{"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/phi-bridging-domain-shift-in-long-term-action","title":"PHI: Bridging Domain Shift in Long-Term Action Quality Assessment via Progressive Hierarchical Instruction","arxiv_id":"2505.19972","date":"2025-05-26","proceeding":null,"authors":["Kanglei Zhou","Hubert P. H. Shum","Frederick W. B. Li","Xingxing Zhang","Xiaohui Liang"],"abstract":"Long-term Action Quality Assessment (AQA) aims to evaluate the quantitative performance of actions in long videos. However, existing methods face challenges due to domain shifts between the pre-trained large-scale action recognition backbones and the specific AQA task, thereby hindering their performance. This arises since fine-tuning resource-intensive backbones on small AQA datasets is impractical. We address this by identifying two levels of domain shift: task-level, regarding differences in task objectives, and feature-level, regarding differences in important features. For feature-level shifts, which are more detrimental, we propose Progressive Hierarchical Instruction (PHI) with two strategies. First, Gap Minimization Flow (GMF) leverages flow matching to progressively learn a fast flow path that reduces the domain gap between initial and desired features across shallow to deep layers. Additionally, a temporally-enhanced attention module captures long-range dependencies essential for AQA. Second, List-wise Contrastive Regularization (LCR) facilitates coarse-to-fine alignment by comprehensively comparing batch pairs to learn fine-grained cues while mitigating domain shift. Integrating these modules, PHI offers an effective solution. Experiments demonstrate that PHI achieves state-of-the-art performance on three representative long-term AQA datasets, proving its superiority in addressing the domain shift for long-term AQA.","url_abs":"https://arxiv.org/abs/2505.19972v1","url_pdf":"https://arxiv.org/pdf/2505.19972v1.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":"phi-bridging-domain-shift-in-long-term-action","repo_url":"https://github.com/zhoukanglei/phi_aqa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"action-quality-assessment","task_name":"Action Quality Assessment"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.19972","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19972"}},"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/zhoukanglei/phi_aqa","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"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":"ab477db0564a8017","entry":"choose_activate","repo":"zhoukanglei/phi_aqa","repo_kind":"official","path":"models/model_phi.py","file_url":"https://github.com/zhoukanglei/phi_aqa/blob/HEAD/models/model_phi.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ab477db0564a8017"}},{"code_sha256_prefix":"6347c7b79b0cbdd1","entry":"choose_align","repo":"zhoukanglei/phi_aqa","repo_kind":"official","path":"models/loss.py","file_url":"https://github.com/zhoukanglei/phi_aqa/blob/HEAD/models/loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6347c7b79b0cbdd1"}},{"code_sha256_prefix":"5b1dedae123fedaf","entry":"compute_matric","repo":"zhoukanglei/phi_aqa","repo_kind":"official","path":"utils.py","file_url":"https://github.com/zhoukanglei/phi_aqa/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5b1dedae123fedaf"}},{"code_sha256_prefix":"72be75429e05bdf3","entry":"etf","repo":"zhoukanglei/phi_aqa","repo_kind":"official","path":"models/model_phi.py","file_url":"https://github.com/zhoukanglei/phi_aqa/blob/HEAD/models/model_phi.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"72be75429e05bdf3"}},{"code_sha256_prefix":"72c3954c8a6f336f","entry":"generate_orthogonal_matrix","repo":"zhoukanglei/phi_aqa","repo_kind":"official","path":"models/loss.py","file_url":"https://github.com/zhoukanglei/phi_aqa/blob/HEAD/models/loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"72c3954c8a6f336f"}},{"code_sha256_prefix":"4fc7a1f729fddee6","entry":"generate_random_orthogonal_matrix","repo":"zhoukanglei/phi_aqa","repo_kind":"official","path":"models/model_phi.py","file_url":"https://github.com/zhoukanglei/phi_aqa/blob/HEAD/models/model_phi.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4fc7a1f729fddee6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}