</> Code with Papers by Syntology

Papers › CLIP2TV: Align, Match and Distill for Video-Text Retrieval

CLIP2TV: Align, Match and Distill for Video-Text Retrieval

10 Nov 2021arXiv:2111.05610archive 2025-07-28

Zijian Gao, Jingyu Liu, Weiqi Sun, Sheng Chen, Dedan Chang, Lili Zhao

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%.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Representation LearningRetrievalText RetrievalVideo RetrievalVideo-Text Retrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Retrieval MSR-VTT CLIP2TV text-to-video Mean Rank 44.7 #21 of 40 Archive leaderboard report
Video Retrieval MSR-VTT CLIP2TV text-to-video Median Rank 3 #21 of 40 Archive leaderboard report
Video Retrieval MSR-VTT CLIP2TV text-to-video R@1 33.1 #21 of 40 Archive leaderboard report
Video Retrieval MSR-VTT CLIP2TV text-to-video R@10 68.9 #21 of 40 Archive leaderboard report
Video Retrieval MSR-VTT CLIP2TV text-to-video R@5 58.9 #21 of 40 Archive leaderboard report
Video Retrieval MSR-VTT-1kA CLIP2TV text-to-video Mean Rank 12.8 #13 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA CLIP2TV text-to-video Median Rank 1 #13 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA CLIP2TV text-to-video R@1 52.9 #13 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA CLIP2TV text-to-video R@10 86.5 #13 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA CLIP2TV text-to-video R@5 78.5 #13 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA CLIP2TV video-to-text Mean Rank 9.0 #13 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA CLIP2TV video-to-text Median Rank 1 #13 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA CLIP2TV video-to-text R@1 54.1 #13 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA CLIP2TV video-to-text R@10 85.7 #13 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA CLIP2TV video-to-text R@5 77.4 #13 of 63 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections