ["Discriminative-Element-Aware Sparse Representation for Action Recognition", "Nanjing University of Science and Technology, Xiaolingwei, Xuanwu, 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", "2016"], ["Multi-view Super Vector for Action Recognition", "", "Chinese University of Hong Kong", "Chinese University of Hong Kong", "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "22.41626320", "114.21093180", "edu", "", "China", "2014"], ["Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset", "", "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"], ["Diversity encouraging ensemble of convolutional networks for high performance action recognition", "CAS Center for Excellence in Brain Science and Intelligence Technology; National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences; University of Chinese Academy of Sciences, Beijing, China", "Chinese Academy of Science", "Chinese Academy of Science", "52 Sanlihe Rd, Xicheng Qu, Beijing Shi, China", "39.91063270", "116.33563210", "edu", "", "China", "2017"], ["VideoCapsuleNet: A Simplified Network for Action Detection", "", "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"], ["Computer Vision \u2013 ECCV 2016 Workshops", "Microsoft Research Asia, Beijing, China", "Microsoft Research Asia", "Microsoft Research Asia", "1 Memorial Dr, Cambridge, MA 02142, USA", "42.36142560", "-71.08120920", "company", "", "United States", "2016"], ["TaiChi: A Fine-Grained Action Recognition Dataset", "East China Normal University, Shanghai, China", "East China Normal University", "East China Normal University", "\u534e\u4e1c\u5e08\u8303\u5927\u5b66, 3663, \u4e2d\u5c71\u5317\u8def, \u66f9\u5bb6\u6e21, \u666e\u9640\u533a, \u666e\u9640\u533a (Putuo), \u4e0a\u6d77\u5e02, 200062, \u4e2d\u56fd", "31.22849230", "121.40211389", "edu", "", "China", "2017"], ["Towards Universal Representation for Unseen Action Recognition", "", "Newcastle University", "Newcastle University", "Newcastle University, Claremont Walk, Haymarket, Newcastle upon Tyne, Tyne and Wear, North East England, England, NE1 7RU, UK", "54.98023235", "-1.61452627", "edu", "", "United Kingdom", "2018"], ["Visual to Sound: Generating Natural Sound for Videos in the Wild", "", "University of North Carolina at Chapel Hill", "University of North Carolina at Chapel Hill", "University of North Carolina at Chapel Hill, East Cameron Avenue, Chapel Hill, Orange County, North Carolina, 27514, USA", "35.91139710", "-79.05045290", "edu", "", "United States", "2017"], ["Using phase instead of optical flow for action recognition", "", "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"], ["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"], ["Deep multi-view robust representation learning", "School of Electronics Engineering and Computer Science, Peking University, Beijing 100871, 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", "2017"], ["Large-Scale Mapping of Human Activity using Geo-Tagged Videos", "University of Southern California", "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"], ["Lattice Long Short-Term Memory for Human Action Recognition", "", "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", "2017"], ["Learning correlations for human action recognition in videos", "Key Laboratory of Embedded System and Service Computing, Ministry of Education, Tongji University, Shanghai, People\u2019s Republic of 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"], ["Temporal Action Localization by Structured Maximal Sums", "", "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"], ["Unsupervised Domain Adaptation for Zero-Shot 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", "2015"], ["Simple, Efficient and Effective Encodings of Local Deep Features for Video Action Recognition", "University of Trento, Trento, Italy", "University of Trento", "University of Trento", "University of Trento, Via Giuseppe Verdi, Piedicastello, Trento, Territorio Val d'Adige, TN, TAA, 38122, Italia", "46.06588360", "11.11598940", "edu", "", "Italy", "2017"], ["Video Frame Synthesis Using Deep Voxel Flow", "", "Google", "Google, Inc.", "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "37.42199990", "-122.08405750", "company", "Google, Mountain View, CA", "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"], ["Learning Semantic-Aligned Action Representation", "Department of Electrical Engineering, Shanghai Jiao Tong University, Shanghai, 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"], ["Leveraging Inexpensive Supervision Signals for Visual Learning", "", "Carnegie Mellon University Silicon Valley", "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"], ["Multi-fiber Networks for Video Recognition", "", "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"], ["Morph: Flexible Acceleration for 3D CNN-based Video Understanding", "", "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"], ["DYAN: A Dynamical Atoms-Based Network for Video Prediction", "", "Electrical and Computer Engineering", "Electrical and Computer Engineering", "Electrical and Computer Engineering, Boston Avenue, South Overton, Lubbock, Lubbock County, Texas, 79409, USA", "33.58667840", "-101.87539204", "edu", "", "United States", "2018"], ["Recent Advances in Zero-Shot Recognition: Toward Data-Efficient Understanding of Visual Content", "Visual Computation, Queen Mary University, London, United Kingdom", "Queen Mary University", "Queen Mary University", "Universitatea Cre\u0219tin\u0103 Partium - Cl\u0103direa Sulyok, 27, Strada Prim\u0103riei, Ora\u0219ul Nou, Oradea, Bihor, 410209, Rom\u00e2nia", "47.05702220", "21.92270900", "edu", "", "Romania", "2018"], ["Informativeness of Degraded Data in Training a Classification System", "Space and Naval Warfare Systems Center Pacific, San Diego, CA, 92152, United States", "Space and Naval Warfare Systems Center Pacific, San Diego, CA", "Space and Naval Warfare Systems Center Pacific, San Diego, CA, 92152, United States", "53560 Hull St, San Diego, CA 92152, USA", "32.70865800", "-117.24724910", "mil", "", "United States", "2017"], ["DAP3D-Net: Where, what and how actions occur in videos?", "", "Northumbria University", "Northumbria University", "Northumbria University, Birkdale Close, High Heaton, Newcastle upon Tyne, Tyne and Wear, North East England, England, NE7 7TP, UK", "55.00306320", "-1.57463231", "edu", "", "United Kingdom", "2017"], ["Action Recognition by Learning Deep Multi-Granular Spatio-Temporal Video Representation", "", "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", "2016"], ["Hierarchical and Spatio-Temporal Sparse Representation for Human Action Recognition", "Institute of Information Science, Beijing jiaotong University, Beijing, China", "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"], ["Beyond Bag-of-Words: Fast video classification with Fisher Kernel Vector of Locally Aggregated Descriptors", "LAPI, University Politehnica of Bucharest, 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", "2015"], ["Driver Drowsiness Detection System Based on Feature Representation Learning Using Various Deep Networks", "", "KAIST", "KAIST", "291 Daehak-ro, Eoeun-dong, Yuseong-gu, Daejeon, South Korea", "36.37214270", "127.36039000", "edu", "", "South Korea", "2016"], ["Better and Faster: Knowledge Transfer from Multiple Self-supervised Learning Tasks via Graph Distillation for Video Classification", "", "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"], ["Adversarial Perturbations Against Real-Time Video Classification Systems", "", "University of California, Riverside", "University of California, Riverside", "University of California, Riverside, Linden Street, Riverside, Riverside County, California, 92521, USA", "33.98071305", "-117.33261035", "edu", "", "United States", "2018"], ["Temporal Relational Reasoning in Videos", "", "MIT CSAIL", "MIT CSAIL", "32 Vassar St, Cambridge, MA 02139, USA", "42.36194070", "-71.09043780", "edu", "", "United States", "2018"], ["Spatio-Temporal Instance Learning: Action Tubes from Class Supervision", "", "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"], ["Deep CCA based super vector for action recognition", "School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing", "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", "2015"], ["Rapid human action recognition in H.264/AVC compressed domain for video surveillance", "Video Analytics Laboratory, SERC, 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", "2013"], ["Ordered Pooling of Optical Flow Sequences for Action Recognition", "", "Australian National University", "Australian National University", "Canberra ACT 0200, Australia", "-35.27769990", "149.11852700", "edu", "", "Australia", "2017"], ["Encoding Video and Label Priors for Multi-label Video Classification on YouTube-8M dataset", "", "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"], ["Electronic Theses and Dissertations Title Mining Spatial and Spatio-Temporal ROIs for Action Recognition Permalink", "", "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", "2016"], ["Unsupervised Learning using Sequential Verification for Action Recognition", "", "Carnegie Mellon University Silicon Valley", "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"], ["A Fungus Spores Dataset and a Convolutional Neural Network Based Approach for Fungus Detection", "Institute for Microsensors, Actuators and Systems, University of Bremen, Bremen, Germany", "University of Bremen", "University of Bremen", "Bibliothekstra\u00dfe 1, 28359 Bremen, Germany", "53.10675800", "8.85204000", "edu", "", "", "2018"], ["Visual Text Correction", "", "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"], ["Classifying advertising video by topicalizing high-level semantic concepts", "School of Information Science and Engineering, Shandong Normal University, Jinan, 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", "2018"], ["ActionSnapping: Motion-Based Video Synchronization", "", "Disney Research", "Disney Research", "521 Circle 7 Dr, Glendale, CA 91201, USA", "34.15797420", "-118.28947290", "company", "", "United States", "2016"], ["Minimum-risk temporal alignment of videos", "University of Technology Sydney, Broadway, Australia", "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", "2017"], ["Compressed-domain video classification with deep neural networks: \u201cThere's way too much information to decode the matrix\u201d", "University College London (UCL), Electronic and Electrical Engineering Department, London, U.K.", "Dithen, London, U.K.", "Dithen, London, U.K.", "London, UK", "51.50735090", "-0.12775830", "edu", "", "", "2017"], ["Two-Stream Convolutional Networks for Action Recognition in Videos", "", "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", "2014"], ["Evolution-Preserving Dense Trajectory Descriptors", "", "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", "2017"], ["Mining semantic affordances of visual object categories", "", "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", "2015"], ["3 D ConvNets with Optical Flow Based Regularization", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "United States", "2015"], ["Unsupervised Representation Learning by Sorting Sequences", "", "Virginia Tech", "Virginia Tech", "Blacksburg, VA 24061, USA", "37.22838430", "-80.42341670", "edu", "", "United States", "2017"], ["Detecting self-stimulatory behaviours for autism diagnosis", "Vision & Sensing Group, HCC Lab, ESTeM University of Canberra, Australia", "ESTeM University of Canberra", "Vision & Sensing Group, HCC Lab, ESTeM University of Canberra, Australia", "Building 1/11 Kirinari St, Bruce ACT 2617, Australia", "-35.23845510", "149.08444550", "edu", "", "Australia", "2014"], ["Unsupervised Learning of Long-Term Motion Dynamics for Videos", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "United States", "2017"], ["Actionness Estimation Using Hybrid Fully Convolutional Networks", "", "ETH Zurich", "ETH Zurich", "R\u00e4mistrasse 101, 8092 Z\u00fcrich, Switzerland", "47.37631300", "8.54766990", "edu", "", "Switzerland", "2016"], ["Learning hierarchical video representation for action recognition", "University of Science and Technology of China, Hefei, People\u2019s Republic of China", "University of Science and Technology of China", "University of Science and Technology of China", "\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", "31.83907195", "117.26420748", "edu", "", "China", "2016"], ["Recognizing Activities of Daily Living with a Wrist-Mounted Camera", "", "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"], ["Label Efficient Learning of Transferable Representations across Domains and Tasks", "", "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"], ["Improved Dense Trajectory with Cross Streams", "", "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"], ["Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "United States", "2018"], ["Differentiating Objects by Motion: Joint Detection and Tracking of Small Flying Objects", "", "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", "2017"], ["Convolutional Two-Stream Network Fusion for Video Action Recognition", "", "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"], ["A modified vector of locally aggregated descriptors approach for fast video classification", "LAPI, University Politehnica of Bucharest, Bucharest, 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", "2015"], ["Action Recognition in Video Sequences using Deep Bi-Directional LSTM With CNN Features", "Intelligent Media Laboratory, Digital Contents Research Institute, Sejong University, Seoul, South Korea", "Sejong University", "Intelligent Media Laboratory, Digital Contents Research Institute, Sejong University, Seoul, South Korea", "209 Neungdong-ro, Gunja-dong, Gwangjin-gu, Seoul, South Korea", "37.55025960", "127.07313900", "edu", "", "South Korea", "2018"], ["Pillar Networks++: Distributed non-parametric deep and wide networks", "", "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", "2017"], ["Temporal Hallucinating for Action Recognition with Few Still Images", "", "Shenzhen Institutes of Advanced Technology", "Shenzhen Institutes of Advanced Technology", "\u4e2d\u56fd\u79d1\u5b66\u9662\u6df1\u5733\u5148\u8fdb\u6280\u672f\u7814\u7a76\u9662, 1068, \u79d1\u7814\u8def, \u6df1\u5733\u5927\u5b66\u57ce, \u4e09\u5751\u6751, \u5357\u5c71\u533a, \u6df1\u5733\u5e02, \u5e7f\u4e1c\u7701, 518000, \u4e2d\u56fd", "22.59805605", "113.98533784", "edu", "", "China", "2018"], ["Visual Data Synthesis via GAN for Zero-Shot Video Classification", "", "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"], ["ACTIVITY ANALYSIS OF SPECTATOR PERFORMER VIDEOS USING MOTION TRAJECTORIES", "", "University of Nebraska - Lincoln", "University of Nebraska - Lincoln", "Sheldon Museum of Art, North 12th Street, West Lincoln, Lincoln, Lancaster County, Nebraska, 68588-0300, USA", "40.81747230", "-96.70444680", "edu", "", "United States", "2016"], ["Decomposing Motion and Content for Natural Video Sequence Prediction", "", "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", "2017"], ["Action Recognition Using Convolutional Restricted Boltzmann Machines", "Queen Mary University of London, London, United Kingdom", "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", "2016"], ["A New Urban Objects Detection Framework Using Weakly Annotated Sets", "", "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"], ["Deep Residual Feature Learning for Action Prediction", "University of Chinese Academy of Sciences, School of Computer and Control Engineering, 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"], ["Learning to Recognize Actions From Limited Training Examples Using a Recurrent Spiking Neural Model", "", "Intel Labs", "Intel Labs", "4720 Forbes Ave, Pittsburgh, PA 15213, USA", "40.44397890", "-79.94646340", "company", "", "United States", "2018"], ["Towards Usable Multimedia Event Detection from Web Videos", "", "Carnegie Mellon University Silicon Valley", "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"], ["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"], ["Low-complexity HOG for efficient video saliency", "Technische Universitt Darmstadt, Computer Systems Group, Darmstadt, Germany", "Technische Universitt Darmstadt", "Technische Universitt Darmstadt, Computer Systems Group, Darmstadt, Germany", "Hochschulstra\u00dfe 10, 64289 Darmstadt, Germany", "49.87741510", "8.65461020", "edu", "", "Germany", "2015"], ["Fast Simplex-HMM for One-Shot Learning Activity Recognition", "", "Kingston University", "Kingston University", "Kingston University, Kingston Hill, Kingston Vale, Kingston-upon-Thames, London, Greater London, England, KT2 7TF, UK", "51.42930860", "-0.26840440", "edu", "", "United Kingdom", "2017"], ["Action Detection from a Robot-Car Perspective", "", "Oxford, UK", "Oxford, UK", "Oxford, UK", "51.75202090", "-1.25772630", "edu", "", "", "2018"], ["A2-Nets: Double Attention Networks", "", "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"], ["Action Recognition and Detection by Combining Motion and Appearance Features", "", "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", "2014"], ["Temporal Coherency based Criteria for Predicting Video Frames using Deep Multi-stage Generative Adversarial Networks", "", "Indian Institute of Technology Madras, Chennai, India", "Indian Institute of Technology Madras, Chennai, India", "Indian Institute Of Technology, Chennai, Tamil Nadu 600036, India", "12.99149290", "80.23369070", "edu", "", "India", "2017"], ["Semantic embedding space for zero-shot action recognition", "", "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", "2015"], ["Unseen Action Recognition with Multimodal Learning", "", "Indiana University", "Indiana University", "Indiana University East, West Cart Road, Richmond, Wayne County, Indiana, 47374, USA", "39.86948105", "-84.87956905", "edu", "", "United States", "2018"], ["Entity Competition Network for Video Classification", "University of Chinese Academy of Sciences", "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"], ["Exploiting Temporal Information for DCNN-Based Fine-Grained Object Classification", "", "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", "2016"], ["Human Action Recognition using Hu Moment Invariants and Euclidean Distance Classifier", "", "University of Arkansas at Little Rock", "University of Arkansas at Little Rock", "University of Arkansas At Little Rock (UALR), 2801, U A L R Campus Drive, Little Rock, Pulaski County, Arkansas, 72204, USA", "34.72236805", "-92.33830255", "edu", "", "United States", "2017"], ["Connectionist Temporal Modeling for Weakly Supervised Action Labeling", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "United States", "2016"], ["Embedded Real-Time Fall Detection Using Deep Learning For Elderly Care", "", "Samsung Electronics", "Samsung Electronics", "25 The West Mall, Etobicoke, ON M9C 1B8, Canada", "43.61294840", "-79.55903030", "edu", "", "Canada", "2017"], ["Activity recognition in unconstrained RGB-D video using 3D trajectories", "Nanyang Technological University, Singapore", "Nanyang Technological University", "Nanyang Technological University", "NTU, Faculty Avenue, Jurong West, Southwest, 637460, Singapore", "1.34841040", "103.68297965", "edu", "", "Singapore", "2014"], ["Spot On: Action Localization from Pointly-Supervised Proposals", "", "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"], ["Vision-Based Fall Detection with Convolutional Neural Networks", "", "IKERBASQUE, Basque Foundation for Science, Bilbao, Spain", "IKERBASQUE, Basque Foundation for Science, Bilbao, Spain", "Mar\u00eda D\u00edaz Haroko Kalea, 3, 48013 Bilbo, Bizkaia, Spain", "43.26425400", "-2.94302300", "edu", "", "Spain", "2017"], ["A New Large Scale Dynamic Texture Dataset with Application to ConvNet Understanding", "", "York University", "York University", "York University, Keele Campus, Campus Walk, North York, Toronto, Ontario, M3J 2S5, Canada", "43.77439110", "-79.50481085", "edu", "", "Canada", "2018"], ["Deep Learning for Semantic Video Understanding by Sourabh Kulhare", "", "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"], ["MoFAP: A Multi-level Representation for Action Recognition", "Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China", "Shenzhen Institutes of Advanced Technology", "Shenzhen Institutes of Advanced Technology", "\u4e2d\u56fd\u79d1\u5b66\u9662\u6df1\u5733\u5148\u8fdb\u6280\u672f\u7814\u7a76\u9662, 1068, \u79d1\u7814\u8def, \u6df1\u5733\u5927\u5b66\u57ce, \u4e09\u5751\u6751, \u5357\u5c71\u533a, \u6df1\u5733\u5e02, \u5e7f\u4e1c\u7701, 518000, \u4e2d\u56fd", "22.59805605", "113.98533784", "edu", "", "China", "2015"], ["Excitation Dropout: Encouraging Plasticity in Deep Neural Networks", "", "University of Verona", "University of Verona", "Via S. Francesco, 22, 37129 Verona VR, Italy", "45.43739800", "11.00337600", "edu", "", "Italy", "2018"], ["Pooling the Convolutional Layers in Deep ConvNets for Action Recognition", "", "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", "2015"], ["Unsupervised Hierarchical Dynamic Parsing and Encoding for Action Recognition", "Science and Technology on Integrated Information System Laboratory, Institute of Software, 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", "2017"], ["Two-Stream SR-CNNs for Action Recognition in Videos", "", "ETH Zurich", "ETH Zurich", "R\u00e4mistrasse 101, 8092 Z\u00fcrich, Switzerland", "47.37631300", "8.54766990", "edu", "", "Switzerland", "2016"], ["What Makes a Video a Video : Analyzing Temporal Information in Video Understanding Models and Datasets", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "United States", "2018"], ["Who's Better, Who's Best: Skill Determination in Video using Deep Ranking", "", "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"], ["Efficient and Effective Solutions for Video Classification", "", "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", "2017"], ["Top-Down Attention Recurrent VLAD Encoding for Action Recognition in Videos", "", "University of Trento", "University of Trento", "University of Trento, Via Giuseppe Verdi, Piedicastello, Trento, Territorio Val d'Adige, TN, TAA, 38122, Italia", "46.06588360", "11.11598940", "edu", "", "Italy", "2018"], ["VIENA2: A Driving Anticipation Dataset", "", "EPFL", "EPFL", "Route Cantonale, 1015 Lausanne, Switzerland", "46.51905570", "6.56675760", "edu", "", "Switzerland", "2018"], ["L 1-regularized Logistic Regression Stacking and Transductive CRF Smoothing for Action Recognition in Video", "", "University of Florence", "University of Florence", "Piazza di San Marco, 4, 50121 Firenze FI, Italy", "43.77764260", "11.25976500", "edu", "", "Italy", "2013"], ["UC-HCC Submission to Thumos 2014", "", "University of Canberra", "University of Canberra", "University of Canberra, University Drive, Bruce, Belconnen, Australian Capital Territory, 2617, Australia", "-35.23656905", "149.08446994", "edu", "", "Australia", "2014"], ["Concepts not alone: exploring pairwise relationships for zero-shot video activity recognition", "", "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"], ["Building semantic understanding beyond deep learning from sound and vision", "Dept. of Computer Science & Engineering, University of South Florida, Tampa, 33620, United States of America", "University of South Florida", "University of South Florida", "University of South Florida, Leroy Collins Boulevard, Tampa, Hillsborough County, Florida, 33620, USA", "28.05999990", "-82.41383619", "edu", "", "United States", "2016"], ["Submodular Attribute Selection for Action Recognition in Video", "", "National Institute of Standards and Technology", "National Institute of Standards and Technology", "National Institute of Standards and Technology, Summer Walk Drive, Diamond Farms, Gaithersburg, Montgomery County, Maryland, 20878, USA", "39.12549380", "-77.22293475", "edu", "", "United States", "2014"], ["Spatio-Temporal Person Retrieval via Natural Language Queries", "", "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", "2017"], ["Searching Persuasively: Joint Event Detection and Evidence Recounting with Limited Supervision", "University of Technology Sydney, Sydney, Australia", "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", "2015"], ["Action recognition with trajectory-pooled deep-convolutional descriptors", "", "Shenzhen Institutes of Advanced Technology", "Shenzhen Institutes of Advanced Technology", "\u4e2d\u56fd\u79d1\u5b66\u9662\u6df1\u5733\u5148\u8fdb\u6280\u672f\u7814\u7a76\u9662, 1068, \u79d1\u7814\u8def, \u6df1\u5733\u5927\u5b66\u57ce, \u4e09\u5751\u6751, \u5357\u5c71\u533a, \u6df1\u5733\u5e02, \u5e7f\u4e1c\u7701, 518000, \u4e2d\u56fd", "22.59805605", "113.98533784", "edu", "", "China", "2015"], ["Cascaded temporal spatial features for video action recognition", "National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences", "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"], ["ODN: Opening the Deep Network for Open-Set Action Recognition", "School of Information and Electronics, Beijing Institute of Technology, 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"], ["The Pose Knows: Video Forecasting by Generating Pose Futures", "", "Carnegie Mellon University Silicon Valley", "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"], ["Online multimodal matrix factorization for human action video indexing", "MindLAB Research Group, Universidad Nacional de Colombia, Colombia", "Universidad Nacional de Colombia", "MindLAB Research Group, Universidad Nacional de Colombia, Colombia", "Cra 45, Bogot\u00e1, Colombia", "4.63819380", "-74.08404640", "edu", "", "Colombia", "2014"], ["In Unsupervised Spatio-temporal Feature Learning", "", "University of California", "University of California", "Berkeley, CA, USA", "37.87189920", "-122.25853990", "edu", "", "United States", "2018"], ["Viewpoint-aware Video Summarization", "", "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-Task Transfer Methods to Improve One-Shot Learning for Multimedia Event Detection", "", "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", "2015"], ["End-to-end temporal attention extraction and human action recognition", "Schepens Eye Research Institute, Harvard University, Cambridge, USA", "Harvard University", "Harvard University", "Harvard University, Soldiers Field Road, Allston, Boston, Suffolk County, Massachusetts, 02163, USA", "42.36782045", "-71.12666653", "edu", "", "United States", "2018"], ["Boosting VLAD with double assignment using deep features for action recognition in videos", "", "University of Trento", "University of Trento", "University of Trento, Via Giuseppe Verdi, Piedicastello, Trento, Territorio Val d'Adige, TN, TAA, 38122, Italia", "46.06588360", "11.11598940", "edu", "", "Italy", "2016"], ["Improving Human Action Recognition through Hierarchical Neural Network Classifiers", "Institute of Robotics, Innopolis University, Russia", "Innopolis University", "Institute of Robotics, Innopolis University, Russia", "Universitetskaya St, 1, Innopolis, Respublika Tatarstan, Russia, 420500", "55.75344900", "48.74341100", "edu", "", "Russia", "2018"], ["Temporal Convolutional Neural Network for Gesture Recognition", "School of Computer Science, Communication University of China, Beijing, China", "Communication University of China", "Communication University of China", "\u4e2d\u56fd\u4f20\u5a92\u5927\u5b66, \u671d\u9633\u8def, \u5b9a\u798f\u5e84, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100024, \u4e2d\u56fd", "39.91199955", "116.55189141", "edu", "", "China", "2018"], ["Key frame extraction for salient activity recognition", "Computer Science, Rochester Institute of Technology, USA", "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"], ["Exploiting Multi-modal Curriculum in Noisy Web Data for Large-scale Concept Learning", "", "Carnegie Mellon University Silicon Valley", "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"], ["Categorizing Big Video Data on the Web: Challenges and Opportunities", "", "Shanghai, China", "Shanghai, China", "Shanghai, China", "31.23039040", "121.47370210", "edu", "", "", "2015"], ["Differential Angular Imaging for 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", "2017"], ["Part-Activated Deep Reinforcement Learning for Action Prediction", "", "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"], ["Bags-of-daglets for action recognition", "Institut Mines-Télécom; Télécom ParisTech; CNRS LTCI", "T\u00e9l\u00e9com ParisTech", "Institut Mines-Telecom, Telecom ParisTech, CNRS LTCI, Sophia Antipolis, France", "Business P\u00f4le. 1047 route des Dolines. All\u00e9e Pierre Ziller, 06560 Sophia Antipolis, France", "43.62716550", "7.04109170", "edu", "", "France", "2014"], ["Dense-Captioning Events in Videos", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "United States", "2017"], ["Deep recurrent neural network reveals a hierarchy of process memory during dynamic natural vision.", "", "Purdue University", "Purdue University", "Purdue University, West Stadium Avenue, West Lafayette, Tippecanoe County, Indiana, 47907, USA", "40.43197220", "-86.92389368", "edu", "", "United States", "2018"], ["TPC: Temporal Preservation Convolutional Networks for Precise Temporal Action Localization.", "", "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"], ["Learning features from Improved Dense Trajectories using deep convolutional networks for Human Activity Recognition", "", "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", "2015"], ["Segment-Tube: Spatio-Temporal Action Localization in Untrimmed Videos with Per-Frame Segmentation", "", "Microsoft", "Microsoft Corporation, Redmond, WA, USA", "One Microsoft Way, Redmond, WA 98052, USA", "47.64233180", "-122.13693020", "company", "", "United States", "2018"], ["MuseumVisitors: A dataset for pedestrian and group detection, gaze estimation and behavior understanding", "", "Columbia University", "Columbia University", "Columbia University Medical Center, 630, West 168th Street, Washington Heights, Manhattan, Manhattan Community Board 12, New York County, NYC, New York, 10031, USA", "40.84198360", "-73.94368971", "edu", "", "United States", "2015"], ["Incorporating Context Information into Deep Neural Network Acoustic Models", "", "Carnegie Mellon University Silicon Valley", "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"], ["SCNN: Sequential convolutional neural network for human action recognition in videos", "CAS Center for Excellence in Brain Science and Intelligence Technology; National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences; University of Chinese Academy of Sciences, Beijing, China", "Chinese Academy of Science", "Chinese Academy of Science", "52 Sanlihe Rd, Xicheng Qu, Beijing Shi, China", "39.91063270", "116.33563210", "edu", "", "China", "2017"], ["Joint Spatio-Temporal Action Localization in Untrimmed Videos with Per-Frame Segmentation", "", "Microsoft", "Microsoft Corporation, Redmond, WA, USA", "One Microsoft Way, Redmond, WA 98052, USA", "47.64233180", "-122.13693020", "company", "", "United States", "2018"], ["Discriminative GoDec+ for Classification", "School of Electronic and Information Engineering, South China University of Technology, Guangdong, China", "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", "2017"], ["Im 2 vid : Future Video Prediction for Static Image Action Recognition", "", "Virginia Tech", "Virginia Tech", "Blacksburg, VA 24061, USA", "37.22838430", "-80.42341670", "edu", "", "United States", "2018"], ["Spatio-Temporal VLAD Encoding for Human Action Recognition in Videos", "", "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", "2017"], ["Heterogeneous Semantic Level Features Fusion for Action Recognition", "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", "2015"], ["A survey on aggregating methods for action recognition with dense trajectories", "School of Electronic Science and Engineering, National ASIC Research and Engineering Center, Southeast University, Nanjing, China", "Southeast University", "Southeast University", "SEU, \u4f53\u80b2\u9986\u8def, \u65b0\u8857\u53e3, \u6708\u5b63\u56ed, \u7384\u6b66\u533a, \u5357\u4eac\u5e02, \u6c5f\u82cf\u7701, 210008, \u4e2d\u56fd", "32.05752790", "118.78682252", "edu", "", "China", "2015"], ["Learning Attributes Equals Multi-Source Domain Generalization", "", "University of Iowa", "University of Iowa", "University of Iowa, Hawkeye Court, Iowa City, Johnson County, Iowa, 52246, USA", "41.66590000", "-91.57310307", "edu", "", "United States", "2016"], ["AMTnet: Action-Micro-Tube Regression by End-to-end Trainable Deep Architecture", "", "Oxford Brookes University", "Oxford Brookes University", "Oxford Brookes University, Headington Road, Headington, Oxford, Oxon, South East, England, OX3 0BL, UK", "51.75552050", "-1.22615970", "edu", "", "United Kingdom", "2017"], ["Exploring hybrid spatio-temporal convolutional networks for human action recognition", "The State Key Laboratory of Integrated Services Networks (ISN), Xidian University, Xi\u2019an, China", "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", "2017"], ["Deep Keyframe Detection in Human Action Videos", "", "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"], ["A Zero-Shot Architecture for Action Recognition in Still Images", "Department of Computer Science, University Of Central Florida", "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"], ["Sport Action Recognition with Siamese Spatio-Temporal CNNs: Application to Table Tennis", "Univ. La Rochelle, MIA La Rochelle, France", "Univ. La Rochelle, MIA La Rochelle, France", "Univ. La Rochelle, MIA La Rochelle, France", "23 Avenue Albert Einstein, 17000 La Rochelle, France", "46.14764610", "-1.15494150", "edu", "", "", "2018"], ["Exploiting Images for Video Recognition with Hierarchical Generative Adversarial Networks", "", "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"], ["Encouraging LSTMs to Anticipate Actions Very Early", "", "Australian National University", "Australian National University", "Canberra ACT 0200, Australia", "-35.27769990", "149.11852700", "edu", "", "Australia", "2017"], ["Scalable Discrete Supervised Multimedia Hash Learning With Clustering", "State Key Laboratory of Intelligent Technology and Systems, TNList, Department of Computer Science and Technology, 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", "2018"], ["A Deep Ranking Model for Spatio-Temporal Highlight Detection From a 360\u25e6 Video", "", "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"], ["Videos from the 2013 Boston Marathon : An Event Reconstruction Dataset for Synchronization and Localization", "", "Carnegie Mellon University Silicon Valley", "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"], ["RESOUND: Towards Action Recognition Without Representation Bias", "", "UC San Diego", "UC San Diego", "9500 Gilman Dr, La Jolla, CA 92093, USA", "32.88006040", "-117.23401350", "edu", "", "United States", "2018"], ["Multiscale Deep Alternative Neural Network for Large-Scale Video Classification", "Department of Electrical and Computer Engineering, 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", "2018"], ["Deep multi-scale video prediction beyond mean square error", "", "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", "2015"], ["Improved Motion Description for Action Classification", "", "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", "2016"], ["Evaluating Two-Stream CNN for Video Classification", "", "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", "2015"], ["Learning Object-Centric Transformation for Video Prediction", "Peking University, Shenzhen, 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", "2017"], ["A Review on Human Activity Recognition Using Vision-Based Method", "", "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"], ["Recurrent Neural Networks and Transfer Learning for Action Recognition", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "United States", "2015"], ["Efficient Two-Stream Motion and Appearance 3 D CNNs for Video Classification", "", "ETH Zurich", "ETH Zurich", "R\u00e4mistrasse 101, 8092 Z\u00fcrich, Switzerland", "47.37631300", "8.54766990", "edu", "", "Switzerland", "2016"], ["Video Generation Using 3D Convolutional Neural Network", "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"], ["Fast action proposals for human action detection and search", "", "Nanyang Technological University", "Nanyang Technological University", "NTU, Faculty Avenue, Jurong West, Southwest, 637460, Singapore", "1.34841040", "103.68297965", "edu", "", "Singapore", "2015"], ["Hierarchical Attention Network for Action Recognition in Videos.", "", "Arizona State University", "Arizona State University", "Arizona State University Polytechnic campus, East Texas Avenue, Mesa, Maricopa County, Arizona, 85212, USA", "33.30715065", "-111.67653157", "edu", "", "United States", "2016"], ["Stratified pooling based deep convolutional neural networks for human action recognition", "School of Information, Hunan University of Humanities, Science and Technology, Loudi, China", "Fujian Key Laboratory of the Brain-like Intelligent Systems, Xiamen, China", "Fujian Key Laboratory of the Brain-like Intelligent Systems, Xiamen, China", "Xiamen, Fujian, China", "24.47983300", "118.08942500", "edu", "", "China", "2016"], ["Adaptive feature learning CNN for behavior recognition in crowd scene", "Fundamental and Applied Science Department, Universiti Teknologi PETRONAS, Seri Iskandar, 32610, Perak Malaysia", "Universiti Teknologi Petronas", "Universiti Teknologi PETRONAS", "UTP, Universiti Teknologi Petronas, Persiaran Desa Kediaman, Puncak Iskandar, Seri Iskandar, PRK, 32610, Malaysia", "4.38304640", "100.97001540", "edu", "", "Malaysia", "2017"], ["Large-Scale Video Classification with Convolutional 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", "2014"], ["A Hierarchical Deep Temporal Model for Group Activity Recognition", "", "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", "2016"], ["Spatio-Temporal AutoEncoder for Video Anomaly Detection", "Zhejiang University & Alibaba Group, Hangzhou, China", "Zhejiang University & Alibaba Group", "Zhejiang University & Alibaba Group, Hangzhou, China", "38 Zheda Rd, Xihu Qu, Hangzhou Shi, Zhejiang Sheng, China, 310027", "30.26394400", "120.12327900", "edu", "", "China", "2017"], ["DeepCache: Principled Cache for Mobile Deep Vision", "", "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"], ["UntrimmedNets for Weakly Supervised Action Recognition and Detection", "", "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"], ["Sequential Max-Margin Event Detectors", "", "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", "2014"], ["Spatiotemporal Multiplier Networks for Video Action Recognition", "", "York University", "York University", "York University, Keele Campus, Campus Walk, North York, Toronto, Ontario, M3J 2S5, Canada", "43.77439110", "-79.50481085", "edu", "", "Canada", "2017"], ["PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding", "", "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"], ["Graph Distillation for Action Detection with Privileged Modalities", "", "Google", "Google, Inc.", "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "37.42199990", "-122.08405750", "company", "Google, Mountain View, CA", "United States", "2018"], ["Temporal and Fine-Grained Pedestrian Action Recognition on Driving Recorder Database", "", "Tokyo Metropolitan University", "Tokyo Metropolitan University", "\u9996\u90fd\u5927\u5b66\u6771\u4eac, \u7531\u6728\u7dd1\u9053, \u516b\u738b\u5b50\u5e02, \u6771\u4eac\u90fd, \u95a2\u6771\u5730\u65b9, 1920364, \u65e5\u672c", "35.62009250", "139.38296706", "edu", "", "Japan", "2018"], ["Using Convolutional 3D Neural Networks for User-independent continuous gesture recognition", "", "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", "2016"], ["Human Action Recognition Using Fusion of Modern Deep Convolutional and Recurrent Neural Networks", "National Technical University of Ukraine, \u201cIgor Sikorsky Kyiv Polytechnic Institute\u201d, Institute for Applied System Analysis, Kyiv, Ukraine", "National Technical University of Ukraine", "National Technical University of Ukraine, \u201cIgor Sikorsky Kyiv Polytechnic Institute\u201d, Institute for Applied System Analysis, Kyiv, Ukraine", "\u041a\u043e\u0440\u043f\u0443\u0441 \u21161, Peremohy Ave, 37, Kyiv, Ukraine, 03056", "50.44951200", "30.46081360", "edu", "", "Ukraine", "2018"], ["Projection Bank: From High-Dimensional Data to Medium-Length Binary Codes", "", "Northumbria University", "Northumbria University", "Northumbria University, Birkdale Close, High Heaton, Newcastle upon Tyne, Tyne and Wear, North East England, England, NE7 7TP, UK", "55.00306320", "-1.57463231", "edu", "", "United Kingdom", "2015"], ["ContextVP: Fully Context-Aware Video Prediction", "", "ETH Zurich", "ETH Zurich", "R\u00e4mistrasse 101, 8092 Z\u00fcrich, Switzerland", "47.37631300", "8.54766990", "edu", "", "Switzerland", "2018"], ["A survey on compressed domain video analysis techniques", "Video Analytics Laboratory, SERC, 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", "2014"], ["Time-varying LSTM networks for action recognition", "Nanjing University of Posts and Telecommunications, Nanjing, China", "Nanjing University of Posts and Telecommunications", "College of Telecommunications & Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China", "9 Wenyuan Rd, Qixia Qu, Nanjing Shi, Jiangsu Sheng, China, 210046", "32.10574800", "118.93170100", "edu", "", "China", "2018"], ["Human action recognition system for elderly and children care using three stream ConvNet", "Department of Computer Science and Information Engineering, National Central University, Taoyuan, Taiwan, R.O.C.", "National Central University", "National Central University", "NCU, 300, \u4e2d\u5927\u8def, \u4e0a\u4e09\u5ea7\u5c4b, \u4e94\u6b0a\u91cc, \u6a39\u6797\u5b50, \u4e2d\u58e2\u5340, \u6843\u5712\u5e02, 320, \u81fa\u7063", "24.96841805", "121.19139696", "edu", "", "Taiwan", "2015"], ["Robust Global Motion Compensation in Presence of Predominant Foreground", "", "Michigan State University", "Michigan State University", "Michigan State University, Farm Lane, East Lansing, Ingham County, Michigan, 48824, USA", "42.71856800", "-84.47791571", "edu", "", "United States", "2015"], ["Computer Vision \u2013 ECCV 2018", "Hebrew University of Jerusalem, Jerusalem, Israel", "Hebrew University of Jerusalem", "The Hebrew University of Jerusalem", "\u05d4\u05d0\u05d5\u05e0\u05d9\u05d1\u05e8\u05e1\u05d9\u05d8\u05d4 \u05d4\u05e2\u05d1\u05e8\u05d9\u05ea \u05d1\u05d9\u05e8\u05d5\u05e9\u05dc\u05d9\u05dd, Reagan Plaza, \u05e7\u05e8\u05d9\u05ea \u05de\u05e0\u05d7\u05dd \u05d1\u05d2\u05d9\u05df, \u05d4\u05e8 \u05d4\u05e6\u05d5\u05e4\u05d9\u05dd, \u05d9\u05e8\u05d5\u05e9\u05dc\u05d9\u05dd, \u05de\u05d7\u05d5\u05d6 \u05d9\u05e8\u05d5\u05e9\u05dc\u05d9\u05dd, NO, \u05d9\u05e9\u05e8\u05d0\u05dc", "31.79185550", "35.24472300", "edu", "", "Israel", "2018"], ["Exploring Semantic Inter-Class Relationships (SIR) for Zero-Shot Action Recognition", "", "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", "2015"], ["Single Shot Temporal Action 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", "2017"], ["Temporal Action Detection by Joint Identification-Verification", "", "Northeastern University", "Northeastern University", "Snell Library, 360, Huntington Avenue, Roxbury Crossing, Fenway, Boston, Suffolk County, Massachusetts, 02115, USA", "42.33836680", "-71.08793524", "edu", "", "United States", "2018"], ["Visual Recognition Using Directional Distribution Distance", "", "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", "2015"], ["LEARNING FROM LARGE-SCALE VISUAL DATA FOR ROBOTS", "", "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"], ["Cross-Modal and Hierarchical Modeling of Video and Text", "", "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"], ["Combining multiple sources of knowledge in deep CNNs for action recognition", "", "University of North Carolina at Chapel Hill", "University of North Carolina at Chapel Hill", "University of North Carolina at Chapel Hill, East Cameron Avenue, Chapel Hill, Orange County, North Carolina, 27514, USA", "35.91139710", "-79.05045290", "edu", "", "United States", "2016"], ["A Comprehensive Review on Handcrafted and Learning-Based Action Representation Approaches for Human Activity Recognition", "", "COMSATS Institute of Information Technology, Lahore", "COMSATS Institute of Information Technology", "COMSATS Institute of Information Technology, Ali Akbar Road, Dawood Residency, \u0628\u062d\u0631\u06cc\u06c1 \u0679\u0627\u0624\u0646\u202c\u200e, Lahore District, \u067e\u0646\u062c\u0627\u0628, 54700, \u200f\u067e\u0627\u06a9\u0633\u062a\u0627\u0646\u200e", "31.40063320", "74.21372960", "edu", "", "Pakistan", "2017"], ["Localizing Actions from Video Labels and Pseudo-Annotations", "", "Columbia University", "Columbia University", "Columbia University Medical Center, 630, West 168th Street, Washington Heights, Manhattan, Manhattan Community Board 12, New York County, NYC, New York, 10031, USA", "40.84198360", "-73.94368971", "edu", "", "United States", "2017"], ["What Actions are Needed for Understanding Human Actions in Videos?", "", "Carnegie Mellon University Silicon Valley", "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"], ["Action Recognition Based on Efficient Deep Feature Learning in the Spatio-Temporal Domain", "RheinAhrCampus der Hochschule Koblenz, Remagen, Germany", "RheinAhrCampus der Hochschule Koblenz", "RheinAhrCampus der Hochschule Koblenz, Remagen, Germany", "RheinAhrCampus, 2, Joseph-Rovan-Allee, Remagen, Landkreis Ahrweiler, Rheinland-Pfalz, 53424, Deutschland", "50.57225620", "7.25318610", "edu", "", "Germany", "2016"], ["Action Recognition with Joint Attention on Multi-Level Deep Features", "", "Beijing, China", "Beijing, China", "Beijing, China", "39.90419990", "116.40739630", "edu", "", "China", "2016"], ["A new dataset for hand gesture estimation", "Southeast University, Nanjing, China", "Southeast University", "Southeast University", "SEU, \u4f53\u80b2\u9986\u8def, \u65b0\u8857\u53e3, \u6708\u5b63\u56ed, \u7384\u6b66\u533a, \u5357\u4eac\u5e02, \u6c5f\u82cf\u7701, 210008, \u4e2d\u56fd", "32.05752790", "118.78682252", "edu", "", "China", "2017"], ["Human action recognition in compressed domain using PBL-McRBFN approach", "Supercomputer Education and Research Centre, Indian Institute of Science, Bangalore", "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", "2014"], ["Regularizing Long Short Term Memory with 3D Human-Skeleton Sequences for Action Recognition", "", "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", "2016"], ["Semantic Aware Video Transcription Using Random Forest Classifiers", "", "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", "2014"], ["Fudan-Huawei at MediaEval 2015: Detecting Violent Scenes and Affective Impact in Movies with Deep Learning", "", "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", "2015"], ["Joint Constrained Clustering and Feature Learning based on Deep Neural Networks", "", "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"], ["Action recognition with gradient boundary convolutional network", "Research Institute of Shenzhen, Wuhan University, Shenzhen, 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", "2017"], ["Convex Multiview Semi-Supervised Classification", "State Key Laboratory of Transient Optics and Photonics, Center for OPTical IMagery Analysis and Learning, Xi\u2019an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi\u2019an, 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"], ["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"], ["Searching Video , Detecting Events and Describing Video", "", "Beijing, China", "Beijing, China", "Beijing, China", "39.90419990", "116.40739630", "edu", "", "China", "2017"], ["Alternative Semantic Representations for Zero-Shot Human Action Recognition", "", "University of Manchester", "University of Manchester", "University of Manchester - Main Campus, Brunswick Street, Curry Mile, Ardwick, Manchester, Greater Manchester, North West England, England, M13 9NR, UK", "53.46600455", "-2.23300881", "edu", "", "United Kingdom", "2017"], ["Action Representation Using Classifier Decision Boundaries", "", "Australian National University", "Australian National University", "Canberra ACT 0200, Australia", "-35.27769990", "149.11852700", "edu", "", "Australia", "2017"], ["Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images", "", "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"], ["MIC-TJU in MediaEval 2017 Emotional Impact of Movies Task.", "", "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"], ["Recurrent Tubelet Proposal and Recognition Networks for Action Detection", "", "Microsoft Research Asia", "Microsoft Research Asia", "1 Memorial Dr, Cambridge, MA 02142, USA", "42.36142560", "-71.08120920", "company", "", "United States", "2018"], ["Learning Discriminative Features via Label Consistent Neural Network", "", "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"], ["Temporal Modular Networks for Retrieving Complex Compositional Activities in Videos", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "United States", "2018"], ["Attentive Sequence to Sequence Translation for Localizing Clips of Interest by Natural Language Descriptions", "", "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", "2018"], ["Compressed domain human action recognition in H.264/AVC video streams", "Video Analytics Lab, SERC, 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", "2014"], ["Submodular Attribute Selection for Visual Recognition", "Raytheon BBN Technologies, 10 Moulton St, Cambridge, MA", "Raytheon BBN Technologies, Cambridge, MA", "Raytheon BBN Technologies, Cambridge, MA", "10 Moulton St, Cambridge, MA 02138, USA", "42.38980550", "-71.14759860", "company", "", "United States", "2016"], ["Natural Video Sequence Prediction", "", "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", "2017"], ["Deep Quantization: Encoding Convolutional Activations with Deep Generative Model", "", "Microsoft Research Asia", "Microsoft Research Asia", "1 Memorial Dr, Cambridge, MA 02142, USA", "42.36142560", "-71.08120920", "company", "", "United States", "2017"], ["Human Action Recognition Using Factorized Spatio-Temporal Convolutional Networks", "", "University of Macau", "University of Macau", "\u7814\u7a76\u751f\u5bbf\u820d Resid\u00eancia de Estudantes de P\u00f3s-Gradua\u00e7\u00e3o da Universidade de Macau, \u6fb3\u9580\u5927\u5b78 Universidade de Macau, \u5609\u6a21\u5802\u5340 Nossa Senhora do Carmo, \u6c39\u4ed4 Taipa, Universidade de Macau em Ilha de Montanha \u6fb3\u9580\u5927\u5b78\u6a6b\u7434\u6821\u5340, \u4e2d\u56fd", "22.12401870", "113.54510901", "edu", "", "China", "2015"], ["Multimedia event detection with \u21132-regularized logistic Gaussian mixture regression", "School of Computer Science, Wuyi University, Jiangmen, China", "Carnegie Mellon University Silicon Valley", "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", "2014"], ["USC at THUMOS 2014", "", "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", "2014"], ["GeePS: scalable deep learning on distributed GPUs with a GPU-specialized parameter server", "", "Carnegie Mellon University Silicon Valley", "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"], ["Initialization Strategies of Spatio-Temporal Convolutional Neural Networks", "", "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", "2015"], ["Finding action tubes", "", "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"], ["Suggesting Sounds for Images from Video Collections", "", "Disney Research", "Disney Research", "521 Circle 7 Dr, Glendale, CA 91201, USA", "34.15797420", "-118.28947290", "company", "", "United States", "2016"], ["Hierarchical Temporal Memory Enhanced One-Shot Distance Learning for Action Recognition", "School of Information and Electronics, Beijing Institute of Technology, 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"], ["Cross-Species Learning: A Low-Cost Approach to Learning Human Fight from Animal Fight", "Max Planck Institute for Informatics, Saarland Informatics Campus, Saarbr\u00fccken, Germany", "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"], ["Sequential Video VLAD: Training the Aggregation Locally and Temporally", "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"], ["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"], ["Human Pose Estimation : Extension and Application", "", "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", "2017"], ["Exploiting the locality information of dense trajectory feature for human action recognition", "Tianjin University, China", "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", "2015"], ["VOS-GAN: Adversarial Learning of Visual-Temporal Dynamics for Unsupervised Dense Prediction in Videos", "", "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"], ["Beyond short snippets: Deep networks for video classification", "", "Google", "Google, Inc.", "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA", "37.42199990", "-122.08405750", "company", "Google, Mountain View, CA", "United States", "2015"], ["Searching Action Proposals via Spatial Actionness Estimation and Temporal Path Inference and Tracking", "", "University of Trento", "University of Trento", "University of Trento, Via Giuseppe Verdi, Piedicastello, Trento, Territorio Val d'Adige, TN, TAA, 38122, Italia", "46.06588360", "11.11598940", "edu", "", "Italy", "2016"], ["Compositional Structure Learning for Action Understanding", "", "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"], ["Detecting the Moment of Completion: Temporal Models for Localising Action Completion", "", "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"], ["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"], ["Fast Automatic Video Retrieval using Web Images", "", "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", "2015"], ["Action 2 Vec : A Crossmodal Embedding Approach to Action Learning", "", "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"], ["Video Captioning with Boundary-aware Hierarchical Language Decoding and Joint Video Prediction", "", "Singapore", "Singapore", "Singapore", "1.35208300", "103.81983600", "edu", "", "Singapore", "2018"], ["EXMOVES: Classifier-based Features for Scalable Action Recognition", "", "Dartmouth College", "Dartmouth College", "Dartmouth College, Tuck Mall, Hanover, Grafton County, New Hampshire, 03755, USA", "43.70479270", "-72.29259090", "edu", "", "United States", "2013"], ["An efficient and sparse approach for large scale human action recognition in videos", "Univ. La Rochelle, La Rochelle, France", "Univ. La Rochelle, La Rochelle, France", "Univ. La Rochelle, La Rochelle, France", "23 Avenue Albert Einstein, 17000 La Rochelle, France", "46.14764610", "-1.15494150", "edu", "", "France", "2016"], ["LPM for Action Recognition in Temporally Untrimmed Videos", "", "University of Ottawa", "University of Ottawa", "University of Ottawa, 1, Stewart Street, Byward Market, Lowertown, Rideau-Vanier, Ottawa, Ontario, K1N 6N5, Canada", "45.42580475", "-75.68740118", "edu", "", "Canada", "2014"], ["RNN Fisher Vectors for Action Recognition and Image Annotation", "", "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", "2016"], ["Intelligent Information and Database Systems", "Wroc\u0142aw University of Science and Technology, Wroc\u0142aw, Poland", "Wroc\u0142aw University of Science and Technology", "Faculty of Electronics, Wroc\u0142aw University of Science and Technology, 50 370 Wroc\u0142aw, Wyb. Wyspianskiego 27, Poland", "wybrze\u017ce Stanis\u0142awa Wyspia\u0144skiego 27, 50-370 Wroc\u0142aw, Poland", "51.10739070", "17.06197120", "edu", "", "Poland", "2018"], ["Compressed Video Action Recognition", "", "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"], ["Predicting Human Intentions from Motion Cues Only: A 2D+3D Fusion Approach", "Istituto Italiano di Tecnologia (IIT), Genova, Italy", "Istituto Italiano di Tecnologia (IIT), Genova, Italy", "Istituto Italiano di Tecnologia (IIT), Genova, Italy", "Via Morego, 30, 16163 Genova GE, Italy", "44.47493740", "8.90622870", "edu", "", "Italy", "2017"], ["Robust Multi-Modal Cues for Dyadic Human Interaction Recognition", "University of Tunis El Manar, Tunis, Tunisia", "University of Tunis El Manar", "SITI Laboratory, University of Tunis El Manar, Tunis, Tunisia", "Universit\u00e9 de Tunis El Manar, Campus Universitaire Farhat Hached, B.P. n\u00b0 94 - ROMMANA, Tunis 1068, Tunisia", "36.82930900", "10.14626800", "edu", "", "Tunisia", "2017"], ["Beyond verbs: Understanding actions in videos with text", "", "University of Manitoba", "University of Manitoba", "University of Manitoba, Gillson Street, Normand Park, Saint Vital, Winnipeg, Manitoba, R3T 2N2, Canada", "49.80915360", "-97.13304179", "edu", "", "Canada", "2016"], ["Large-Scale Video Classification with Elastic Streaming Sequential Data Processing System", "University of Washington, 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", "2017"], ["A Dense SURF and Triangulation Based Spatio-temporal Feature for Action Recognition", "", "University of Electro-Communications", "The University of Electro-Communications", "\u96fb\u6c17\u901a\u4fe1\u5927\u5b66, \u7532\u5dde\u8857\u9053, \u8abf\u5e03\u5e02, \u6771\u4eac\u90fd, \u95a2\u6771\u5730\u65b9, 182-0026, \u65e5\u672c", "35.65729570", "139.54255868", "edu", "", "Japan", "2014"], ["GIFGIF+: Collecting emotional animated GIFs with clustered multi-task learning", "Media Lab, Massachusetts Institute of Technology, Cambridge, MA, USA", "MIT", "Massachusetts Institute", "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "42.35839610", "-71.09567788", "edu", "", "United States", "2017"], ["Generated Motion Maps", "", "Tokyo Denki University", "Tokyo Denki University", "\u96fb\u6c17\u901a\u4fe1\u5927\u5b66, \u7532\u5dde\u8857\u9053, \u8abf\u5e03\u5e02, \u6771\u4eac\u90fd, \u95a2\u6771\u5730\u65b9, 182-0026, \u65e5\u672c", "35.65729570", "139.54255868", "edu", "", "Japan", "2017"], ["Computational Methods for Behavior Analysis", "", "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"], ["Natural Language Video Description using Deep Recurrent Neural Networks", "", "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", "2015"], ["Ordered Trajectories for Large Scale Human Action Recognition", "", "Australian National University", "Australian National University", "Canberra ACT 0200, Australia", "-35.27769990", "149.11852700", "edu", "", "Australia", "2013"], ["PKU-MMD: A Large Scale Benchmark for Skeleton-Based Human Action Understanding", "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", "2017"], ["Experimenting Motion Relativity for Action Recognition with a Large Number of Classes", "", "East China Normal University", "East China Normal University", "\u534e\u4e1c\u5e08\u8303\u5927\u5b66, 3663, \u4e2d\u5c71\u5317\u8def, \u66f9\u5bb6\u6e21, \u666e\u9640\u533a, \u666e\u9640\u533a (Putuo), \u4e0a\u6d77\u5e02, 200062, \u4e2d\u56fd", "31.22849230", "121.40211389", "edu", "", "China", "2013"], ["l 1 l 2 l 3 l 4 l 5 ( a ) Class-Agnostic Temporal", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "United States", "2018"], ["Two-Stream Flow-Guided Convolutional Attention Networks for Action Recognition", "", "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"], ["Attend and Interact: Higher-Order Object Interactions for Video Understanding", "", "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"], ["Temporal Action Localization with Pyramid of Score Distribution Features", "", "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"], ["DIY Human Action Data Set Generation", "", "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"], ["Temporal Segment Networks: Towards Good Practices for Deep Action Recognition", "", "Shenzhen Institutes of Advanced Technology", "Shenzhen Institutes of Advanced Technology", "\u4e2d\u56fd\u79d1\u5b66\u9662\u6df1\u5733\u5148\u8fdb\u6280\u672f\u7814\u7a76\u9662, 1068, \u79d1\u7814\u8def, \u6df1\u5733\u5927\u5b66\u57ce, \u4e09\u5751\u6751, \u5357\u5c71\u533a, \u6df1\u5733\u5e02, \u5e7f\u4e1c\u7701, 518000, \u4e2d\u56fd", "22.59805605", "113.98533784", "edu", "", "China", "2016"], ["Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization", "", "Dartmouth College", "Dartmouth College", "Dartmouth College, Tuck Mall, Hanover, Grafton County, New Hampshire, 03755, USA", "43.70479270", "-72.29259090", "edu", "", "United States", "2018"], ["Deep Manifold Learning Combined With Convolutional Neural Networks for Action Recognition", "Guangdong Key Laboratory of Information Security Technology, School of Data and Computer Science, 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"], ["Joint Attention in Driver-Pedestrian Interaction: from Theory to Practice", "", "York University", "York University", "York University, Keele Campus, Campus Walk, North York, Toronto, Ontario, M3J 2S5, Canada", "43.77439110", "-79.50481085", "edu", "", "Canada", "2018"], ["Deep Learning for Video Classification and Captioning", "", "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", "2016"], ["Deep Learning for Fixed Model Reuse", "", "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", "2017"], ["Saliency-Informed Spatio-Temporal Vector of Locally Aggregated Descriptors and Fisher Vectors for Visual Action Recognition", "", "Northumbria University", "Northumbria University", "Northumbria University, Birkdale Close, High Heaton, Newcastle upon Tyne, Tyne and Wear, North East England, England, NE7 7TP, UK", "55.00306320", "-1.57463231", "edu", "", "United Kingdom", "2018"], ["Investigation of Small Group Social Interactions Using Deep Visual Activity-Based Nonverbal Features", "Istituto Italiano di Tecnologia, Genoa, Italy", "Istituto Italiano di Tecnologia", "Istituto Italiano di Tecnologia", "77 Massachusetts Ave, Cambridge, MA 02139, USA", "42.36009100", "-71.09416000", "edu", "", "United States", "2018"], ["Combined Ordered and Improved Trajectories for Large Scale Human Action Recognition", "", "Australian National University", "Australian National University", "Canberra ACT 0200, Australia", "-35.27769990", "149.11852700", "edu", "", "Australia", "2013"], ["Towards Good Practices for Action Video Encoding", "", "Singapore", "Singapore", "Singapore", "1.35208300", "103.81983600", "edu", "", "Singapore", "2014"], ["Denser Trajectories of Anchor Points for Action Recognition", "Department of ECE, National University of 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", "2018"], ["Recurrent Spatial-Temporal Attention Network for Action Recognition in Videos", "Shenzhen College of Advanced Technology, University of Chinese Academy of Sciences, 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"], ["Beyond Temporal Pooling: Recurrence and Temporal Convolutions for Gesture Recognition in Video", "", "Ghent University", "Ghent University", "St. Pietersnieuwstraat 33, 9000 Gent, Belgium", "51.04656190", "3.72791810", "edu", "", "Belgium", "2016"], ["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"], ["Multi-task Joint Learning for Videos in the Wild", "Yonsei University, Seoul, Rebublic of 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", "2018"], ["Improving Human Intention Prediction Using Data Augmentation", "School of Engineering Technology, Purdue University, West Lafayette, IN, 47907, USA", "Purdue University", "Purdue University", "Purdue University, West Stadium Avenue, West Lafayette, Tippecanoe County, Indiana, 47907, USA", "40.43197220", "-86.92389368", "edu", "", "United States", "2018"], ["Shuffle and Learn: Unsupervised Learning Using Temporal Order Verification", "", "Carnegie Mellon University", "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "40.44416190", "-79.94272826", "edu", "", "United States", "2016"], ["Sparse Adversarial Perturbations for Videos", "", "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"], ["MSR-CNN: Applying motion salient region based descriptors for action recognition", "", "Arizona State University", "Arizona State University", "Arizona State University Polytechnic campus, East Texas Avenue, Mesa, Maricopa County, Arizona, 85212, USA", "33.30715065", "-111.67653157", "edu", "", "United States", "2016"], ["Learning to hash-tag videos with Tag2Vec", "", "CVIT, KCIS, IIIT Hyderabad, India", "CVIT, KCIS, IIIT Hyderabad, India", "IIIT, Gachibowli, Gachibowli, Hyderabad, Telangana 500032, India", "17.44509810", "78.34976780", "edu", "", "India", "2016"], ["Three-Dimensional Attention-Based Deep Ranking Model for Video Highlight Detection", "National Laboratory of Pattern Recognition, 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"], ["Pose from Action: Unsupervised Learning of Pose Features based on Motion", "", "Carnegie Mellon University Silicon Valley", "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"], ["Boosting VLAD with Supervised Dictionary Learning and High-Order Statistics", "", "Shenzhen, China", "Shenzhen, China", "Shenzhen, Guangdong, China", "22.54309600", "114.05786500", "edu", "", "China", "2014"], ["Fine-grained Activity Recognition with Holistic and Pose based Features", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "United States", "2014"], ["A Survey on Deep Learning: Algorithms, Techniques, and Applications", "University of Miami, Coral Gables, FL", "University of Miami", "University of Miami", "University of Miami, Theo Dickenson Drive, Coral Gables, Miami-Dade County, Florida, 33124, USA", "25.71733390", "-80.27866887", "edu", "", "United States", "2018"], ["A Dataset To Evaluate The Representations Learned By Video Prediction Models", "", "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", "2018"], ["Flip-Invariant Motion Representation", "", "National Institute of Advanced Industrial Science and Technology", "National Institute of Advanced Industrial Science and Technology", "\u7523\u696d\u6280\u8853\u7dcf\u5408\u7814\u7a76\u6240\uff1b\u897f\u4e8b\u696d\u6240, \u5b66\u5712\u897f\u5927\u901a\u308a, Onogawa housing complex, \u3064\u304f\u3070\u5e02, \u8328\u57ce\u770c, \u95a2\u6771\u5730\u65b9, 305-0051, \u65e5\u672c", "36.05238585", "140.11852361", "edu", "", "Japan", "2017"], ["Bidirectional Multirate Reconstruction for Temporal Modeling in Videos", "", "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", "2017"], ["Deep Adaptive Temporal Pooling for Activity Recognition", "", "Singapore", "Singapore", "Singapore", "1.35208300", "103.81983600", "edu", "", "Singapore", "2018"], ["Video Action Recognition Based on Deeper Convolution Networks with Pair-Wise Frame Motion Concatenation", "", "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"], ["How scenes imply actions in realistic videos?", "Center for Research on Intelligent Perception and Computing, Institute of Automation, National Laboratory of Pattern Recognition, Chinese Academy of Sciences", "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"], ["Action Completion: A Temporal Model for Moment Detection", "", "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", "2018"], ["Temporally Robust Global Motion Compensation by Keypoint-based Congealing", "", "Michigan State University", "Michigan State University", "Michigan State University, Farm Lane, East Lansing, Ingham County, Michigan, 48824, USA", "42.71856800", "-84.47791571", "edu", "", "United States", "2016"], ["Exploring Pooling Strategies based on Idiosyncrasies of Spatio-Temporal Interest Points", "The Graduate Center, City University of New York, New York, NY, USA", "City University of New York", "The City University of New York", "Lehman College of the City University of New York, 250, Bedford Park Boulevard West, Bedford Park, The Bronx, Bronx County, NYC, New York, 10468, USA", "40.87228250", "-73.89489171", "edu", "", "United States", "2015"], ["Weakly Supervised Action Localization by Sparse Temporal Pooling Network", "", "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"], ["Action Sets: Weakly Supervised Action Segmentation without Ordering Constraints", "", "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", "2017"], ["Action and Gesture Temporal Spotting with Super Vector Representation", "", "Shenzhen Institutes of Advanced Technology", "Shenzhen Institutes of Advanced Technology", "\u4e2d\u56fd\u79d1\u5b66\u9662\u6df1\u5733\u5148\u8fdb\u6280\u672f\u7814\u7a76\u9662, 1068, \u79d1\u7814\u8def, \u6df1\u5733\u5927\u5b66\u57ce, \u4e09\u5751\u6751, \u5357\u5c71\u533a, \u6df1\u5733\u5e02, \u5e7f\u4e1c\u7701, 518000, \u4e2d\u56fd", "22.59805605", "113.98533784", "edu", "", "China", "2014"], ["BSN: Boundary Sensitive Network for Temporal Action Proposal Generation", "", "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"], ["Exploring deep learning based solutions in fine grained activity recognition in the wild", "Computer Science Department, University of Southern California, Los Angeles, 90089, United States of America", "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", "2016"], ["AdaScan: Adaptive Scan Pooling in Deep Convolutional Neural Networks for Human Action Recognition in Videos", "", "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"], ["M-PACT: An Open Source Platform for Repeatable Activity Classification Research", "", "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"], ["A BoW-equivalent Recurrent Neural Network for Action Recognition", "", "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"], ["Multi-kernel learning of deep convolutional features for action recognition", "", "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", "2017"], ["Leaving Some Stones Unturned: Dynamic Feature Prioritization for Activity Detection in Streaming Video", "", "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", "2016"], ["Temporal Tessellation: A Unified Approach for Video Analysis", "", "Open University of Israel", "Open University of Israel", "\u05d4\u05d0\u05d5\u05e0\u05d9\u05d1\u05e8\u05e1\u05d9\u05d8\u05d4 \u05d4\u05e4\u05ea\u05d5\u05d7\u05d4, 15, \u05d0\u05d1\u05d0 \u05d7\u05d5\u05e9\u05d9, \u05d7\u05d9\u05e4\u05d4, \u05d2\u05d1\u05e2\u05ea \u05d3\u05d0\u05d5\u05e0\u05e1, \u05d7\u05d9\u05e4\u05d4, \u05de\u05d7\u05d5\u05d6 \u05d7\u05d9\u05e4\u05d4, NO, \u05d9\u05e9\u05e8\u05d0\u05dc", "32.77824165", "34.99565673", "edu", "", "Israel", "2017"], ["Pooled motion features for first-person videos", "", "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"], ["Action Recognition by an Attention-Aware Temporal Weighted Convolutional Neural Network", "", "Microsoft", "Microsoft Corporation, Redmond, WA, USA", "One Microsoft Way, Redmond, WA 98052, USA", "47.64233180", "-122.13693020", "company", "", "United States", "2018"], ["Attribute-based supervised deep learning model for action recognition", "School of Software, 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", "2016"], ["Crowd Scene Understanding from Video: A Survey", "University of Notre Dame, Notre Dame, Indiana", "University of Notre Dame", "University of Notre Dame", "University of Notre Dame du Lac, Holy Cross Drive, Notre Dame, Maple Lane, Saint Joseph County, Indiana, 46556, USA", "41.70456775", "-86.23822026", "edu", "", "United States", "2017"], ["Deep Spatio-temporal Manifold Network for Action Recognition", "", "Beijing, China", "Beijing, China", "Beijing, China", "39.90419990", "116.40739630", "edu", "", "China", "2017"], ["Recognizing unseen actions in a domain-adapted embedding space", "", "Arizona State University", "Arizona State University", "Arizona State University Polytechnic campus, East Texas Avenue, Mesa, Maricopa County, Arizona, 85212, USA", "33.30715065", "-111.67653157", "edu", "", "United States", "2016"], ["Towards an Unequivocal Representation of Actions", "", "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", "2018"], ["Discriminative convolutional Fisher vector network for action recognition", "", "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"], ["Action Classification and Highlighting in Videos", "", "Disney Research Pittsburgh", "Disney Research Pittsburgh", "4720 Forbes Ave, Pittsburgh, PA 15213, USA", "40.44397890", "-79.94646340", "edu", "", "United States", "2017"], ["Power difference template for action recognition", "State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China", "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"], ["Efficient Two-Stream Motion and Appearance 3D CNNs for Video Classification", "", "ETH Zurich", "ETH Zurich", "R\u00e4mistrasse 101, 8092 Z\u00fcrich, Switzerland", "47.37631300", "8.54766990", "edu", "", "Switzerland", "2016"], ["Sports Videos in the Wild (SVW): A video dataset for sports analysis", "", "Michigan State University", "Michigan State University", "Michigan State University, Farm Lane, East Lansing, Ingham County, Michigan, 48824, USA", "42.71856800", "-84.47791571", "edu", "", "United States", "2015"], ["More efficient and effective tricks for deep action recognition", "The Third Research Institute of the Ministry of Public Security, Shanghai, China", "The Third Research Institute of the Ministry of Public Security, Shanghai, China", "The Third Research Institute of the Ministry of Public Security, Shanghai, China", "China, Shanghai, Xuhui, \u5cb3\u9633\u8def76\u53f7", "31.20700600", "121.45196400", "gov", "", "China", "2017"], ["Dimensionality Reduction on Grassmannian via Riemannian Optimization: A Generalized Perspective", "", "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"], ["THETIS: Three Dimensional Tennis Shots a Human Action Dataset", "", "National Technical University of Athens", "National Technical University of Athens", "\u0395\u03b8\u03bd\u03b9\u03ba\u03cc \u039c\u03b5\u03c4\u03c3\u03cc\u03b2\u03b9\u03bf \u03a0\u03bf\u03bb\u03c5\u03c4\u03b5\u03c7\u03bd\u03b5\u03af\u03bf, \u03a3\u03c4\u03bf\u03c5\u03c1\u03bd\u03ac\u03c1\u03b7, \u039c\u03bf\u03c5\u03c3\u03b5\u03af\u03bf, \u0391\u03b8\u03ae\u03bd\u03b1, \u0394\u03ae\u03bc\u03bf\u03c2 \u0391\u03b8\u03b7\u03bd\u03b1\u03af\u03c9\u03bd, \u03a0.\u0395. \u039a\u03b5\u03bd\u03c4\u03c1\u03b9\u03ba\u03bf\u03cd \u03a4\u03bf\u03bc\u03ad\u03b1 \u0391\u03b8\u03b7\u03bd\u03ce\u03bd, \u03a0\u03b5\u03c1\u03b9\u03c6\u03ad\u03c1\u03b5\u03b9\u03b1 \u0391\u03c4\u03c4\u03b9\u03ba\u03ae\u03c2, \u0391\u03c4\u03c4\u03b9\u03ba\u03ae, 11250, \u0395\u03bb\u03bb\u03ac\u03b4\u03b1", "37.98782705", "23.73179733", "edu", "", "Greece", "2013"], ["Learning to tell brake and turn signals in videos using CNN-LSTM structure", "University of California, Merced", "University of California, Merced", "University of California, Merced", "University of California, Merced, Ansel Adams Road, Merced County, California, USA", "37.36566745", "-120.42158888", "edu", "", "United States", "2017"], ["Improving Classification by Improving Labelling: Introducing Probabilistic Multi-Label Object Interaction Recognition", "", "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"], ["Modeling Spatial-Temporal Clues in a Hybrid Deep Learning Framework for Video Classification", "", "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", "2015"], ["Semi-Supervised Learning for Optical Flow with Generative Adversarial Networks", "", "Virginia Tech", "Virginia Tech", "Blacksburg, VA 24061, USA", "37.22838430", "-80.42341670", "edu", "", "United States", "2017"], ["Fine-grained Video Attractiveness Prediction Using Multimodal Deep Learning on a Large Real-world Dataset", "", "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"], ["Shannon information based adaptive sampling for action recognition", "Dept. of Electrical and Computer Engineering & Centre for Intelligent Machines, McGill University, Montreal, Quebec, Canada", "McGill University", "McGill University", "McGill University, Rue Sherbrooke Ouest, Quartier des Spectacles, Ville-Marie, Montr\u00e9al, Agglom\u00e9ration de Montr\u00e9al, Montr\u00e9al (06), Qu\u00e9bec, H3A 3P8, Canada", "45.50397610", "-73.57496870", "edu", "", "Canada", "2016"], ["Dense Optical Flow Prediction from a Static Image", "", "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"], ["Long-term video interpolation with bidirectional predictive 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", "2017"], ["Temporal Action Detection Using a Statistical Language Model", "", "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", "2016"], ["Multi-feature Spectral Clustering with Minimax Optimization", "", "Nanyang Technological University", "Nanyang Technological University", "NTU, Faculty Avenue, Jurong West, Southwest, 637460, Singapore", "1.34841040", "103.68297965", "edu", "", "Singapore", "2014"], ["Hierarchical Video Generation From Orthogonal Information: Optical Flow and Texture", "", "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"], ["Pooling the Convolutional Layers in Deep ConvNets for Video Action Recognition", "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"], ["Pillar Networks for action recognition", "", "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", "2017"], ["A 46.1 fps Global Matching Optical Flow Estimation Processor for Action Recognition in Mobile Devices", "Korea Advanced Institute of Science and Technology (KAIST), School of Electrical Engineering, Daejeon,Republic of Korea", "Korea Advanced Institute of Science and Technology", "Korea Advanced Institute of Science and Technology", "\uce74\uc774\uc2a4\ud2b8, 291, \ub300\ud559\ub85c, \uc628\ucc9c2\ub3d9, \uc628\ucc9c\ub3d9, \uc720\uc131\uad6c, \ub300\uc804, 34141, \ub300\ud55c\ubbfc\uad6d", "36.36971910", "127.36253700", "edu", "", "South Korea", "2018"], ["Self-Supervised Video Representation Learning with Odd-One-Out Networks", "", "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"], ["Video Frame Interpolation by Plug-and-Play Deep Locally Linear Embedding", "", "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", "2018"], ["Action Temporal Localization in Untrimmed Videos via Multi-stage CNNs", "", "Columbia University", "Columbia University", "Columbia University Medical Center, 630, West 168th Street, Washington Heights, Manhattan, Manhattan Community Board 12, New York County, NYC, New York, 10031, USA", "40.84198360", "-73.94368971", "edu", "", "United States", "2016"], ["Sequential Segment Networks for Action Recognition", "Department of Electronic Engineering, 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"], ["Hierarchical Label Inference for Video Classification", "", "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"], ["Multi-modal learning for affective content analysis in movies", "Shanghai Engineering Research Center of Industrial Vision Perception & Intelligent Computing, Shanghai, People\u2019s Republic of China", "Shanghai Engineering Research Center of Industrial Vision Perception & Intelligent Computing, Shanghai, People\u2019s Republic of China", "Shanghai Engineering Research Center of Industrial Vision Perception & Intelligent Computing, Shanghai, People\u2019s Republic of China", "Shanghai, China", "31.23039040", "121.47370210", "edu", "", "China", "2018"], ["Watch, Think and Attend: End-to-End Video Classification via Dynamic Knowledge Evolution Modeling", "Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China", "Chinese Academy of Sciences & University of Chinese Academy of Sciences", "Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China", "China, Beijing, Haidian, Zhongguancun South 1st Alley, \u4e2d\u5173\u6751\u5357\u4e00\u6761", "39.98177000", "116.33008600", "edu", "", "China", "2018"], ["Video Question Answering via Gradually Refined Attention over Appearance and Motion", "Zhejiang University, Hangzhou, China", "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"], ["Ranking Domain-Specific Highlights by Analyzing Edited Videos", "", "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", "2014"], ["Recognizing an Action Using Its Name: A Knowledge-Based Approach", "Zhejiang University, Hangzhou, China", "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"], ["Deep learning based human action recognition: A survey", "School of Control Science and Engineering, Shandong University, Jinan, 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", "2017"], ["Dense Dilated Network for Few Shot Action Recognition", "Shanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai, 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"], ["Sidekick Policy Learning for Active Visual Exploration", "", "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"], ["Recurrent Residual Learning for Action Recognition", "", "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", "2017"], ["Temporal Perceptive Network for Skeleton-Based Action Recognition", "", "Beijing, China", "Beijing, China", "Beijing, China", "39.90419990", "116.40739630", "edu", "", "China", "2017"], ["Mining Spatial and Spatio-Temporal ROIs for Action Recognition", "", "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", "2016"], ["Efficient On-the-fly Category Retrieval using ConvNets and GPUs", "", "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", "2014"], ["Mgn: Multi-Glimpse Network for Action Recognition", "National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences", "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"], ["Incorporating Scalability in Unsupervised Spatio- Temporal Feature Learning", "", "University of California", "University of California", "Berkeley, CA, USA", "37.87189920", "-122.25853990", "edu", "", "United States", "2018"], ["Temporal Sequence Distillation: Towards Few-Frame Action Recognition in Videos", "", "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"], ["Appearance-and-Relation Networks for Video Classification", "", "Computer Vision Laboratory, ETH Zurich, Switzerland", "Computer Vision Laboratory, ETH Zurich, Switzerland", "Sternwartstrasse 7, 8092 Z\u00fcrich, Switzerland", "47.37723980", "8.55216180", "edu", "", "Malaysia", "2017"], ["Temporal Action Detection with Structured Segment Networks", "", "Computer Vision Laboratory, ETH Zurich, Switzerland", "Computer Vision Laboratory, ETH Zurich, Switzerland", "Sternwartstrasse 7, 8092 Z\u00fcrich, Switzerland", "47.37723980", "8.55216180", "edu", "", "Malaysia", "2017"], ["Human activity recognition using an ensemble of support vector machines", "Department of Electrical and Computer Engineering, University of Windsor, 401 Sunset Avenue, Windsor, N9B 3P4, Canada", "University of Windsor", "University of Windsor", "Bridge AA, Ambassador Bridge, Windsor, Essex, Ontario, N9C 2J9, Canada", "42.30791465", "-83.07176915", "edu", "", "Canada", "2016"], ["Learning Match Kernels on Grassmann Manifolds for Action Recognition", "University of Electronic Science and Technology of China, Chendu, 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", "2019"], ["Where and When to Look? Spatio-temporal Attention for Action Recognition in Videos", "", "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", "2018"], ["Learning to Estimate Pose by Watching Videos", "", "IIT Kanpur", "IIT Kanpur", "Kalyanpur, Kanpur, Uttar Pradesh 208016, India", "26.51233880", "80.23290000", "edu", "", "India", "2017"], ["A spiking thalamus model for form and motion processing of images", "HRL Laboratories, LLC, Information Systems and Sciences Lab, Malibu, CA 90265 USA", "HRL Laboratories, Malibu, CA", "HRL Laboratories, LLC, Information Systems and Sciences Lab, Malibu, CA 90265 USA", "4797, 3011 Malibu Canyon Rd, Malibu, CA 90265, United States", "34.04286290", "-118.69525780", "company", "", "United States", "2013"], ["Much Ado About Time: Exhaustive Annotation of Temporal Data", "", "Carnegie Mellon University Silicon Valley", "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"], ["RECOGNITIONWITH GRADIENT BOUNDARY CONVOLUTIONAL NETWORK", "", "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", "2017"], ["Hand Detection and Tracking in Videos for Fine-Grained Action Recognition", "", "University of Electro-Communications", "The University of Electro-Communications", "\u96fb\u6c17\u901a\u4fe1\u5927\u5b66, \u7532\u5dde\u8857\u9053, \u8abf\u5e03\u5e02, \u6771\u4eac\u90fd, \u95a2\u6771\u5730\u65b9, 182-0026, \u65e5\u672c", "35.65729570", "139.54255868", "edu", "", "Japan", "2014"], ["Multi-Stream Multi-Class Fusion of Deep Networks for Video Classification", "Fudan University, Shanghai, China", "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", "2016"], ["LikeNet: A Siamese Motion Estimation Network Trained in an Unsupervised Way", "", "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", "2018"], ["Learning Person Trajectory Representations for Team Activity Analysis", "", "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"], ["Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks", "", "Microsoft Research Asia", "Microsoft Research Asia", "1 Memorial Dr, Cambridge, MA 02142, USA", "42.36142560", "-71.08120920", "company", "", "United States", "2017"], ["Impact of temporal subsampling on accuracy and performance in practical video classification", "", "University of Bologna", "University of Bologna", "Via Zamboni, 33, 40126 Bologna BO, Italy", "44.49623180", "11.35415700", "edu", "", "", "2017"], ["Learning End-to-end Video Classification with Rank-Pooling", "", "Australian National University", "Australian National University", "Canberra ACT 0200, Australia", "-35.27769990", "149.11852700", "edu", "", "Australia", "2016"], ["Going Deeper into First-Person Activity Recognition", "", "Carnegie Mellon University Silicon Valley", "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"], ["Motion Feature Network: Fixed Motion Filter for Action Recognition", "", "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"], ["DECK: Discovering Event Composition Knowledge from Web Images for Zero-Shot Event Detection and Recounting in Videos", "", "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"], ["Dense body part trajectories for human action recognition", "Vision & Sensing Group, HCC Lab, ESTeM, University of Canberra, Australia", "University of Canberra", "University of Canberra", "University of Canberra, University Drive, Bruce, Belconnen, Australian Capital Territory, 2617, Australia", "-35.23656905", "149.08446994", "edu", "", "Australia", "2014"], ["Mixture Statistic Metric Learning for Robust Human Action and Expression Recognition", "Department of Electrical and Computer Engineering, Stevens Institute of Technology, Hoboken, NJ, USA", "Stevens Institute of Technology", "Stevens Institute of Technology", "Stevens Institute of Technology, River Terrace, Hoboken, Hudson County, New Jersey, 07030, USA", "40.74225200", "-74.02709490", "edu", "", "United States", "2018"], ["Controllable Video Generation with Sparse Trajectories", "", "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"], ["Learning motion and content-dependent features with convolutions for action recognition", "School of Information Science and Engineering, Hunan city University, Yiyang, 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", "2015"], ["Activity Understanding and Labeling in Natural Videos", "", "University of California", "University of California", "Berkeley, CA, USA", "37.87189920", "-122.25853990", "edu", "", "United States", "2016"], ["What do 15,000 object categories tell us about classifying and localizing actions?", "University of Amsterdam, The Netherlands", "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"], ["Content-Attention Representation by Factorized Action-Scene Network for Action Recognition", "Beijing Laboratory of Intelligent Information Technology, School of Computer Science, Beijing Institute of Technology, Beijing, China", "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", "2018"], ["Deep Learning for Detecting Multiple Space-Time Action Tubes in Videos", "", "Oxford, UK", "Oxford, UK", "Oxford, UK", "51.75202090", "-1.25772630", "edu", "", "", "2016"], ["StNet: Local and Global Spatial-Temporal Modeling for Action Recognition", "", "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 have we learned from deep representations for action recognition?", "", "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"], ["Action Recognition with 3D ConvNet-GRU Architecture", "Institute of Optics and Electronics, Chinese Academy of Science, University of Electronic Science and Technology of China, University of Chinese Academy of Sciences", "Chinese Academy of Science", "Chinese Academy of Science", "52 Sanlihe Rd, Xicheng Qu, Beijing Shi, China", "39.91063270", "116.33563210", "edu", "", "China", "2018"], ["DMMLN: A deep multi-task and metric learning based network for video classification", "National Digital Switching System Engineering and Technological Research Center, Zhengzhou, China", "National Digital Switching System Engineering and Technological Research Center, Zhengzhou, China", "National Digital Switching System Engineering and Technological Research Center, Zhengzhou, China", "Zhengzhou, Henan, China", "34.74661100", "113.62532800", "edu", "", "China", "2017"], ["Attention-based LSTM with Semantic Consistency for Videos Captioning", "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", "2016"], ["Human action recognition with DeepAction Kernel Gaussian Process", "Guangdong Key Lab of Comp. Vis. & Vi. Real., Shenzhen Institutes of Advanced Technology, CAS, China", "Shenzhen Institutes of Advanced Technology", "Shenzhen Institutes of Advanced Technology", "\u4e2d\u56fd\u79d1\u5b66\u9662\u6df1\u5733\u5148\u8fdb\u6280\u672f\u7814\u7a76\u9662, 1068, \u79d1\u7814\u8def, \u6df1\u5733\u5927\u5b66\u57ce, \u4e09\u5751\u6751, \u5357\u5c71\u533a, \u6df1\u5733\u5e02, \u5e7f\u4e1c\u7701, 518000, \u4e2d\u56fd", "22.59805605", "113.98533784", "edu", "", "China", "2016"], ["Large Video Event Ontology Browsing, Search and Tagging (EventNet Demo)", "", "Columbia University", "Columbia University", "Columbia University Medical Center, 630, West 168th Street, Washington Heights, Manhattan, Manhattan Community Board 12, New York County, NYC, New York, 10031, USA", "40.84198360", "-73.94368971", "edu", "", "United States", "2015"], ["Audio-Visual Scene Analysis with Self-Supervised Multisensory Features", "", "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"], ["A Torch Library for Action Recognition and Detection Using CNNs and LSTMs", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "United States", "2016"], ["Dual Motion GAN for Future-Flow Embedded Video Prediction", "", "Carnegie Mellon University Silicon Valley", "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"], ["Exploiting Image-trained CNN Architectures for Unconstrained Video Classification", "", "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", "2015"], ["How Do We Evaluate the Quality of Computational Editing Systems", "", "University of Wisconsin Madison", "University of Wisconsin Madison", "University of Wisconsin-Madison, Marsh Lane, Madison, Dane County, Wisconsin, 53705-2221, USA", "43.07982815", "-89.43066425", "edu", "", "United States", "2014"], ["Action Prediction From Videos via Memorizing Hard-to-Predict Samples", "", "Northeastern University", "Northeastern University", "Snell Library, 360, Huntington Avenue, Roxbury Crossing, Fenway, Boston, Suffolk County, Massachusetts, 02115, USA", "42.33836680", "-71.08793524", "edu", "", "United States", "2018"], ["DLSTM approach to video modeling with hashing for large-scale video retrieval", "Department of Computer Science, University of Central Florida, Orlando, 32816, United States of America", "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", "2016"], ["Trajectory-based 3 D Convolutional Descriptors for Action Recognition in Videos", "", "Jiangsu University", "Jiangsu University", "\u6c5f\u82cf\u5927\u5b66, 301, \u5b66\u5e9c\u8def, \u4eac\u53e3\u533a, \u8c61\u5c71\u8857\u9053, \u4eac\u53e3\u533a (Jingkou), \u9547\u6c5f\u5e02 / Zhenjiang, \u6c5f\u82cf\u7701, 212013, \u4e2d\u56fd", "32.20302965", "119.50968362", "edu", "", "China", "2018"], ["Learning Optical Flow via Dilated Networks and Occlusion Reasoning", "", "University of California, Merced", "University of California, Merced", "University of California, Merced, Ansel Adams Road, Merced County, California, USA", "37.36566745", "-120.42158888", "edu", "", "United States", "2018"], ["Articulated motion discovery using pairs of trajectories", "", "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", "2015"], ["Player Experience Extraction from Gameplay Video", "", "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"], ["Learning a joint discriminative-generative model for action recognition", "Vision Semantics Ltd, UK", "Vision Semantics Ltd, UK", "Vision Semantics Ltd, UK", "United Kingdom", "55.37805100", "-3.43597300", "edu", "", "United Kingdom", "2015"], ["Revisiting hand-crafted feature for action recognition: a set of improved dense trajectories", "", "Hiroshima University", "Hiroshima University", "Hiroshima University\u3000\u5e83\u5cf6\u5927\u5b66 \u6771\u5e83\u5cf6\u30ad\u30e3\u30f3\u30d1\u30b9, \u51fa\u4f1a\u3044\u306e\u9053\u3000Deai-no-michi Str., \u897f\u6761\u4e0b\u898b, \u6771\u5e83\u5cf6\u5e02, \u5e83\u5cf6\u770c, \u4e2d\u56fd\u5730\u65b9, 739-0047, \u65e5\u672c", "34.40197660", "132.71231950", "edu", "", "Japan", "2017"], ["Video Frame Interpolation Using Recurrent Convolutional Layers", "Shanghai Jiao Tong University, Institute of Image Communication and Network Engineering", "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"], ["Generalized Rank Pooling for Activity Recognition", "", "Australian National University", "Australian National University", "Canberra ACT 0200, Australia", "-35.27769990", "149.11852700", "edu", "", "Australia", "2017"], ["Combining nonuniform sampling, hybrid super vector, and random forest with discriminative decision trees for action recognition", "Samsung R&D Institute, China", "Samsung R&D Institute, China", "Samsung R&D Institute, China", "233 Tianhe N Rd, TianHeBei, Tianhe Qu, Guangzhou Shi, Guangdong Sheng, China, 510610", "23.14157130", "113.32485930", "company", "", "China", "2015"], ["Detecting Social Actions of Fruit Flies", "", "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", "2014"], ["IMOTION - Searching for Video Sequences Using Multi-Shot Sketch Queries", "", "University of Basel", "University of Basel", "Faculty of Psychology, University of Basel, 60-62, Missionsstrasse, Grossbasel, Am Ring, Basel, Basel-Stadt, 4055, Schweiz/Suisse/Svizzera/Svizra", "47.56126510", "7.57529610", "edu", "", "Switzerland", "2016"], ["Layer-Centric Memory Reuse and Data Migration for Extreme-Scale Deep Learning on Many-Core Architectures", "National University of 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", "2018"], ["Unsupervised Learning of Video Representations using LSTMs", "", "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", "2015"], ["Video2vec: Learning semantic spatio-temporal embeddings for video representation", "", "Arizona State University", "Arizona State University", "Arizona State University Polytechnic campus, East Texas Avenue, Mesa, Maricopa County, Arizona, 85212, USA", "33.30715065", "-111.67653157", "edu", "", "United States", "2016"], ["Human action and event recognition using a novel descriptor based on improved dense trajectories", "IIIT Chittoor, SriCity, Andhra Pradesh, India", "IIIT Chittoor, SriCity, Andhra Pradesh, India", "IIIT Chittoor, SriCity, Andhra Pradesh, India", "630 Gnan Marg, Sri City, Andhra Pradesh 517646, India", "13.55681710", "80.02612830", "edu", "", "", "2017"], ["Attention-Based Temporal Weighted Convolutional Neural Network for Action Recognition", "", "Microsoft", "Microsoft Corporation, Redmond, WA, USA", "One Microsoft Way, Redmond, WA 98052, USA", "47.64233180", "-122.13693020", "company", "", "United States", "2018"], ["Action Recognition by Weakly-Supervised Discriminative Region Localization.", "", "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", "2014"], ["Real-time Action Recognition with Dissimilarity-based Training of Specialized Module Networks", "", "Alexandria University", "Alexandria University", "\u062c\u0627\u0645\u0639\u0629 \u0627\u0644\u0625\u0633\u0643\u0646\u062f\u0631\u064a\u0629, \u0627\u0644\u0643\u0648\u0631\u0646\u064a\u0634, \u0625\u0628\u0631\u0627\u0647\u064a\u0645\u064a\u0629, \u0627\u0644\u0625\u0633\u0643\u0646\u062f\u0631\u064a\u0629, 21522, \u0645\u0635\u0631", "31.21051105", "29.91314562", "edu", "", "Egypt", "2018"], ["Action Anticipation with RBF Kernelized Feature Mapping RNN", "", "Australian National University", "Australian National University", "Canberra ACT 0200, Australia", "-35.27769990", "149.11852700", "edu", "", "Australia", "2018"], ["CTC Network with Statistical Language Modeling for Action Sequence Recognition in Videos", "Tokyo Institute of Technology, Tokyo, Japan", "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", "2017"], ["Precise Temporal Action Localization by Evolving Temporal Proposals", "", "Shanghai, China", "Shanghai, China", "Shanghai, China", "31.23039040", "121.47370210", "edu", "", "", "2018"], ["Tube ConvNets: Better exploiting motion for action recognition", "School of Electronic and Computer Engineering, Peking University", "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"], ["Depth2Action: Exploring Embedded Depth for Large-Scale Action Recognition", "", "University of California, Merced", "University of California, Merced", "University of California, Merced, Ansel Adams Road, Merced County, California, USA", "37.36566745", "-120.42158888", "edu", "", "United States", "2016"], ["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"], ["Disentangling Motion, Foreground and Background Features in Videos", "", "Facebook", "Facebook", "250 Bryant St, Mountain View, CA 94041, USA", "37.39367170", "-122.08072620", "company", "Facebook, Mountain View, CA", "United States", "2017"], ["Towards temporal adaptive representation for video action recognition", "University of Texas at San Antonio, San Antonio, Texas", "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", "2016"], ["A Dataset and a Technique for Generalized Nuclear Segmentation for Computational Pathology", "IIT Guwahati, Guwahati, India", "Indian Institute of Technology Guwahati", "IIT Guwahati, Guwahati, India", "Indian Institute of Technology Guwahati - IIT Guwahati, NH27, Amingaon, Guwahati, Kamrup, Assam, 781015, India", "26.19247875", "91.69463569", "edu", "", "India", "2017"], ["Multimodal feature fusion for CNN-based gait recognition: an empirical comparison", "", "University of Cordoba", "University of Cordoba", "Av. de Medina Azahara, 5, 14071 C\u00f3rdoba, Spain", "37.88469010", "-4.78850280", "edu", "", "", "2018"], ["Joint Attributes and Event Analysis for Multimedia Event Detection", "University of Technology Sydney, Ultimo, NSW, Australia", "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", "2018"], ["Object and Text-guided Semantics for CNN-based Activity Recognition", "", "U.S. Army Research Laboratory, Adelphi, MD, USA", "U.S. Army Research Laboratory, Adelphi, MD, USA", "2800 Powder Mill Rd, Adelphi, MD 20783, USA", "39.02985870", "-76.96380270", "mil", "", "United States", "2018"], ["Unsupervised Learning and Segmentation of Complex Activities from Video", "", "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"], ["LPM for Fast Action Recognition with Large Number of Classes", "", "University of Ottawa", "University of Ottawa", "University of Ottawa, 1, Stewart Street, Byward Market, Lowertown, Rideau-Vanier, Ottawa, Ontario, K1N 6N5, Canada", "45.42580475", "-75.68740118", "edu", "", "Canada", "2013"], ["Recurrent Temporal Sparse Autoencoder for attention-based action recognition", "Image Processing Center, Beihang University, Beijing, China", "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", "2016"], ["A Key Volume Mining Deep Framework for Action Recognition", "", "Shenzhen Institutes of Advanced Technology", "Shenzhen Institutes of Advanced Technology", "\u4e2d\u56fd\u79d1\u5b66\u9662\u6df1\u5733\u5148\u8fdb\u6280\u672f\u7814\u7a76\u9662, 1068, \u79d1\u7814\u8def, \u6df1\u5733\u5927\u5b66\u57ce, \u4e09\u5751\u6751, \u5357\u5c71\u533a, \u6df1\u5733\u5e02, \u5e7f\u4e1c\u7701, 518000, \u4e2d\u56fd", "22.59805605", "113.98533784", "edu", "", "China", "2016"], ["Spatio-Temporal Scale Selection in Video Data", "Computational Brain Science Lab, Department of Computational Science and Technology, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden", "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", "2017"], ["A Temporally-Aware Interpolation Network for Video Frame Inpainting", "", "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"], ["MovieScope : Movie trailer classification using Deep Neural Networks", "", "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", "2017"], ["Soft video parsing by label distribution learning", "Department of Computer Science and Engineering, Southeast University, Nanjing, China", "Southeast University", "Southeast University", "SEU, \u4f53\u80b2\u9986\u8def, \u65b0\u8857\u53e3, \u6708\u5b63\u56ed, \u7384\u6b66\u533a, \u5357\u4eac\u5e02, \u6c5f\u82cf\u7701, 210008, \u4e2d\u56fd", "32.05752790", "118.78682252", "edu", "", "China", "2017"], ["Joint Network based Attention for Action Recognition", "", "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"], ["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"], ["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"], ["An Integrated Signature-Based Framework for Efficient Visual Similarity Detection and Measurement in Video Shots", "University of Nottingham (Malaysia Campus), Malaysia", "University of Nottingham (Malaysia Campus)", "University of Nottingham (Malaysia Campus), Malaysia", "B34, 43500 Semenyih, Selangor, Malaysia", "2.94513320", "101.87609130", "edu", "", "Malaysia", "2018"], ["Towards Usable Multimedia Event Detection", "", "Carnegie Mellon University Silicon Valley", "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"], ["The Open World of Micro-Videos", "", "Carnegie Mellon University Silicon Valley", "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"], ["Exploiting Objects with LSTMs for Video Categorization", "NTT Media Intelligence Laboratories, Tokyo, Japan", "NTT Media Intelligence Laboratories, Tokyo, Japan", "NTT Media Intelligence Laboratories, Tokyo, Japan", "Tokyo, Japan", "35.68948750", "139.69170640", "company", "", "Japan", "2016"], ["Situation Recognition: Visual Semantic Role Labeling for Image Understanding", "", "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"], ["Spatio-temporal human action localisation and instance segmentation in temporally untrimmed videos", "", "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"], ["Predicting the Future with Transformational States", "", "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", "2018"], ["Bi-Level Semantic Representation Analysis for Multimedia Event Detection", "Xiamen University of Technology, Xiamen, China", "Xiamen University of Technology", "Xiamen University of Technology, Xiamen 361024, China", "600 Ligong Rd, Jimei Qu, Xiamen Shi, Fujian Sheng, China, 361024", "24.62053900", "118.08463100", "edu", "", "China", "2017"], ["Discriminative Action States Discovery for Online Action Recognition", "School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore", "Nanyang Technological University", "Nanyang Technological University", "NTU, Faculty Avenue, Jurong West, Southwest, 637460, Singapore", "1.34841040", "103.68297965", "edu", "", "Singapore", "2016"], ["From Lifestyle Vlogs to Everyday Interactions", "", "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"], ["CUHK & SIAT Submission for THUMOS 15 Action Recognition Challenge", "", "Shenzhen Institutes of Advanced Technology", "Shenzhen Institutes of Advanced Technology", "\u4e2d\u56fd\u79d1\u5b66\u9662\u6df1\u5733\u5148\u8fdb\u6280\u672f\u7814\u7a76\u9662, 1068, \u79d1\u7814\u8def, \u6df1\u5733\u5927\u5b66\u57ce, \u4e09\u5751\u6751, \u5357\u5c71\u533a, \u6df1\u5733\u5e02, \u5e7f\u4e1c\u7701, 518000, \u4e2d\u56fd", "22.59805605", "113.98533784", "edu", "", "China", "2015"], ["Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding", "", "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"], ["Spatiotemporal Multi-Task Network for Human Activity Understanding", "Zhejiang University, Hangzhou, China", "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"], ["Pulling Actions out of Context : Explicit Separation for Effective Combination", "", "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", ""], ["Reconstruction Dataset for Synchronization and Localization", "", "Carnegie Mellon University Silicon Valley", "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"], ["Temporally enhanced image object proposals for videos", "School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore", "Nanyang Technological University", "Nanyang Technological University", "NTU, Faculty Avenue, Jurong West, Southwest, 637460, Singapore", "1.34841040", "103.68297965", "edu", "", "Singapore", "2017"], ["shuttleNet: A biologically-inspired RNN with loop connection and parameter sharing", "", "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"], ["Real-Time Action Recognition with Enhanced Motion Vector CNNs", "", "ETH Zurich", "ETH Zurich", "R\u00e4mistrasse 101, 8092 Z\u00fcrich, Switzerland", "47.37631300", "8.54766990", "edu", "", "Switzerland", "2016"], ["Attentional Pooling for Action Recognition", "", "Carnegie Mellon University", "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "40.44416190", "-79.94272826", "edu", "", "United States", "2017"], ["Fast-BoW: Scaling Bag-of-Visual-Words 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"], ["Matching video net: Memory-based embedding for video action recognition", "Graduate School of Convergence Science and Technology, Seoul National University, Seoul, Korea", "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"], ["Now You Shake Me : Towards Automatic 4 D Cinema", "", "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"], ["Overview: Video recognition from handcrafted method to deep learning method", "School of Communication and Information Engineering, Shanghai University, 200444, China", "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", "2016"], ["Exploring synonyms as context in zero-shot action recognition", "Vision Semantics Ltd", "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", "2016"], ["Two-Stream Convolutional Networks for Dynamic Texture Synthesis", "", "York University", "York University", "York University, Keele Campus, Campus Walk, North York, Toronto, Ontario, M3J 2S5, Canada", "43.77439110", "-79.50481085", "edu", "", "Canada", "2017"], ["DVD: Constructing a Discriminative Video Descriptor by Convolving Frame Features", "McGill University, School of Computer Science, Montr\u00e9al, Canada", "McGill University", "McGill University", "McGill University, Rue Sherbrooke Ouest, Quartier des Spectacles, Ville-Marie, Montr\u00e9al, Agglom\u00e9ration de Montr\u00e9al, Montr\u00e9al (06), Qu\u00e9bec, H3A 3P8, Canada", "45.50397610", "-73.57496870", "edu", "", "Canada", "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"], ["Video similarity detection using fixed-length Statistical Dominant Colour Profile (SDCP) signatures", "University of Lincoln, Lincoln, UK", "University of Lincoln", "University of Lincoln", "University of Lincoln, Brayford Way, Whitton Park, New Boultham, Lincoln, Lincolnshire, East Midlands, England, LN6 7TS, UK", "53.22853665", "-0.54873472", "edu", "", "United Kingdom", "2017"], ["What Can We Learn about Motion Videos from Still Images?", "School of Computer Science and Technology, Tianjin University, Tianjin, China", "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", "2014"], ["Unsupervised convolutional neural networks for motion estimation", "", "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", "2016"], ["Convolutions through time for multi-label movie genre classification", "Pontif\u00edcia Universidade Cat\u00f3lica do RS, Porto Alegre-RS, Brazil", "Pontif\u00edcia Universidade Cat\u00f3lica do RS, Porto Alegre-RS, Brazil", "Pontif\u00edcia Universidade Cat\u00f3lica do RS, Porto Alegre-RS, Brazil", "Av. Ipiranga, 6681 - Partenon, Porto Alegre - RS, 90619-900, Brazil", "-30.05934460", "-51.17349120", "edu", "", "Brazil", "2017"], ["Benchmarking a Multimodal and Multiview and Interactive Dataset for Human Action Recognition", "School of Electronic Information Engineering, Tianjin University, Tianjin, China", "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"], ["DiscrimNet: Semi-Supervised Action Recognition from Videos using Generative Adversarial Networks", "", "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"], ["EXMOVES: Mid-level Features for Efficient Action Recognition and Video Analysis", "Computer Science Department, Dartmouth College, Hanover, USA", "Dartmouth College", "Dartmouth College", "Dartmouth College, Tuck Mall, Hanover, Grafton County, New Hampshire, 03755, USA", "43.70479270", "-72.29259090", "edu", "", "United States", "2016"]]}
|
