{"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/learning-procedure-aware-video-representation","title":"Learning Procedure-aware Video Representation from Instructional Videos and Their Narrations","arxiv_id":"2303.17839","date":"2023-03-31","proceeding":"CVPR 2023 1","authors":["Yiwu Zhong","Licheng Yu","Yang Bai","Shangwen Li","Xueting Yan","Yin Li"],"abstract":"The abundance of instructional videos and their narrations over the Internet offers an exciting avenue for understanding procedural activities. In this work, we propose to learn video representation that encodes both action steps and their temporal ordering, based on a large-scale dataset of web instructional videos and their narrations, without using human annotations. Our method jointly learns a video representation to encode individual step concepts, and a deep probabilistic model to capture both temporal dependencies and immense individual variations in the step ordering. We empirically demonstrate that learning temporal ordering not only enables new capabilities for procedure reasoning, but also reinforces the recognition of individual steps. Our model significantly advances the state-of-the-art results on step classification (+2.8% / +3.3% on COIN / EPIC-Kitchens) and step forecasting (+7.4% on COIN). Moreover, our model attains promising results in zero-shot inference for step classification and forecasting, as well as in predicting diverse and plausible steps for incomplete procedures. Our code is available at https://github.com/facebookresearch/ProcedureVRL.","url_abs":"https://arxiv.org/abs/2303.17839v1","url_pdf":"https://arxiv.org/pdf/2303.17839v1.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":"learning-procedure-aware-video-representation","repo_url":"https://github.com/facebookresearch/procedurevrl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.17839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.17839"}},"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/facebookresearch/procedurevrl","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/facebookresearch/ProcedureVRL","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":3,"unverified":2},"by_repo_kind":{"official":{"samples":5,"ran":3,"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":"1385cee74dfe54ab","entry":"ResidualAttentionBlock","repo":"facebookresearch/ProcedureVRL","repo_kind":"official","path":"lib/models/tfm_model.py","file_url":"https://github.com/facebookresearch/ProcedureVRL/blob/HEAD/lib/models/tfm_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"1385cee74dfe54ab"}},{"code_sha256_prefix":"a8e06e074c8ee49d","entry":"SinusoidalPositionEmbeddings","repo":"facebookresearch/ProcedureVRL","repo_kind":"official","path":"lib/models/tfm_model.py","file_url":"https://github.com/facebookresearch/ProcedureVRL/blob/HEAD/lib/models/tfm_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"a8e06e074c8ee49d"}},{"code_sha256_prefix":"08bd39c741d6dbd2","entry":"TemporalModelling","repo":"facebookresearch/ProcedureVRL","repo_kind":"official","path":"lib/models/tfm_model.py","file_url":"https://github.com/facebookresearch/ProcedureVRL/blob/HEAD/lib/models/tfm_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"08bd39c741d6dbd2"}},{"code_sha256_prefix":"7e73618add2cd74c","entry":"DiffusionTransformer","repo":"facebookresearch/ProcedureVRL","repo_kind":"official","path":"lib/models/tfm_model.py","file_url":"https://github.com/facebookresearch/ProcedureVRL/blob/HEAD/lib/models/tfm_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"7e73618add2cd74c"}},{"code_sha256_prefix":"efb41cfbeca22b63","entry":"ennoise","repo":"facebookresearch/ProcedureVRL","repo_kind":"official","path":"lib/models/tfm_model.py","file_url":"https://github.com/facebookresearch/ProcedureVRL/blob/HEAD/lib/models/tfm_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"efb41cfbeca22b63"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}