Papers › A Straightforward Framework For Video Retrieval Using CLIP

A Straightforward Framework For Video Retrieval Using CLIP

24 Feb 2021arXiv:2102.12443archive 2025-07-28

Jesús Andrés Portillo-Quintero, José Carlos Ortiz-Bayliss, Hugo Terashima-Marín

Video Retrieval is a challenging task where a text query is matched to a video or vice versa. Most of the existing approaches for addressing such a problem rely on annotations made by the users. Although simple, this approach is not always feasible in practice. In this work, we explore the application of the language-image model, CLIP, to obtain video representations without the need for said annotations. This model was explicitly trained to learn a common space where images and text can be compared. Using various techniques described in this document, we extended its application to videos, obtaining state-of-the-art results on the MSR-VTT and MSVD benchmarks.

PaperPDFCode

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

Code

Deferf/CLIP_Video_Representation officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

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

Tasks

RetrievalVideo Retrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Retrieval LSMDC CLIP text-to-video Median Rank 56.5 #31 of 38 Archive leaderboard report
Video Retrieval LSMDC CLIP text-to-video R@1 11.3 #31 of 38 Archive leaderboard report
Video Retrieval LSMDC CLIP text-to-video R@10 29.2 #31 of 38 Archive leaderboard report
Video Retrieval LSMDC CLIP text-to-video R@5 22.7 #31 of 38 Archive leaderboard report
Video Retrieval LSMDC CLIP video-to-text Median Rank 73 #31 of 38 Archive leaderboard report
Video Retrieval LSMDC CLIP video-to-text R@1 6.8 #31 of 38 Archive leaderboard report
Video Retrieval LSMDC CLIP video-to-text R@10 22.1 #31 of 38 Archive leaderboard report
Video Retrieval LSMDC CLIP video-to-text R@5 16.4 #31 of 38 Archive leaderboard report
Video Retrieval MSR-VTT CLIP text-to-video Median Rank 10 #32 of 40 Archive leaderboard report
Video Retrieval MSR-VTT CLIP text-to-video R@1 21.4 #32 of 40 Archive leaderboard report
Video Retrieval MSR-VTT CLIP text-to-video R@10 50.4 #32 of 40 Archive leaderboard report
Video Retrieval MSR-VTT CLIP text-to-video R@5 41.1 #32 of 40 Archive leaderboard report
Video Retrieval MSR-VTT CLIP video-to-text Median Rank 2 #32 of 40 Archive leaderboard report
Video Retrieval MSR-VTT CLIP video-to-text R@1 40.3 #32 of 40 Archive leaderboard report
Video Retrieval MSR-VTT CLIP video-to-text R@10 79.2 #32 of 40 Archive leaderboard report
Video Retrieval MSR-VTT CLIP video-to-text R@5 69.7 #32 of 40 Archive leaderboard report
Video Retrieval MSR-VTT-1kA CLIP text-to-video Median Rank 4 #47 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA CLIP text-to-video R@1 31.2 #47 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA CLIP text-to-video R@10 64.2 #47 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA CLIP text-to-video R@5 53.7 #47 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA CLIP video-to-text Median Rank 5 #47 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA CLIP video-to-text R@1 27.2 #47 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA CLIP video-to-text R@10 62.6 #47 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA CLIP video-to-text R@5 51.7 #47 of 63 Archive leaderboard report
Video Retrieval MSVD CLIP text-to-video Median Rank 3.0 #21 of 24 Archive leaderboard report
Video Retrieval MSVD CLIP text-to-video R@1 37 #21 of 24 Archive leaderboard report
Video Retrieval MSVD CLIP text-to-video R@10 73.8 #21 of 24 Archive leaderboard report
Video Retrieval MSVD CLIP text-to-video R@5 64.1 #21 of 24 Archive leaderboard report
Video Retrieval MSVD CLIP video-to-text Median Rank 1 #21 of 24 Archive leaderboard report
Video Retrieval MSVD CLIP video-to-text R@1 59.9 #21 of 24 Archive leaderboard report
Video Retrieval MSVD CLIP video-to-text R@10 90.7 #21 of 24 Archive leaderboard report
Video Retrieval MSVD CLIP video-to-text R@5 85.2 #21 of 24 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