{"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/group-aware-contrastive-regression-for-action","title":"Group-aware Contrastive Regression for Action Quality Assessment","arxiv_id":"2108.07797","date":"2021-08-17","proceeding":"ICCV 2021 10","authors":["Xumin Yu","Yongming Rao","Wenliang Zhao","Jiwen Lu","Jie zhou"],"abstract":"Assessing action quality is challenging due to the subtle differences between videos and large variations in scores. Most existing approaches tackle this problem by regressing a quality score from a single video, suffering a lot from the large inter-video score variations. In this paper, we show that the relations among videos can provide important clues for more accurate action quality assessment during both training and inference. Specifically, we reformulate the problem of action quality assessment as regressing the relative scores with reference to another video that has shared attributes (e.g., category and difficulty), instead of learning unreferenced scores. Following this formulation, we propose a new Contrastive Regression (CoRe) framework to learn the relative scores by pair-wise comparison, which highlights the differences between videos and guides the models to learn the key hints for assessment. In order to further exploit the relative information between two videos, we devise a group-aware regression tree to convert the conventional score regression into two easier sub-problems: coarse-to-fine classification and regression in small intervals. To demonstrate the effectiveness of CoRe, we conduct extensive experiments on three mainstream AQA datasets including AQA-7, MTL-AQA and JIGSAWS. Our approach outperforms previous methods by a large margin and establishes new state-of-the-art on all three benchmarks.","url_abs":"https://arxiv.org/abs/2108.07797v1","url_pdf":"https://arxiv.org/pdf/2108.07797v1.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":"group-aware-contrastive-regression-for-action","repo_url":"https://github.com/yuxumin/CoRe","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-quality-assessment","task_name":"Action Quality Assessment"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-quality-assessment-on-aqa-7","task":"Action Quality Assessment","dataset":"AQA-7","model":"CoRe","rank_in_archive_order":2,"of":9,"metrics":{"RL2(*100)":"2.12","Spearman Correlation":"84.01%"},"uses_additional_data":false},{"leaderboard":"/sota/action-quality-assessment-on-aqa-7","task":"Action Quality Assessment","dataset":"AQA-7","model":"I3D+MLP","rank_in_archive_order":5,"of":9,"metrics":{"RL2(*100)":"3.20","Spearman Correlation":"76.01%"},"uses_additional_data":false},{"leaderboard":"/sota/action-quality-assessment-on-mtl-aqa","task":"Action Quality Assessment","dataset":"MTL-AQA","model":"CoRe(w/ DD)","rank_in_archive_order":6,"of":21,"metrics":{"RL2(*100)":"0.260","Spearman Correlation":"95.12"},"uses_additional_data":false},{"leaderboard":"/sota/action-quality-assessment-on-mtl-aqa","task":"Action Quality Assessment","dataset":"MTL-AQA","model":"I3D+MLP(w/ DD)","rank_in_archive_order":8,"of":21,"metrics":{"RL2(*100)":" 0.394","Spearman Correlation":"93.81"},"uses_additional_data":false},{"leaderboard":"/sota/action-quality-assessment-on-mtl-aqa","task":"Action Quality Assessment","dataset":"MTL-AQA","model":"CoRe","rank_in_archive_order":9,"of":21,"metrics":{"RL2(*100)":"0.365","Spearman Correlation":"93.41"},"uses_additional_data":false},{"leaderboard":"/sota/action-quality-assessment-on-mtl-aqa","task":"Action Quality Assessment","dataset":"MTL-AQA","model":"I3D+MLP","rank_in_archive_order":14,"of":21,"metrics":{"RL2(*100)":"0.465","Spearman Correlation":"91.96"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2108.07797","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.07797"}},"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/yuxumin/CoRe","reach":null}],"summary":{"ran":1},"by_repo_kind":{"listed":{"samples":1,"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":1,"samples":[{"code_sha256_prefix":"f323a0a51fc3e74b","entry":"Group_helper","repo":"yuxumin/CoRe","repo_kind":"listed","path":"utils/Group_helper.py","file_url":"https://github.com/yuxumin/CoRe/blob/HEAD/utils/Group_helper.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f323a0a51fc3e74b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}