{"list":"other","total":73,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1604.07379","title":"Context Encoders: Feature Learning by Inpainting","created":"2016-04-25","cited_by_count":1428},{"id":"1603.09246","title":"Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles","created":"2016-03-30","cited_by_count":1382},{"id":"1906.05849","title":"Contrastive Multiview Coding","created":"2019-06-13","cited_by_count":1301},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"1908.08530","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","created":"2019-08-22","cited_by_count":954},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"1907.10529","title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","created":"2019-07-24","cited_by_count":834},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"1811.10830","title":"From Recognition to Cognition: Visual Commonsense Reasoning","created":"2018-11-27","cited_by_count":556},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"1705.08168","title":"Look, Listen and Learn","created":"2017-05-23","cited_by_count":458},{"id":"1908.06066","title":"Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training","created":"2019-08-16","cited_by_count":451},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"1808.01340","title":"A Short Note about Kinetics-600","created":"2018-08-03","cited_by_count":333},{"id":"1711.08496","title":"Temporal Relational Reasoning in Videos","created":"2017-11-22","cited_by_count":324},{"id":"1812.02707","title":"Video Action Transformer Network","created":"2018-12-06","cited_by_count":316},{"id":"1907.06987","title":"A Short Note on the Kinetics-700 Human Action Dataset","created":"2019-07-15","cited_by_count":310},{"id":"1512.02902","title":"MovieQA: Understanding Stories in Movies through Question-Answering","created":"2015-12-09","cited_by_count":304},{"id":"1904.02811","title":"Video Classification with Channel-Separated Convolutional Networks","created":"2019-04-04","cited_by_count":290},{"id":"1903.07593","title":"Learning Correspondence from the Cycle-Consistency of Time","created":"2019-03-18","cited_by_count":269},{"id":"1912.06992","title":"Action Genome: Actions as Composition of Spatio-temporal Scene Graphs","created":"2019-12-15","cited_by_count":250},{"id":"1807.00230","title":"Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization","created":"2018-06-30","cited_by_count":249},{"id":"1812.05038","title":"Long-Term Feature Banks for Detailed Video Understanding","created":"2018-12-12","cited_by_count":239},{"id":"2006.14613","title":"Space-Time Correspondence as a Contrastive Random Walk","created":"2020-06-25","cited_by_count":239},{"id":"1806.01810","title":"Videos as Space-Time Region Graphs","created":"2018-06-05","cited_by_count":221},{"id":"1510.07945","title":"Learning Multi-Domain Convolutional Neural Networks for Visual Tracking","created":"2015-10-27","cited_by_count":209},{"id":"2007.10937","title":"MovieNet: A Holistic Dataset for Movie Understanding","created":"2020-07-21","cited_by_count":206},{"id":"1704.07333","title":"Detecting and Recognizing Human-Object Interactions","created":"2017-04-24","cited_by_count":199},{"id":"2007.15649","title":"Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild","created":"2020-07-30","cited_by_count":152},{"id":"2001.08740","title":"Audiovisual SlowFast Networks for Video Recognition","created":"2020-01-23","cited_by_count":146},{"id":"1904.05349","title":"H+O: Unified Egocentric Recognition of 3D Hand-Object Poses and Interactions","created":"2019-04-10","cited_by_count":141},{"id":"1804.09066","title":"ECO: Efficient Convolutional Network for Online Video Understanding","created":"2018-04-24","cited_by_count":115},{"id":"2001.04583","title":"EGO-TOPO: Environment Affordances from Egocentric Video","created":"2020-01-14","cited_by_count":111},{"id":"2005.04208","title":"Condensed Movies: Story Based Retrieval with Contextual Embeddings","created":"2020-05-08","cited_by_count":95},{"id":"1812.01289","title":"Timeception for Complex Action Recognition","created":"2018-12-04","cited_by_count":89},{"id":"1807.10982","title":"Actor-Centric Relation Network","created":"2018-07-28","cited_by_count":87},{"id":"1704.02895","title":"ActionVLAD: Learning spatio-temporal aggregation for action classification","created":"2017-04-10","cited_by_count":73},{"id":"1712.06761","title":"MovieGraphs: Towards Understanding Human-Centric Situations from Videos","created":"2017-12-19","cited_by_count":67},{"id":"1806.06157","title":"Object Level Visual Reasoning in Videos","created":"2018-06-16","cited_by_count":67},{"id":"2004.07485","title":"Asynchronous Interaction Aggregation for Action Detection","created":"2020-04-16","cited_by_count":65},{"id":"1912.00998","title":"A Multigrid Method for Efficiently Training Video Models","created":"2019-12-02","cited_by_count":52},{"id":"1904.09288","title":"STEP: Spatio-Temporal Progressive Learning for Video Action Detection","created":"2019-04-19","cited_by_count":51},{"id":"1411.6031","title":"Finding Action Tubes","created":"2014-11-21","cited_by_count":50},{"id":"1412.6056","title":"Unsupervised Learning of Spatiotemporally Coherent Metrics","created":"2014-12-18","cited_by_count":46},{"id":"1812.03544","title":"A Structured Model For Action Detection","created":"2018-12-09","cited_by_count":43},{"id":"1711.06330","title":"Attend and Interact: Higher-Order Object Interactions for Video Understanding","created":"2017-11-16","cited_by_count":37},{"id":"1910.11009","title":"A Graph-Based Framework to Bridge Movies and Synopses","created":"2019-10-24","cited_by_count":31},{"id":"1512.01848","title":"Rank Pooling for Action Recognition","created":"2015-12-06","cited_by_count":29},{"id":"2003.13594","title":"Speech2Action: Cross-modal Supervision for Action Recognition","created":"2020-03-30","cited_by_count":26},{"id":"1704.04224","title":"Spatial Memory for Context Reasoning in Object Detection","created":"2017-04-13","cited_by_count":22}],"next_cursor":null}