{"list":"other","total":53,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2001.07685","title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","created":"2020-01-21","cited_by_count":2085},{"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":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1911.04252","title":"Self-training with Noisy Student improves ImageNet classification","created":"2019-11-11","cited_by_count":1311},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"1408.5882","title":"Convolutional Neural Networks for Sentence Classification","created":"2014-08-25","cited_by_count":1127},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"1602.00763","title":"Simple Online and Realtime Tracking","created":"2016-02-02","cited_by_count":868},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"1604.02808","title":"NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis","created":"2016-04-11","cited_by_count":686},{"id":"1905.04757","title":"NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding","created":"2019-05-12","cited_by_count":533},{"id":"1811.11742","title":"3D human pose estimation in video with temporal convolutions and semi-supervised training","created":"2018-11-28","cited_by_count":403},{"id":"1705.03098","title":"A simple yet effective baseline for 3d human pose estimation","created":"2017-05-08","cited_by_count":401},{"id":"2003.14111","title":"Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition","created":"2020-03-31","cited_by_count":343},{"id":"1711.08496","title":"Temporal Relational Reasoning in Videos","created":"2017-11-22","cited_by_count":324},{"id":"1812.01601","title":"Learning 3D Human Dynamics from Video","created":"2018-12-04","cited_by_count":316},{"id":"2004.06704","title":"FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding","created":"2020-04-14","cited_by_count":234},{"id":"1801.03150","title":"Moments in Time Dataset: one million videos for event understanding","created":"2018-01-09","cited_by_count":215},{"id":"1811.09795","title":"Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles","created":"2018-11-24","cited_by_count":149},{"id":"1803.08225","title":"PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model","created":"2018-03-22","cited_by_count":133},{"id":"1906.11415","title":"Few-Shot Video Classification via Temporal Alignment","created":"2019-06-27","cited_by_count":125},{"id":"1912.05534","title":"Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition","created":"2019-12-11","cited_by_count":117},{"id":"1909.11825","title":"Unsupervised Domain Adaptation through Self-Supervision","created":"2019-09-26","cited_by_count":116},{"id":"2007.00394","title":"The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Pose","created":"2020-07-01","cited_by_count":95},{"id":"2010.05599","title":"MS$^2$L: Multi-Task Self-Supervised Learning for Skeleton Based Action Recognition","created":"2020-10-12","cited_by_count":92},{"id":"2007.10730","title":"Video Representation Learning by Recognizing Temporal Transformations","created":"2020-07-21","cited_by_count":83},{"id":"1912.00381","title":"Gate-Shift Networks for Video Action Recognition","created":"2019-12-01","cited_by_count":76},{"id":"1812.00442","title":"Deep Cosine Metric Learning for Person Re-Identification","created":"2018-12-02","cited_by_count":73},{"id":"1812.02699","title":"Online Model Distillation for Efficient Video Inference","created":"2018-12-06","cited_by_count":60},{"id":"1904.04571","title":"3DPeople: Modeling the Geometry of Dressed Humans","created":"2019-04-09","cited_by_count":58},{"id":"1908.04781","title":"Predicting 3D Human Dynamics from Video","created":"2019-08-13","cited_by_count":51},{"id":"1912.01001","title":"View-Invariant Probabilistic Embedding for Human Pose","created":"2019-12-02","cited_by_count":47},{"id":"1611.08461","title":"Discriminative Correlation Filter with Channel and Spatial Reliability","created":"2016-11-25","cited_by_count":45},{"id":"1909.07945","title":"ProtoGAN: Towards Few Shot Learning for Action Recognition","created":"2019-09-17","cited_by_count":41},{"id":"1801.09086","title":"A Generative Approach to Zero-Shot and Few-Shot Action Recognition","created":"2018-01-27","cited_by_count":39},{"id":"1912.07249","title":"Mimetics: Towards Understanding Human Actions Out of Context","created":"2019-12-16","cited_by_count":32},{"id":"2008.04524","title":"Vid2Player: Controllable Video Sprites that Behave and Appear like Professional Tennis Players","created":"2020-08-11","cited_by_count":30},{"id":"2007.13303","title":"Reconstructing NBA Players","created":"2020-07-27","cited_by_count":24},{"id":"2012.01405","title":"Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization","created":"2020-12-02","cited_by_count":19},{"id":"2004.10141","title":"TAEN: Temporal Aware Embedding Network for Few-Shot Action Recognition","created":"2020-04-21","cited_by_count":12},{"id":"1812.10000","title":"Similarity R-C3D for Few-shot Temporal Activity Detection","created":"2018-12-25","cited_by_count":2}],"next_cursor":null}