{"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/diffusion-action-segmentation","title":"Diffusion Action Segmentation","arxiv_id":"2303.17959","date":"2023-03-31","proceeding":"ICCV 2023 1","authors":["Daochang Liu","Qiyue Li","AnhDung Dinh","Tingting Jiang","Mubarak Shah","Chang Xu"],"abstract":"Temporal action segmentation is crucial for understanding long-form videos. Previous works on this task commonly adopt an iterative refinement paradigm by using multi-stage models. We propose a novel framework via denoising diffusion models, which nonetheless shares the same inherent spirit of such iterative refinement. In this framework, action predictions are iteratively generated from random noise with input video features as conditions. To enhance the modeling of three striking characteristics of human actions, including the position prior, the boundary ambiguity, and the relational dependency, we devise a unified masking strategy for the conditioning inputs in our framework. Extensive experiments on three benchmark datasets, i.e., GTEA, 50Salads, and Breakfast, are performed and the proposed method achieves superior or comparable results to state-of-the-art methods, showing the effectiveness of a generative approach for action segmentation.","url_abs":"https://arxiv.org/abs/2303.17959v2","url_pdf":"https://arxiv.org/pdf/2303.17959v2.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":"diffusion-action-segmentation","repo_url":"https://github.com/finspire13/diffact","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-segmentation","task_name":"Action Segmentation"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":null,"task_name":"Position"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"temporal-action-segmentation","task_name":"Temporal Action Segmentation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-segmentation-on-50-salads-1","task":"Action Segmentation","dataset":"50 Salads","model":"DiffAct","rank_in_archive_order":4,"of":28,"metrics":{"Acc":"88.9","Edit":"85.0","F1@10%":"90.1","F1@25%":"89.2","F1@50%":"83.7"},"uses_additional_data":false},{"leaderboard":"/sota/action-segmentation-on-breakfast-1","task":"Action Segmentation","dataset":"Breakfast","model":"DiffAct","rank_in_archive_order":5,"of":37,"metrics":{"Acc":"76.4","Average F1":"73.6","Edit":"78.4","F1@10%":"80.3","F1@25%":"75.9","F1@50%":"64.6"},"uses_additional_data":false},{"leaderboard":"/sota/action-segmentation-on-gtea-1","task":"Action Segmentation","dataset":"GTEA","model":"DiffAct","rank_in_archive_order":3,"of":28,"metrics":{"Acc":"82.2","Edit":"89.6","F1@10%":"92.5","F1@25%":"91.5","F1@50%":"84.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.17959","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.17959"}},"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/finspire13/diffact","reach":null}],"summary":{"ran":5,"unverified":4},"by_repo_kind":{"listed":{"samples":9,"ran":5,"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":"fd77486cce5e32ae","entry":"MixedConvAttModule","repo":"finspire13/diffact","repo_kind":"listed","path":"model.py","file_url":"https://github.com/finspire13/diffact/blob/HEAD/model.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":"fd77486cce5e32ae"}},{"code_sha256_prefix":"ef74b7aaf3b39261","entry":"MixedConvAttentionLayer","repo":"finspire13/diffact","repo_kind":"listed","path":"model.py","file_url":"https://github.com/finspire13/diffact/blob/HEAD/model.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":"ef74b7aaf3b39261"}},{"code_sha256_prefix":"32b6836e0fb9fd26","entry":"MixedConvAttentionLayerV2","repo":"finspire13/diffact","repo_kind":"listed","path":"model.py","file_url":"https://github.com/finspire13/diffact/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"32b6836e0fb9fd26"}},{"code_sha256_prefix":"a26089b06616104c","entry":"denormalize","repo":"finspire13/diffact","repo_kind":"listed","path":"model.py","file_url":"https://github.com/finspire13/diffact/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a26089b06616104c"}},{"code_sha256_prefix":"2e8cfd3fd1d06402","entry":"normalize","repo":"finspire13/diffact","repo_kind":"listed","path":"model.py","file_url":"https://github.com/finspire13/diffact/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2e8cfd3fd1d06402"}},{"code_sha256_prefix":"17f4f458e497d756","entry":"ASDiffusionModel","repo":"finspire13/diffact","repo_kind":"listed","path":"model.py","file_url":"https://github.com/finspire13/diffact/blob/HEAD/model.py","link_basis":"first_harvest_node","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":"17f4f458e497d756"}},{"code_sha256_prefix":"d5e99d7e89351b01","entry":"DecoderModel","repo":"finspire13/diffact","repo_kind":"listed","path":"model.py","file_url":"https://github.com/finspire13/diffact/blob/HEAD/model.py","link_basis":"first_harvest_node","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":"d5e99d7e89351b01"}},{"code_sha256_prefix":"e851843728ef46cd","entry":"EncoderModel","repo":"finspire13/diffact","repo_kind":"listed","path":"model.py","file_url":"https://github.com/finspire13/diffact/blob/HEAD/model.py","link_basis":"first_harvest_node","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":"e851843728ef46cd"}},{"code_sha256_prefix":"eeea21116921cdb3","entry":"MixedConvAttModuleV2","repo":"finspire13/diffact","repo_kind":"listed","path":"model.py","file_url":"https://github.com/finspire13/diffact/blob/HEAD/model.py","link_basis":"first_harvest_node","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":"eeea21116921cdb3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}