{"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/clip-vip-adapting-pre-trained-image-text","title":"CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment","arxiv_id":"2209.06430","date":"2022-09-14","proceeding":null,"authors":["Hongwei Xue","Yuchong Sun","Bei Liu","Jianlong Fu","Ruihua Song","Houqiang Li","Jiebo Luo"],"abstract":"The pre-trained image-text models, like CLIP, have demonstrated the strong power of vision-language representation learned from a large scale of web-collected image-text data. In light of the well-learned visual features, some existing works transfer image representation to video domain and achieve good results. However, how to utilize image-language pre-trained model (e.g., CLIP) for video-language pre-training (post-pretraining) is still under explored. In this paper, we investigate two questions: 1) what are the factors hindering post-pretraining CLIP to further improve the performance on video-language tasks? and 2) how to mitigate the impact of these factors? Through a series of comparative experiments and analyses, we find that the data scale and domain gap between language sources have great impacts. Motivated by these, we propose a Omnisource Cross-modal Learning method equipped with a Video Proxy mechanism on the basis of CLIP, namely CLIP-ViP. Extensive results show that our approach improves the performance of CLIP on video-text retrieval by a large margin. Our model also achieves SOTA results on a variety of datasets, including MSR-VTT, DiDeMo, LSMDC, and ActivityNet. We will release our code and pre-trained CLIP-ViP models at https://github.com/microsoft/XPretrain/tree/main/CLIP-ViP.","url_abs":"https://arxiv.org/abs/2209.06430v4","url_pdf":"https://arxiv.org/pdf/2209.06430v4.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":"clip-vip-adapting-pre-trained-image-text","repo_url":"https://github.com/microsoft/xpretrain","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"text-retrieval","task_name":"Text Retrieval"},{"task_slug":"video-retrieval","task_name":"Video Retrieval"},{"task_slug":"video-text-retrieval","task_name":"Video-Text Retrieval"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-retrieval-on-activitynet","task":"Video Retrieval","dataset":"ActivityNet","model":"CLIP-ViP","rank_in_archive_order":9,"of":31,"metrics":{"text-to-video Median Rank":"1","text-to-video R@1":"61.4","text-to-video R@10":"92.6","text-to-video R@5":"85.7"},"uses_additional_data":true},{"leaderboard":"/sota/video-retrieval-on-didemo","task":"Video Retrieval","dataset":"DiDeMo","model":"CLIP-ViP","rank_in_archive_order":16,"of":40,"metrics":{"text-to-video Median Rank":"1","text-to-video R@1":"55.3","text-to-video R@10":"89.3","text-to-video R@5":"82"},"uses_additional_data":true},{"leaderboard":"/sota/video-retrieval-on-lsmdc","task":"Video Retrieval","dataset":"LSMDC","model":"CLIP-ViP","rank_in_archive_order":9,"of":38,"metrics":{"text-to-video Median Rank":"5","text-to-video R@1":"30.7","text-to-video R@10":"60.6","text-to-video R@5":"51.4"},"uses_additional_data":true},{"leaderboard":"/sota/video-retrieval-on-msr-vtt-1ka","task":"Video Retrieval","dataset":"MSR-VTT-1kA","model":"CLIP-ViP","rank_in_archive_order":2,"of":63,"metrics":{"text-to-video Median Rank":"1.0","text-to-video R@1":"57.7","text-to-video R@10":"88.2","text-to-video R@5":"80.5"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2209.06430","atlas_url":"https://app.syntology.ai/?focus=2209.06430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.06430"}},"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":"deterministic:regex_extraction","url":"https://github.com/microsoft/XPretrain","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/microsoft/xpretrain","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_fixture":1,"ran":1,"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":4,"samples":[{"code_sha256_prefix":"062b60459dee65d8","entry":"split_cls","repo":"microsoft/xpretrain","repo_kind":"official","path":"CLIP-ViP/src/modeling/CLIP_ViP.py","file_url":"https://github.com/microsoft/xpretrain/blob/HEAD/CLIP-ViP/src/modeling/CLIP_ViP.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"062b60459dee65d8"}},{"code_sha256_prefix":"b607b001e42780f1","entry":"CLIPVisionViPEmbeddings","repo":"microsoft/xpretrain","repo_kind":"official","path":"CLIP-ViP/src/modeling/CLIP_ViP.py","file_url":"https://github.com/microsoft/xpretrain/blob/HEAD/CLIP-ViP/src/modeling/CLIP_ViP.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"b607b001e42780f1"}},{"code_sha256_prefix":"e5b89b1f72c319ed","entry":"clip_loss","repo":"microsoft/xpretrain","repo_kind":"official","path":"CLIP-ViP/src/modeling/CLIP_ViP.py","file_url":"https://github.com/microsoft/xpretrain/blob/HEAD/CLIP-ViP/src/modeling/CLIP_ViP.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"e5b89b1f72c319ed"}},{"code_sha256_prefix":"4675779aec92d6c0","entry":"contrastive_loss","repo":"microsoft/xpretrain","repo_kind":"official","path":"CLIP-ViP/src/modeling/CLIP_ViP.py","file_url":"https://github.com/microsoft/xpretrain/blob/HEAD/CLIP-ViP/src/modeling/CLIP_ViP.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"4675779aec92d6c0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}