{"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/chase-learning-convex-hull-adaptive-shift-for","title":"CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition","arxiv_id":"2410.07153","date":"2024-10-09","proceeding":null,"authors":["Yuhang Wen","Mengyuan Liu","Songtao Wu","Beichen Ding"],"abstract":"Skeleton-based multi-entity action recognition is a challenging task aiming to identify interactive actions or group activities involving multiple diverse entities. Existing models for individuals often fall short in this task due to the inherent distribution discrepancies among entity skeletons, leading to suboptimal backbone optimization. To this end, we introduce a Convex Hull Adaptive Shift based multi-Entity action recognition method (CHASE), which mitigates inter-entity distribution gaps and unbiases subsequent backbones. Specifically, CHASE comprises a learnable parameterized network and an auxiliary objective. The parameterized network achieves plausible, sample-adaptive repositioning of skeleton sequences through two key components. First, the Implicit Convex Hull Constrained Adaptive Shift ensures that the new origin of the coordinate system is within the skeleton convex hull. Second, the Coefficient Learning Block provides a lightweight parameterization of the mapping from skeleton sequences to their specific coefficients in convex combinations. Moreover, to guide the optimization of this network for discrepancy minimization, we propose the Mini-batch Pair-wise Maximum Mean Discrepancy as the additional objective. CHASE operates as a sample-adaptive normalization method to mitigate inter-entity distribution discrepancies, thereby reducing data bias and improving the subsequent classifier's multi-entity action recognition performance. Extensive experiments on six datasets, including NTU Mutual 11/26, H2O, Assembly101, Collective Activity and Volleyball, consistently verify our approach by seamlessly adapting to single-entity backbones and boosting their performance in multi-entity scenarios. Our code is publicly available at https://github.com/Necolizer/CHASE .","url_abs":"https://arxiv.org/abs/2410.07153v2","url_pdf":"https://arxiv.org/pdf/2410.07153v2.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":"chase-learning-convex-hull-adaptive-shift-for","repo_url":"https://github.com/Necolizer/CHASE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-human-action-recognition","task_name":"3D Action Recognition"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"group-activity-recognition","task_name":"Group Activity Recognition"},{"task_slug":"human-interaction-recognition","task_name":"Human Interaction Recognition"},{"task_slug":"skeleton-based-action-recognition","task_name":"Skeleton Based Action Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-action-recognition-on-assembly101","task":"3D Action Recognition","dataset":"Assembly101","model":"CHASE(CTR-GCN)","rank_in_archive_order":6,"of":7,"metrics":{"Actions Top-1":"28.03"},"uses_additional_data":false},{"leaderboard":"/sota/group-activity-recognition-on-collective","task":"Group Activity Recognition","dataset":"Collective Activity","model":"CHASE(CTR-GCN)","rank_in_archive_order":4,"of":6,"metrics":{"Accuracy":"89.61"},"uses_additional_data":false},{"leaderboard":"/sota/group-activity-recognition-on-volleyball","task":"Group Activity Recognition","dataset":"Volleyball","model":"CHASE(CTR-GCN)","rank_in_archive_order":7,"of":12,"metrics":{"Accuracy":"92.89"},"uses_additional_data":false},{"leaderboard":"/sota/human-interaction-recognition-on-ntu-rgb-d","task":"Human Interaction Recognition","dataset":"NTU RGB+D","model":"CHASE(CTR-GCN)","rank_in_archive_order":2,"of":5,"metrics":{"Accuracy (Cross-Subject)":"96.5","Accuracy (Cross-View)":"98.8"},"uses_additional_data":false},{"leaderboard":"/sota/human-interaction-recognition-on-ntu-rgb-d-1","task":"Human Interaction Recognition","dataset":"NTU RGB+D 120","model":"CHASE(CTR-GCN)","rank_in_archive_order":2,"of":6,"metrics":{"Accuracy (Cross-Setup)":"92.3","Accuracy (Cross-Subject)":"91.3"},"uses_additional_data":false},{"leaderboard":"/sota/skeleton-based-action-recognition-on-h2o-2","task":"Skeleton Based Action Recognition","dataset":"H2O  (2 Hands and Objects)","model":"CHASE(STSA-Net)","rank_in_archive_order":1,"of":4,"metrics":{"Accuracy":"94.77"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.07153","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07153"}},"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":"deterministic:regex_extraction","url":"https://github.com/Necolizer/CHASE","reach":null}],"summary":{"ran":1,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":"24327371b1f2da78","entry":"CHASWrapper","repo":"Necolizer/CHASE","repo_kind":"official","path":"JournalSubmission/CHASE-Joint/model/Wrapper/chas.py","file_url":"https://github.com/Necolizer/CHASE/blob/HEAD/JournalSubmission/CHASE-Joint/model/Wrapper/chas.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"24327371b1f2da78"}},{"code_sha256_prefix":"48992428a29e341b","entry":"import_class","repo":"necolizer/chase","repo_kind":"official","path":"JournalSubmission/CHASE-Joint/model/CTRGCN/ctrgcn.py","file_url":"https://github.com/necolizer/chase/blob/HEAD/JournalSubmission/CHASE-Joint/model/CTRGCN/ctrgcn.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"48992428a29e341b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}