{"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/graph-contrastive-learning-for-skeleton-based","title":"Graph Contrastive Learning for Skeleton-based Action Recognition","arxiv_id":"2301.10900","date":"2023-01-26","proceeding":null,"authors":["Xiaohu Huang","Hao Zhou","Jian Wang","Haocheng Feng","Junyu Han","Errui Ding","Jingdong Wang","Xinggang Wang","Wenyu Liu","Bin Feng"],"abstract":"In the field of skeleton-based action recognition, current top-performing graph convolutional networks (GCNs) exploit intra-sequence context to construct adaptive graphs for feature aggregation. However, we argue that such context is still \\textit{local} since the rich cross-sequence relations have not been explicitly investigated. In this paper, we propose a graph contrastive learning framework for skeleton-based action recognition (\\textit{SkeletonGCL}) to explore the \\textit{global} context across all sequences. In specific, SkeletonGCL associates graph learning across sequences by enforcing graphs to be class-discriminative, \\emph{i.e.,} intra-class compact and inter-class dispersed, which improves the GCN capacity to distinguish various action patterns. Besides, two memory banks are designed to enrich cross-sequence context from two complementary levels, \\emph{i.e.,} instance and semantic levels, enabling graph contrastive learning in multiple context scales. Consequently, SkeletonGCL establishes a new training paradigm, and it can be seamlessly incorporated into current GCNs. Without loss of generality, we combine SkeletonGCL with three GCNs (2S-ACGN, CTR-GCN, and InfoGCN), and achieve consistent improvements on NTU60, NTU120, and NW-UCLA benchmarks. The source code will be available at \\url{https://github.com/OliverHxh/SkeletonGCL}.","url_abs":"https://arxiv.org/abs/2301.10900v2","url_pdf":"https://arxiv.org/pdf/2301.10900v2.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":"graph-contrastive-learning-for-skeleton-based","repo_url":"https://github.com/oliverhxh/skeletongcl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"graph-learning","task_name":"Graph Learning"},{"task_slug":"skeleton-based-action-recognition","task_name":"Skeleton Based Action Recognition"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"gcn","method_name":"GCN"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/skeleton-based-action-recognition-on-ntu-rgbd","task":"Skeleton Based Action Recognition","dataset":"NTU RGB+D","model":"SkeletonGCL (based on CTR-GCN)","rank_in_archive_order":19,"of":135,"metrics":{"Accuracy (CS)":"93.1","Accuracy (CV)":"97.0","Ensembled Modalities":"4"},"uses_additional_data":false},{"leaderboard":"/sota/skeleton-based-action-recognition-on-ntu-rgbd-1","task":"Skeleton Based Action Recognition","dataset":"NTU RGB+D 120","model":"SkeletonGCL (based on CTR-GCN)","rank_in_archive_order":18,"of":83,"metrics":{"Accuracy (Cross-Setup)":"91.0","Accuracy (Cross-Subject)":"89.5","Ensembled Modalities":"4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2301.10900","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}