{"list":"other","total":52,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"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":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"1711.09577","title":"Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?","created":"2017-11-27","cited_by_count":551},{"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":"1701.01370","title":"Learning from Synthetic Humans","created":"2017-01-05","cited_by_count":359},{"id":"2109.08472","title":"ActionCLIP: A New Paradigm for Video Action Recognition","created":"2021-09-17","cited_by_count":320},{"id":"1812.01601","title":"Learning 3D Human Dynamics from Video","created":"2018-12-04","cited_by_count":316},{"id":"2008.03713","title":"I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image","created":"2020-08-09","cited_by_count":274},{"id":"2004.06704","title":"FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding","created":"2020-04-14","cited_by_count":234},{"id":"1904.03345","title":"Semantic Graph Convolutional Networks for 3D Human Pose Regression","created":"2019-04-06","cited_by_count":204},{"id":"2008.08535","title":"STAR: Sparse Trained Articulated Human Body Regressor","created":"2020-08-19","cited_by_count":194},{"id":"2007.03672","title":"Long-term Human Motion Prediction with Scene Context","created":"2020-07-07","cited_by_count":192},{"id":"2007.11858","title":"Whole-Body Human Pose Estimation in the Wild","created":"2020-07-23","cited_by_count":178},{"id":"2004.03548","title":"Temporal Pyramid Network for Action Recognition","created":"2020-04-07","cited_by_count":163},{"id":"2005.06803","title":"TAM: Temporal Adaptive Module for Video Recognition","created":"2020-05-14","cited_by_count":139},{"id":"1805.06485","title":"QuaterNet: A Quaternion-based Recurrent Model for Human Motion","created":"2018-05-16","cited_by_count":109},{"id":"1505.05641","title":"Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views","created":"2015-05-21","cited_by_count":94},{"id":"2004.13985","title":"Motion Guided 3D Pose Estimation from Videos","created":"2020-04-29","cited_by_count":85},{"id":"2107.13788","title":"Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flows","created":"2021-07-29","cited_by_count":85},{"id":"1803.08319","title":"Learning to Detect and Track Visible and Occluded Body Joints in a Virtual World","created":"2018-03-22","cited_by_count":82},{"id":"1712.02225","title":"Pose-Normalized Image Generation for Person Re-identification","created":"2017-12-06","cited_by_count":70},{"id":"2303.04805","title":"X-Avatar: Expressive Human Avatars","created":"2023-03-08","cited_by_count":66},{"id":"1604.02703","title":"Synthesizing Training Images for Boosting Human 3D Pose Estimation","created":"2016-04-10","cited_by_count":52},{"id":"2107.07797","title":"Conditional Directed Graph Convolution for 3D Human Pose Estimation","created":"2021-07-16","cited_by_count":52},{"id":"1910.12032","title":"HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimation","created":"2019-10-26","cited_by_count":50},{"id":"2307.05853","title":"GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Video","created":"2023-07-12","cited_by_count":47},{"id":"1912.04070","title":"Synthetic Humans for Action Recognition from Unseen Viewpoints","created":"2019-12-09","cited_by_count":46},{"id":"1508.06708","title":"Maximum-Margin Structured Learning with Deep Networks for 3D Human Pose Estimation","created":"2015-08-27","cited_by_count":37},{"id":"2103.15507","title":"Context Modeling in 3D Human Pose Estimation: A Unified Perspective","created":"2021-03-29","cited_by_count":37},{"id":"1612.00881","title":"Procedural Generation of Videos to Train Deep Action Recognition Networks","created":"2016-12-02","cited_by_count":31},{"id":"2211.15692","title":"H3WB: Human3.6M 3D WholeBody Dataset and Benchmark","created":"2022-11-28","cited_by_count":23},{"id":"2107.05617","title":"Let's Play for Action: Recognizing Activities of Daily Living by Learning from Life Simulation Video Games","created":"2021-07-12","cited_by_count":17},{"id":"1602.00828","title":"Learning a Deep Model for Human Action Recognition from Novel Viewpoints","created":"2016-02-02","cited_by_count":12},{"id":"1904.11451","title":"Large Scale Holistic Video Understanding","created":"2019-04-25","cited_by_count":12},{"id":"2202.13096","title":"Continuous Human Action Recognition for Human-Machine Interaction: A Review","created":"2022-02-26","cited_by_count":10},{"id":"2208.03704","title":"Jointformer: Single-Frame Lifting Transformer with Error Prediction and Refinement for 3D Human Pose Estimation","created":"2022-08-07","cited_by_count":10},{"id":"2208.03775","title":"Video-based Human Action Recognition using Deep Learning: A Review","created":"2022-08-07","cited_by_count":7},{"id":"1609.05522","title":"Learning camera viewpoint using CNN to improve 3D body pose estimation","created":"2016-09-18","cited_by_count":6},{"id":"1707.00823","title":"Learning Human Pose Models from Synthesized Data for Robust RGB-D Action Recognition","created":"2017-07-04","cited_by_count":6},{"id":"1906.00161","title":"Temporally Coherent Full 3D Mesh Human Pose Recovery from Monocular Video","created":"2019-06-01","cited_by_count":4}],"next_cursor":null}