{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/dual-path-adaptation-from-image-to-video","title":"Dual-path Adaptation from Image to Video Transformers","arxiv_id":"2303.09857","date":"2023-03-17","proceeding":"CVPR 2023 1","authors":["Jungin Park","Jiyoung Lee","Kwanghoon Sohn"],"abstract":"In this paper, we efficiently transfer the surpassing representation power of the vision foundation models, such as ViT and Swin, for video understanding with only a few trainable parameters. Previous adaptation methods have simultaneously considered spatial and temporal modeling with a unified learnable module but still suffered from fully leveraging the representative capabilities of image transformers. We argue that the popular dual-path (two-stream) architecture in video models can mitigate this problem. We propose a novel DualPath adaptation separated into spatial and temporal adaptation paths, where a lightweight bottleneck adapter is employed in each transformer block. Especially for temporal dynamic modeling, we incorporate consecutive frames into a grid-like frameset to precisely imitate vision transformers' capability that extrapolates relationships between tokens. In addition, we extensively investigate the multiple baselines from a unified perspective in video understanding and compare them with DualPath. Experimental results on four action recognition benchmarks prove that pretrained image transformers with DualPath can be effectively generalized beyond the data domain.","url_abs":"https://arxiv.org/abs/2303.09857v1","url_pdf":"https://arxiv.org/pdf/2303.09857v1.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":"dual-path-adaptation-from-image-to-video","repo_url":"https://github.com/park-jungin/dualpath","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"action-recognition-in-videos-2","task_name":"Action Recognition In Videos"},{"task_slug":"activity-recognition","task_name":"Activity Recognition"},{"task_slug":"activity-recognition-in-videos","task_name":"Activity Recognition In Videos"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[{"method_slug":"adapter","method_name":"Adapter"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-classification-on-diving-48","task":"Action Classification","dataset":"Diving-48","model":"DualPath w/ ViT-B/16","rank_in_archive_order":1,"of":1,"metrics":{"Acc@1":"88.7"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-hmdb51","task":"Action Classification","dataset":"HMDB51","model":"DualPath w/ ViT-B/16 MLPs.","rank_in_archive_order":1,"of":1,"metrics":{"Acc@1":"75.6"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"DualPath w/ ViT-L/14","rank_in_archive_order":33,"of":207,"metrics":{"Acc@1":"87.7","Acc@5":"97.8"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"DualPath w/ ViT-B/16","rank_in_archive_order":53,"of":207,"metrics":{"Acc@1":"85.4","Acc@5":"97.1"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-on-diving-48","task":"Action Recognition","dataset":"Diving-48","model":"DUALPATH","rank_in_archive_order":4,"of":18,"metrics":{"Accuracy":"88.7"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2303.09857","atlas_url":"https://app.syntology.ai/?focus=2303.09857","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2303.09857"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2303.09857\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2303.09857"},"call":"get_concepts_for_paper(arxiv_id=\"2303.09857\")"}],"by_repo":[{"repo":"park-jungin/dualpath","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"300a3a045e66db0bb38f866f7d0f8b69055db42a201cd3732a84b64a333fbc23","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}