{"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/clip2video-mastering-video-text-retrieval-via","title":"CLIP2Video: Mastering Video-Text Retrieval via Image CLIP","arxiv_id":"2106.11097","date":"2021-06-21","proceeding":null,"authors":["Han Fang","Pengfei Xiong","Luhui Xu","Yu Chen"],"abstract":"We present CLIP2Video network to transfer the image-language pre-training model to video-text retrieval in an end-to-end manner. Leading approaches in the domain of video-and-language learning try to distill the spatio-temporal video features and multi-modal interaction between videos and languages from a large-scale video-text dataset. Different from them, we leverage pretrained image-language model, simplify it as a two-stage framework with co-learning of image-text and enhancing temporal relations between video frames and video-text respectively, make it able to train on comparatively small datasets. Specifically, based on the spatial semantics captured by Contrastive Language-Image Pretraining (CLIP) model, our model involves a Temporal Difference Block to capture motions at fine temporal video frames, and a Temporal Alignment Block to re-align the tokens of video clips and phrases and enhance the multi-modal correlation. We conduct thorough ablation studies, and achieve state-of-the-art performance on major text-to-video and video-to-text retrieval benchmarks, including new records of retrieval accuracy on MSR-VTT, MSVD and VATEX.","url_abs":"https://arxiv.org/abs/2106.11097v1","url_pdf":"https://arxiv.org/pdf/2106.11097v1.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":"clip2video-mastering-video-text-retrieval-via","repo_url":"https://github.com/CryhanFang/CLIP2Video","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"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-to-text-retrieval","task_name":"Video to Text Retrieval"},{"task_slug":"video-text-retrieval","task_name":"Video-Text Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-retrieval-on-msr-vtt","task":"Video Retrieval","dataset":"MSR-VTT","model":"CLIP2Video","rank_in_archive_order":26,"of":40,"metrics":{"text-to-video Mean Rank":"45.4","text-to-video Median Rank":"4","text-to-video R@1":"29.8","text-to-video R@10":"66.2","text-to-video R@5":"55.5","video-to-text Mean Rank":"5.3","video-to-text Median Rank":"1","video-to-text R@1":"54.6","video-to-text R@10":"90.8","video-to-text R@5":"82.1"},"uses_additional_data":true},{"leaderboard":"/sota/video-retrieval-on-msr-vtt-1ka","task":"Video Retrieval","dataset":"MSR-VTT-1kA","model":"CLIP2Video","rank_in_archive_order":36,"of":63,"metrics":{"text-to-video Mean Rank":"14.6","text-to-video Median Rank":"2","text-to-video R@1":"45.6","text-to-video R@10":"81.7","text-to-video R@5":"72.6","video-to-text Mean Rank":"10.2","video-to-text Median Rank":"2","video-to-text R@1":"43.3","video-to-text R@10":"82.1","video-to-text R@5":"72.3"},"uses_additional_data":true},{"leaderboard":"/sota/video-retrieval-on-vatex","task":"Video Retrieval","dataset":"VATEX","model":"CLIP2Video","rank_in_archive_order":13,"of":13,"metrics":{"text-to-video R@1":"57.3","text-to-video R@10":"90","text-to-video R@50":"95.5"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.11097","atlas_url":"https://app.syntology.ai/?focus=2106.11097","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.11097"}},"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/CryhanFang/CLIP2Video","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"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":"e129344aedf3001d","entry":"init_device","repo":"CryhanFang/CLIP2Video","repo_kind":"official","path":"infer_retrieval.py","file_url":"https://github.com/CryhanFang/CLIP2Video/blob/HEAD/infer_retrieval.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":"e129344aedf3001d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}