{"list":"other","total":85,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"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":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"1712.06584","title":"End-to-end Recovery of Human Shape and Pose","created":"2017-12-18","cited_by_count":885},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"1607.08128","title":"Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image","created":"2016-07-27","cited_by_count":695},{"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":"2012.15838","title":"Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans","created":"2020-12-31","cited_by_count":634},{"id":"1909.12828","title":"Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop","created":"2019-09-27","cited_by_count":627},{"id":"1912.05656","title":"VIBE: Video Inference for Human Body Pose and Shape Estimation","created":"2019-12-11","cited_by_count":620},{"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":"2104.05670","title":"Action-Conditioned 3D Human Motion Synthesis with Transformer VAE","created":"2021-04-12","cited_by_count":501},{"id":"1611.09813","title":"Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision","created":"2016-11-29","cited_by_count":494},{"id":"2204.14109","title":"TEMOS: Generating diverse human motions from textual descriptions","created":"2022-04-25","cited_by_count":492},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"2007.15240","title":"Action2Motion: Conditioned Generation of 3D Human Motions","created":"2020-07-30","cited_by_count":441},{"id":"2203.08063","title":"MotionCLIP: Exposing Human Motion Generation to CLIP Space","created":"2022-03-15","cited_by_count":408},{"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":"2003.14111","title":"Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition","created":"2020-03-31","cited_by_count":343},{"id":"1711.07319","title":"Cascaded Pyramid Network for Multi-Person Pose Estimation","created":"2017-11-20","cited_by_count":341},{"id":"1607.03827","title":"The KIT Motion-Language Dataset","created":"2016-07-13","cited_by_count":338},{"id":"2104.08527","title":"PARE: Part Attention Regressor for 3D Human Body Estimation","created":"2021-04-17","cited_by_count":337},{"id":"2107.12213","title":"Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition","created":"2021-07-26","cited_by_count":322},{"id":"1812.01601","title":"Learning 3D Human Dynamics from Video","created":"2018-12-04","cited_by_count":316},{"id":"2011.14672","title":"HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation","created":"2020-11-30","cited_by_count":307},{"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":"2106.09696","title":"BABEL: Bodies, Action and Behavior with English Labels","created":"2021-06-17","cited_by_count":265},{"id":"1907.01108","title":"Language2Pose: Natural Language Grounded Pose Forecasting","created":"2019-07-02","cited_by_count":257},{"id":"2104.13586","title":"Revisiting Skeleton-based Action Recognition","created":"2021-04-28","cited_by_count":257},{"id":"2105.01859","title":"Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors","created":"2021-05-05","cited_by_count":246},{"id":"2004.06704","title":"FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding","created":"2020-04-14","cited_by_count":234},{"id":"1904.12659","title":"Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition","created":"2019-04-26","cited_by_count":228},{"id":"1805.04092","title":"Learning to Estimate 3D Human Pose and Shape from a Single Color Image","created":"2018-05-10","cited_by_count":226},{"id":"1701.02468","title":"Unite the People: Closing the Loop Between 3D and 2D Human Representations","created":"2017-01-10","cited_by_count":205},{"id":"2104.14643","title":"AGORA: Avatars in Geography Optimized for Regression Analysis","created":"2021-04-29","cited_by_count":205},{"id":"1712.03453","title":"Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB","created":"2017-12-09","cited_by_count":195},{"id":"2008.08535","title":"STAR: Sparse Trained Articulated Human Body Regressor","created":"2020-08-19","cited_by_count":194},{"id":"1808.05942","title":"Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation","created":"2018-08-17","cited_by_count":185},{"id":"1903.06473","title":"DeepHuman: 3D Human Reconstruction from a Single Image","created":"2019-03-15","cited_by_count":182},{"id":"2103.14675","title":"Synthesis of Compositional Animations from Textual Descriptions","created":"2021-03-26","cited_by_count":178},{"id":"1710.10000","title":"PoseTrack: A Benchmark for Human Pose Estimation and Tracking","created":"2017-10-27","cited_by_count":173},{"id":"2011.08627","title":"Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video","created":"2020-11-17","cited_by_count":163},{"id":"2001.08740","title":"Audiovisual SlowFast Networks for Video Recognition","created":"2020-01-23","cited_by_count":146},{"id":"2112.08274","title":"Putting People in their Place: Monocular Regression of 3D People in Depth","created":"2021-12-15","cited_by_count":142},{"id":"2007.11432","title":"Combining Implicit Function Learning and Parametric Models for 3D Human Reconstruction","created":"2020-07-22","cited_by_count":133},{"id":"1611.06067","title":"An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data","created":"2016-11-18","cited_by_count":126},{"id":"2204.13686","title":"HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling","created":"2022-04-28","cited_by_count":117},{"id":"2204.03646","title":"FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment","created":"2022-04-07","cited_by_count":107},{"id":"1703.08274","title":"View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data","created":"2017-03-24","cited_by_count":105},{"id":"2008.03789","title":"3D Human Motion Estimation via Motion Compression and Refinement","created":"2020-08-09","cited_by_count":98},{"id":"1712.01337","title":"Self-supervised Learning of Motion Capture","created":"2017-12-04","cited_by_count":97},{"id":"1611.05125","title":"Learning To Score Olympic Events","created":"2016-11-16","cited_by_count":88},{"id":"1908.07172","title":"Human Mesh Recovery from Monocular Images via a Skeleton-disentangled Representation","created":"2019-08-20","cited_by_count":87},{"id":"2006.06119","title":"Dance Revolution: Long-Term Dance Generation with Music via Curriculum Learning","created":"2020-06-11","cited_by_count":81},{"id":"2006.07665","title":"Uncertainty-aware Score Distribution Learning for Action Quality Assessment","created":"2020-06-13","cited_by_count":80},{"id":"1907.00837","title":"XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Camera","created":"2019-07-01","cited_by_count":68},{"id":"2110.07588","title":"Playing for 3D Human Recovery","created":"2021-10-14","cited_by_count":64},{"id":"1705.06400","title":"Learning a bidirectional mapping between human whole-body motion and natural language using deep recurrent neural networks","created":"2017-05-18","cited_by_count":61},{"id":"1711.08682","title":"Deep Video Generation, Prediction and Completion of Human Action Sequences","created":"2017-11-23","cited_by_count":52},{"id":"1712.09382","title":"Audio to Body Dynamics","created":"2017-12-19","cited_by_count":48},{"id":"1912.10150","title":"Learning Diverse Stochastic Human-Action Generators by Learning Smooth Latent Transitions","created":"2019-12-21","cited_by_count":46},{"id":"2204.01018","title":"TransRAC: Encoding Multi-scale Temporal Correlation with Transformers for Repetitive Action Counting","created":"2022-04-03","cited_by_count":44},{"id":"2104.08160","title":"Locally Aware Piecewise Transformation Fields for 3D Human Mesh Registration","created":"2021-04-16","cited_by_count":41},{"id":"2108.10378","title":"Lightweight Multi-person Total Motion Capture Using Sparse Multi-view Cameras","created":"2021-08-23","cited_by_count":33},{"id":"2007.01971","title":"Structure-Aware Human-Action Generation","created":"2020-07-04","cited_by_count":28},{"id":"2209.10529","title":"Benchmarking and Analyzing 3D Human Pose and Shape Estimation Beyond Algorithms","created":"2022-09-21","cited_by_count":28},{"id":"2004.10362","title":"Yoga-82: A New Dataset for Fine-grained Classification of Human Poses","created":"2020-04-22","cited_by_count":25},{"id":"1705.08106","title":"Two-Stream 3D Convolutional Neural Network for Skeleton-Based Action Recognition","created":"2017-05-23","cited_by_count":23},{"id":"2112.04159","title":"Garment4D: Garment Reconstruction from Point Cloud Sequences","created":"2021-12-08","cited_by_count":23},{"id":"2105.13965","title":"Revitalizing Optimization for 3D Human Pose and Shape Estimation: A Sparse Constrained Formulation","created":"2021-05-28","cited_by_count":19},{"id":"2110.08729","title":"VoteHMR: Occlusion-Aware Voting Network for Robust 3D Human Mesh Recovery from Partial Point Clouds","created":"2021-10-17","cited_by_count":18},{"id":"1904.10681","title":"A Large-scale Varying-view RGB-D Action Dataset for Arbitrary-view Human Action Recognition","created":"2019-04-24","cited_by_count":16},{"id":"2111.06925","title":"Action2video: Generating Videos of Human 3D Actions","created":"2021-11-12","cited_by_count":15},{"id":"2208.03257","title":"3D Pose Based Feedback for Physical Exercises","created":"2022-08-05","cited_by_count":11}],"next_cursor":null}