{"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/unsupervised-video-domain-adaptation-for-1","title":"Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective","arxiv_id":"2208.07365","date":"2022-08-15","proceeding":"NeurIPS 2023 11","authors":["Pengfei Wei","Lingdong Kong","Xinghua Qu","Yi Ren","Zhiqiang Xu","Jing Jiang","Xiang Yin"],"abstract":"Unsupervised video domain adaptation is a practical yet challenging task. In this work, for the first time, we tackle it from a disentanglement view. Our key idea is to handle the spatial and temporal domain divergence separately through disentanglement. Specifically, we consider the generation of cross-domain videos from two sets of latent factors, one encoding the static information and another encoding the dynamic information. A Transfer Sequential VAE (TranSVAE) framework is then developed to model such generation. To better serve for adaptation, we propose several objectives to constrain the latent factors. With these constraints, the spatial divergence can be readily removed by disentangling the static domain-specific information out, and the temporal divergence is further reduced from both frame- and video-levels through adversarial learning. Extensive experiments on the UCF-HMDB, Jester, and Epic-Kitchens datasets verify the effectiveness and superiority of TranSVAE compared with several state-of-the-art approaches. Code is publicly available.","url_abs":"https://arxiv.org/abs/2208.07365v3","url_pdf":"https://arxiv.org/pdf/2208.07365v3.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":"unsupervised-video-domain-adaptation-for-1","repo_url":"https://github.com/ldkong1205/transvae","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"disentanglement","task_name":"Disentanglement"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2208.07365","atlas_url":"https://app.syntology.ai/?focus=2208.07365","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.07365"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ldkong1205/transvae","reach":null}],"summary":{"ran":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":3,"samples":[{"code_sha256_prefix":"1ef67ff5a31f0abd","entry":"GradReverse","repo":"ldkong1205/transvae","repo_kind":"official","path":"exp/TranSVAE.py","file_url":"https://github.com/ldkong1205/transvae/blob/HEAD/exp/TranSVAE.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":"1ef67ff5a31f0abd"}},{"code_sha256_prefix":"80f6baca01676ab3","entry":"RelationModuleMultiScale","repo":"ldkong1205/transvae","repo_kind":"official","path":"exp/TranSVAE.py","file_url":"https://github.com/ldkong1205/transvae/blob/HEAD/exp/TranSVAE.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"80f6baca01676ab3"}},{"code_sha256_prefix":"8cfac4b471c1648e","entry":"TranSVAE_Video","repo":"ldkong1205/transvae","repo_kind":"official","path":"exp/TranSVAE.py","file_url":"https://github.com/ldkong1205/transvae/blob/HEAD/exp/TranSVAE.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":"8cfac4b471c1648e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}