{"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/channel-wise-topology-refinement-graph","title":"Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition","arxiv_id":"2107.12213","date":"2021-07-26","proceeding":"ICCV 2021 10","authors":["Yuxin Chen","Ziqi Zhang","Chunfeng Yuan","Bing Li","Ying Deng","Weiming Hu"],"abstract":"Graph convolutional networks (GCNs) have been widely used and achieved remarkable results in skeleton-based action recognition. In GCNs, graph topology dominates feature aggregation and therefore is the key to extracting representative features. In this work, we propose a novel Channel-wise Topology Refinement Graph Convolution (CTR-GC) to dynamically learn different topologies and effectively aggregate joint features in different channels for skeleton-based action recognition. The proposed CTR-GC models channel-wise topologies through learning a shared topology as a generic prior for all channels and refining it with channel-specific correlations for each channel. Our refinement method introduces few extra parameters and significantly reduces the difficulty of modeling channel-wise topologies. Furthermore, via reformulating graph convolutions into a unified form, we find that CTR-GC relaxes strict constraints of graph convolutions, leading to stronger representation capability. Combining CTR-GC with temporal modeling modules, we develop a powerful graph convolutional network named CTR-GCN which notably outperforms state-of-the-art methods on the NTU RGB+D, NTU RGB+D 120, and NW-UCLA datasets.","url_abs":"https://arxiv.org/abs/2107.12213v2","url_pdf":"https://arxiv.org/pdf/2107.12213v2.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":"channel-wise-topology-refinement-graph","repo_url":"https://github.com/Uason-Chen/CTR-GCN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"channel-wise-topology-refinement-graph","repo_url":"https://github.com/kennymckormick/pyskl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"skeleton-based-action-recognition","task_name":"Skeleton Based Action Recognition"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/skeleton-based-action-recognition-on-n-ucla","task":"Skeleton Based Action Recognition","dataset":"N-UCLA","model":"CTR-GCN","rank_in_archive_order":13,"of":25,"metrics":{"Accuracy":"96.5"},"uses_additional_data":false},{"leaderboard":"/sota/skeleton-based-action-recognition-on-ntu-rgbd","task":"Skeleton Based Action Recognition","dataset":"NTU RGB+D","model":"CTR-GCN","rank_in_archive_order":33,"of":135,"metrics":{"Accuracy (CS)":"92.4","Accuracy (CV)":"96.8","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":"CTR-GCN","rank_in_archive_order":24,"of":83,"metrics":{"Accuracy (Cross-Setup)":"90.6","Accuracy (Cross-Subject)":"88.9","Ensembled Modalities":"4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2107.12213","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.12213"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Uason-Chen/CTR-GCN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kennymckormick/pyskl","reach":null}],"summary":{"ran":2,"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":1,"repositories":1},"listed":{"samples":2,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"d7d10dd15822d04b","entry":"CTRGC","repo":"Uason-Chen/CTR-GCN","repo_kind":"official","path":"model/ctrgcn.py","file_url":"https://github.com/Uason-Chen/CTR-GCN/blob/HEAD/model/ctrgcn.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d7d10dd15822d04b"}},{"code_sha256_prefix":"a6e280c955a92cc1","entry":"CTRGC","repo":"kennymckormick/pyskl","repo_kind":"listed","path":"pyskl/models/gcns/utils/gcn.py","file_url":"https://github.com/kennymckormick/pyskl/blob/HEAD/pyskl/models/gcns/utils/gcn.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a6e280c955a92cc1"}},{"code_sha256_prefix":"da94160ed9fd5926","entry":"bn_init","repo":"Uason-Chen/CTR-GCN","repo_kind":"official","path":"model/ctrgcn.py","file_url":"https://github.com/Uason-Chen/CTR-GCN/blob/HEAD/model/ctrgcn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"da94160ed9fd5926"}},{"code_sha256_prefix":"0f3bc22a15a9d724","entry":"conv_init","repo":"Uason-Chen/CTR-GCN","repo_kind":"official","path":"model/ctrgcn.py","file_url":"https://github.com/Uason-Chen/CTR-GCN/blob/HEAD/model/ctrgcn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"0f3bc22a15a9d724"}},{"code_sha256_prefix":"a3ca5080ddd9c2fc","entry":"conv_init","repo":"kennymckormick/pyskl","repo_kind":"listed","path":"pyskl/models/gcns/utils/gcn.py","file_url":"https://github.com/kennymckormick/pyskl/blob/HEAD/pyskl/models/gcns/utils/gcn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a3ca5080ddd9c2fc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}