{"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/disentangling-and-unifying-graph-convolutions","title":"Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition","arxiv_id":"2003.14111","date":"2020-03-31","proceeding":"CVPR 2020 6","authors":["Ziyu Liu","Hongwen Zhang","Zhenghao Chen","Zhiyong Wang","Wanli Ouyang"],"abstract":"Spatial-temporal graphs have been widely used by skeleton-based action recognition algorithms to model human action dynamics. To capture robust movement patterns from these graphs, long-range and multi-scale context aggregation and spatial-temporal dependency modeling are critical aspects of a powerful feature extractor. However, existing methods have limitations in achieving (1) unbiased long-range joint relationship modeling under multi-scale operators and (2) unobstructed cross-spacetime information flow for capturing complex spatial-temporal dependencies. In this work, we present (1) a simple method to disentangle multi-scale graph convolutions and (2) a unified spatial-temporal graph convolutional operator named G3D. The proposed multi-scale aggregation scheme disentangles the importance of nodes in different neighborhoods for effective long-range modeling. The proposed G3D module leverages dense cross-spacetime edges as skip connections for direct information propagation across the spatial-temporal graph. By coupling these proposals, we develop a powerful feature extractor named MS-G3D based on which our model outperforms previous state-of-the-art methods on three large-scale datasets: NTU RGB+D 60, NTU RGB+D 120, and Kinetics Skeleton 400.","url_abs":"https://arxiv.org/abs/2003.14111v2","url_pdf":"https://arxiv.org/pdf/2003.14111v2.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":"disentangling-and-unifying-graph-convolutions","repo_url":"https://github.com/kenziyuliu/ms-g3d","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"disentangling-and-unifying-graph-convolutions","repo_url":"https://github.com/kennymckormick/pyskl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"disentangling-and-unifying-graph-convolutions","repo_url":"https://github.com/metrics-lab/st-fmri","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-human-action-recognition","task_name":"3D Action Recognition"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"long-range-modeling","task_name":"Long-range modeling"},{"task_slug":"skeleton-based-action-recognition","task_name":"Skeleton Based Action Recognition"}],"methods":[{"method_slug":"g3d","method_name":"G3D"}],"datasets_introduced":[],"methods_introduced":[{"slug":"g3d","name":"G3D","full_name":"G3D"}],"results":[{"leaderboard":"/sota/3d-action-recognition-on-assembly101","task":"3D Action Recognition","dataset":"Assembly101","model":"MS-G3D","rank_in_archive_order":4,"of":7,"metrics":{"Actions Top-1":"28.7","Object Top-1":"36.3","Verbs Top-1":"65.7"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-on-h2o-2-hands-and-objects","task":"Action Recognition","dataset":"H2O  (2 Hands and Objects)","model":"MS-G3D","rank_in_archive_order":11,"of":11,"metrics":{"Actions Top-1":"50.83","Hand Pose":"3D","Object Label":"No","Object Pose":"No","RGB":"No"},"uses_additional_data":false},{"leaderboard":"/sota/skeleton-based-action-recognition-on-kinetics","task":"Skeleton Based Action Recognition","dataset":"Kinetics-Skeleton dataset","model":"MS-G3D","rank_in_archive_order":10,"of":42,"metrics":{"Accuracy":"38.0"},"uses_additional_data":false},{"leaderboard":"/sota/skeleton-based-action-recognition-on-ntu-rgbd","task":"Skeleton Based Action Recognition","dataset":"NTU RGB+D","model":"MS-G3D Net","rank_in_archive_order":40,"of":135,"metrics":{"Accuracy (CS)":"91.5","Accuracy (CV)":"96.2"},"uses_additional_data":true},{"leaderboard":"/sota/skeleton-based-action-recognition-on-ntu-rgbd-1","task":"Skeleton Based Action Recognition","dataset":"NTU RGB+D 120","model":"MS-G3D Net","rank_in_archive_order":38,"of":83,"metrics":{"Accuracy (Cross-Setup)":"88.4%","Accuracy (Cross-Subject)":"86.9%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2003.14111","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.14111"}},"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/kenziyuliu/ms-g3d","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kennymckormick/pyskl","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/metrics-lab/st-fmri","reach":{"status":"ok"}}],"summary":{"ran_honours":2,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":0,"samples":[{"code_sha256_prefix":"47a234b123ed6809","entry":"get_nonzero_std","repo":"kenziyuliu/ms-g3d","repo_kind":"official","path":"data_gen/ntu_gendata.py","file_url":"https://github.com/kenziyuliu/ms-g3d/blob/HEAD/data_gen/ntu_gendata.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"47a234b123ed6809"}},{"code_sha256_prefix":"c6381bb48f81a144","entry":"read_skeleton_filter","repo":"kenziyuliu/ms-g3d","repo_kind":"official","path":"data_gen/ntu_gendata.py","file_url":"https://github.com/kenziyuliu/ms-g3d/blob/HEAD/data_gen/ntu_gendata.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c6381bb48f81a144"}},{"code_sha256_prefix":"7e6ab20b3ba9e367","entry":"read_xyz","repo":"kenziyuliu/ms-g3d","repo_kind":"official","path":"data_gen/ntu_gendata.py","file_url":"https://github.com/kenziyuliu/ms-g3d/blob/HEAD/data_gen/ntu_gendata.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7e6ab20b3ba9e367"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}