{"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/magr-manifold-aligned-graph-regularization","title":"MAGR: Manifold-Aligned Graph Regularization for Continual Action Quality Assessment","arxiv_id":"2403.04398","date":"2024-03-07","proceeding":null,"authors":["Kanglei Zhou","Liyuan Wang","Xingxing Zhang","Hubert P. H. Shum","Frederick W. B. Li","Jianguo Li","Xiaohui Liang"],"abstract":"Action Quality Assessment (AQA) evaluates diverse skills but models struggle with non-stationary data. We propose Continual AQA (CAQA) to refine models using sparse new data. Feature replay preserves memory without storing raw inputs. However, the misalignment between static old features and the dynamically changing feature manifold causes severe catastrophic forgetting. To address this novel problem, we propose Manifold-Aligned Graph Regularization (MAGR), which first aligns deviated old features to the current feature manifold, ensuring representation consistency. It then constructs a graph jointly arranging old and new features aligned with quality scores. Experiments show MAGR outperforms recent strong baselines with up to 6.56%, 5.66%, 15.64%, and 9.05% correlation gains on the MTL-AQA, FineDiving, UNLV-Dive, and JDM-MSA split datasets, respectively. This validates MAGR for continual assessment challenges arising from non-stationary skill variations. Code is available at https://github.com/ZhouKanglei/MAGR_CAQA}{https://github.com/ZhouKanglei/MAGR_CAQA.","url_abs":"https://arxiv.org/abs/2403.04398v2","url_pdf":"https://arxiv.org/pdf/2403.04398v2.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":"magr-manifold-aligned-graph-regularization","repo_url":"https://github.com/zhoukanglei/magr_caqa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-quality-assessment","task_name":"Action Quality Assessment"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.04398","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04398"}},"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/ZhouKanglei/MAGR_CAQA","reach":null}],"summary":{"ran":1,"ran_honours":1,"unverified":3},"by_repo_kind":{"official":{"samples":5,"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":5,"samples":[{"code_sha256_prefix":"03cc2a99ebbb3a67","entry":"ListNetLoss","repo":"ZhouKanglei/MAGR_CAQA","repo_kind":"official","path":"models/fea_gr.py","file_url":"https://github.com/ZhouKanglei/MAGR_CAQA/blob/HEAD/models/fea_gr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"03cc2a99ebbb3a67"}},{"code_sha256_prefix":"ee0dd472cc3e8dff","entry":"distributed_concat","repo":"ZhouKanglei/MAGR_CAQA","repo_kind":"official","path":"models/fea_gr.py","file_url":"https://github.com/ZhouKanglei/MAGR_CAQA/blob/HEAD/models/fea_gr.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ee0dd472cc3e8dff"}},{"code_sha256_prefix":"0dc99786a7ca9094","entry":"Buffer","repo":"ZhouKanglei/MAGR_CAQA","repo_kind":"official","path":"models/fea_gr.py","file_url":"https://github.com/ZhouKanglei/MAGR_CAQA/blob/HEAD/models/fea_gr.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0dc99786a7ca9094"}},{"code_sha256_prefix":"45fc3083f9e5c62e","entry":"ContinualModel","repo":"ZhouKanglei/MAGR_CAQA","repo_kind":"official","path":"models/fea_gr.py","file_url":"https://github.com/ZhouKanglei/MAGR_CAQA/blob/HEAD/models/fea_gr.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"45fc3083f9e5c62e"}},{"code_sha256_prefix":"5e9851b0c80563c2","entry":"FeaGr","repo":"ZhouKanglei/MAGR_CAQA","repo_kind":"official","path":"models/fea_gr.py","file_url":"https://github.com/ZhouKanglei/MAGR_CAQA/blob/HEAD/models/fea_gr.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5e9851b0c80563c2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}