{"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/learning-multi-granular-spatio-temporal-graph","title":"Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition","arxiv_id":"2108.04536","date":"2021-08-10","proceeding":null,"authors":["Tailin Chen","Desen Zhou","Jian Wang","Shidong Wang","Yu Guan","Xuming He","Errui Ding"],"abstract":"The task of skeleton-based action recognition remains a core challenge in human-centred scene understanding due to the multiple granularities and large variation in human motion. Existing approaches typically employ a single neural representation for different motion patterns, which has difficulty in capturing fine-grained action classes given limited training data. To address the aforementioned problems, we propose a novel multi-granular spatio-temporal graph network for skeleton-based action classification that jointly models the coarse- and fine-grained skeleton motion patterns. To this end, we develop a dual-head graph network consisting of two interleaved branches, which enables us to extract features at two spatio-temporal resolutions in an effective and efficient manner. Moreover, our network utilises a cross-head communication strategy to mutually enhance the representations of both heads. We conducted extensive experiments on three large-scale datasets, namely NTU RGB+D 60, NTU RGB+D 120, and Kinetics-Skeleton, and achieves the state-of-the-art performance on all the benchmarks, which validates the effectiveness of our method.","url_abs":"https://arxiv.org/abs/2108.04536v1","url_pdf":"https://arxiv.org/pdf/2108.04536v1.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":"learning-multi-granular-spatio-temporal-graph","repo_url":"https://github.com/tailin1009/dualhead-network","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"skeleton-based-action-recognition","task_name":"Skeleton Based Action Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/skeleton-based-action-recognition-on-kinetics","task":"Skeleton Based Action Recognition","dataset":"Kinetics-Skeleton dataset","model":"DualHead-Net","rank_in_archive_order":9,"of":42,"metrics":{"Accuracy":"38.4"},"uses_additional_data":false},{"leaderboard":"/sota/skeleton-based-action-recognition-on-ntu-rgbd","task":"Skeleton Based Action Recognition","dataset":"NTU RGB+D","model":"DualHead-Net","rank_in_archive_order":35,"of":135,"metrics":{"Accuracy (CS)":"92.0","Accuracy (CV)":"96.6"},"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":"DualHead-Net","rank_in_archive_order":29,"of":83,"metrics":{"Accuracy (Cross-Setup)":"89.3","Accuracy (Cross-Subject)":"88.2","Ensembled Modalities":"4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2108.04536","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.04536"}},"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/tailin1009/dualhead-network","reach":{"status":"ok"}}],"summary":{"ran_honours":2,"ran_draft_wrong":1,"ran_violates":1},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":4,"samples":[{"code_sha256_prefix":"47a234b123ed6809","entry":"get_nonzero_std","repo":"tailin1009/dualhead-network","repo_kind":"official","path":"data_gen/ntu120_gendata.py","file_url":"https://github.com/tailin1009/dualhead-network/blob/HEAD/data_gen/ntu120_gendata.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"47a234b123ed6809"}},{"code_sha256_prefix":"c6381bb48f81a144","entry":"read_skeleton_filter","repo":"tailin1009/dualhead-network","repo_kind":"official","path":"data_gen/ntu_gendata.py","file_url":"https://github.com/tailin1009/dualhead-network/blob/HEAD/data_gen/ntu_gendata.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c6381bb48f81a144"}},{"code_sha256_prefix":"7e6ab20b3ba9e367","entry":"read_xyz","repo":"tailin1009/dualhead-network","repo_kind":"official","path":"data_gen/ntu_gendata.py","file_url":"https://github.com/tailin1009/dualhead-network/blob/HEAD/data_gen/ntu_gendata.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7e6ab20b3ba9e367"}},{"code_sha256_prefix":"f017532fc389cbfe","entry":"str2bool","repo":"tailin1009/dualhead-network","repo_kind":"official","path":"main_dualhead.py","file_url":"https://github.com/tailin1009/dualhead-network/blob/HEAD/main_dualhead.py","link_basis":"plan_row","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f017532fc389cbfe"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}