{"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/cofinal-enhancing-action-quality-assessment","title":"CoFInAl: Enhancing Action Quality Assessment with Coarse-to-Fine Instruction Alignment","arxiv_id":"2404.13999","date":"2024-04-22","proceeding":null,"authors":["Kanglei Zhou","Junlin Li","Ruizhi Cai","Liyuan Wang","Xingxing Zhang","Xiaohui Liang"],"abstract":"Action Quality Assessment (AQA) is pivotal for quantifying actions across domains like sports and medical care. Existing methods often rely on pre-trained backbones from large-scale action recognition datasets to boost performance on smaller AQA datasets. However, this common strategy yields suboptimal results due to the inherent struggle of these backbones to capture the subtle cues essential for AQA. Moreover, fine-tuning on smaller datasets risks overfitting. To address these issues, we propose Coarse-to-Fine Instruction Alignment (CoFInAl). Inspired by recent advances in large language model tuning, CoFInAl aligns AQA with broader pre-trained tasks by reformulating it as a coarse-to-fine classification task. Initially, it learns grade prototypes for coarse assessment and then utilizes fixed sub-grade prototypes for fine-grained assessment. This hierarchical approach mirrors the judging process, enhancing interpretability within the AQA framework. Experimental results on two long-term AQA datasets demonstrate CoFInAl achieves state-of-the-art performance with significant correlation gains of 5.49% and 3.55% on Rhythmic Gymnastics and Fis-V, respectively. Our code is available at https://github.com/ZhouKanglei/CoFInAl_AQA.","url_abs":"https://arxiv.org/abs/2404.13999v1","url_pdf":"https://arxiv.org/pdf/2404.13999v1.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":"cofinal-enhancing-action-quality-assessment","repo_url":"https://github.com/zhoukanglei/cofinal_aqa","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"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2404.13999","atlas_url":"https://app.syntology.ai/?focus=2404.13999","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.13999"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/CoFInAl_AQA","reach":null}],"summary":{"ran":4,"ran_honours":2,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":9,"ran":7,"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":9,"samples":[{"code_sha256_prefix":"2a35b66b19765a2e","entry":"TransformerDecoder","repo":"ZhouKanglei/CoFInAl_AQA","repo_kind":"official","path":"models/model.py","file_url":"https://github.com/ZhouKanglei/CoFInAl_AQA/blob/HEAD/models/model.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":"2a35b66b19765a2e"}},{"code_sha256_prefix":"c86543c3850a069d","entry":"TransformerDecoderLayer","repo":"ZhouKanglei/CoFInAl_AQA","repo_kind":"official","path":"models/model.py","file_url":"https://github.com/ZhouKanglei/CoFInAl_AQA/blob/HEAD/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c86543c3850a069d"}},{"code_sha256_prefix":"ee98f18eb34ce80e","entry":"TransformerEncoder","repo":"ZhouKanglei/CoFInAl_AQA","repo_kind":"official","path":"models/model.py","file_url":"https://github.com/ZhouKanglei/CoFInAl_AQA/blob/HEAD/models/model.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":"ee98f18eb34ce80e"}},{"code_sha256_prefix":"a78727691a69cd7f","entry":"TransformerEncoderLayer","repo":"ZhouKanglei/CoFInAl_AQA","repo_kind":"official","path":"models/model.py","file_url":"https://github.com/ZhouKanglei/CoFInAl_AQA/blob/HEAD/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a78727691a69cd7f"}},{"code_sha256_prefix":"9387230cf1a2e3af","entry":"choose_activate","repo":"ZhouKanglei/CoFInAl_AQA","repo_kind":"official","path":"models/model.py","file_url":"https://github.com/ZhouKanglei/CoFInAl_AQA/blob/HEAD/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9387230cf1a2e3af"}},{"code_sha256_prefix":"d1b7e40c513a9bd1","entry":"eth","repo":"ZhouKanglei/CoFInAl_AQA","repo_kind":"official","path":"models/model.py","file_url":"https://github.com/ZhouKanglei/CoFInAl_AQA/blob/HEAD/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d1b7e40c513a9bd1"}},{"code_sha256_prefix":"b553b3a1fc9ebdda","entry":"generate_random_orthogonal_matrix","repo":"ZhouKanglei/CoFInAl_AQA","repo_kind":"official","path":"models/model.py","file_url":"https://github.com/ZhouKanglei/CoFInAl_AQA/blob/HEAD/models/model.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":"b553b3a1fc9ebdda"}},{"code_sha256_prefix":"2ccc1d4af5076c89","entry":"Transformer","repo":"ZhouKanglei/CoFInAl_AQA","repo_kind":"official","path":"models/model.py","file_url":"https://github.com/ZhouKanglei/CoFInAl_AQA/blob/HEAD/models/model.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":"2ccc1d4af5076c89"}},{"code_sha256_prefix":"12713b2504ea68d0","entry":"cofinal","repo":"ZhouKanglei/CoFInAl_AQA","repo_kind":"official","path":"models/model.py","file_url":"https://github.com/ZhouKanglei/CoFInAl_AQA/blob/HEAD/models/model.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":"12713b2504ea68d0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}