{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/gast-net-graph-attention-spatio-temporal","title":"A Graph Attention Spatio-temporal Convolutional Network for 3D Human Pose Estimation in Video","arxiv_id":"2003.14179","date":"2020-03-11","proceeding":null,"authors":["Junfa Liu","Juan Rojas","Zhijun Liang","Yihui Li","Yisheng Guan"],"abstract":"Spatio-temporal information is key to resolve occlusion and depth ambiguity in 3D pose estimation. Previous methods have focused on either temporal contexts or local-to-global architectures that embed fixed-length spatio-temporal information. To date, there have not been effective proposals to simultaneously and flexibly capture varying spatio-temporal sequences and effectively achieves real-time 3D pose estimation. In this work, we improve the learning of kinematic constraints in the human skeleton: posture, local kinematic connections, and symmetry by modeling local and global spatial information via attention mechanisms. To adapt to single- and multi-frame estimation, the dilated temporal model is employed to process varying skeleton sequences. Also, importantly, we carefully design the interleaving of spatial semantics with temporal dependencies to achieve a synergistic effect. To this end, we propose a simple yet effective graph attention spatio-temporal convolutional network (GAST-Net) that comprises of interleaved temporal convolutional and graph attention blocks. Experiments on two challenging benchmark datasets (Human3.6M and HumanEva-I) and YouTube videos demonstrate that our approach effectively mitigates depth ambiguity and self-occlusion, generalizes to half upper body estimation, and achieves competitive performance on 2D-to-3D video pose estimation. Code, video, and supplementary information is available at: \\href{http://www.juanrojas.net/gast/}{http://www.juanrojas.net/gast/}","url_abs":"https://arxiv.org/abs/2003.14179v4","url_pdf":"https://arxiv.org/pdf/2003.14179v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"gast-net-graph-attention-spatio-temporal","repo_url":"https://github.com/fabro66/GAST-Net-3DPoseEstimation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-human-pose-estimation","task_name":"3D Human Pose Estimation"},{"task_slug":"3d-pose-estimation","task_name":"3D Pose Estimation"},{"task_slug":"graph-attention","task_name":"Graph Attention"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"temporal-sequences","task_name":"Temporal Sequences"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-human-pose-estimation-on-humaneva-i","task":"3D Human Pose Estimation","dataset":"HumanEva-I","model":"GAST","rank_in_archive_order":12,"of":31,"metrics":{"Mean Reconstruction Error (mm)":"21.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2003.14179","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}