{"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/clip2tv-an-empirical-study-on-transformer","title":"CLIP2TV: Align, Match and Distill for Video-Text Retrieval","arxiv_id":"2111.05610","date":"2021-11-10","proceeding":null,"authors":["Zijian Gao","Jingyu Liu","Weiqi Sun","Sheng Chen","Dedan Chang","Lili Zhao"],"abstract":"Modern video-text retrieval frameworks basically consist of three parts: video encoder, text encoder and the similarity head. With the success on both visual and textual representation learning, transformer based encoders and fusion methods have also been adopted in the field of video-text retrieval. In this report, we present CLIP2TV, aiming at exploring where the critical elements lie in transformer based methods. To achieve this, We first revisit some recent works on multi-modal learning, then introduce some techniques into video-text retrieval, finally evaluate them through extensive experiments in different configurations. Notably, CLIP2TV achieves 52.9@R1 on MSR-VTT dataset, outperforming the previous SOTA result by 4.1%.","url_abs":"https://arxiv.org/abs/2111.05610v2","url_pdf":"https://arxiv.org/pdf/2111.05610v2.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":[],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"},{"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":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-retrieval-on-msr-vtt","task":"Video Retrieval","dataset":"MSR-VTT","model":"CLIP2TV","rank_in_archive_order":21,"of":40,"metrics":{"text-to-video Mean Rank":"44.7","text-to-video Median Rank":"3","text-to-video R@1":"33.1","text-to-video R@10":"68.9","text-to-video R@5":"58.9"},"uses_additional_data":true},{"leaderboard":"/sota/video-retrieval-on-msr-vtt-1ka","task":"Video Retrieval","dataset":"MSR-VTT-1kA","model":"CLIP2TV","rank_in_archive_order":13,"of":63,"metrics":{"text-to-video Mean Rank":"12.8","text-to-video Median Rank":"1","text-to-video R@1":"52.9","text-to-video R@10":"86.5","text-to-video R@5":"78.5","video-to-text Mean Rank":"9.0","video-to-text Median Rank":"1","video-to-text R@1":"54.1","video-to-text R@10":"85.7","video-to-text R@5":"77.4"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2111.05610","atlas_url":"https://app.syntology.ai/?focus=2111.05610","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}