Papers › CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval

CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval

18 Apr 2021arXiv:2104.08860archive 2025-07-28

Huaishao Luo, Lei Ji, Ming Zhong, Yang Chen, Wen Lei, Nan Duan, Tianrui Li

Video-text retrieval plays an essential role in multi-modal research and has been widely used in many real-world web applications. The CLIP (Contrastive Language-Image Pre-training), an image-language pre-training model, has demonstrated the power of visual concepts learning from web collected image-text datasets. In this paper, we propose a CLIP4Clip model to transfer the knowledge of the CLIP model to video-language retrieval in an end-to-end manner. Several questions are investigated via empirical studies: 1) Whether image feature is enough for video-text retrieval? 2) How a post-pretraining on a large-scale video-text dataset based on the CLIP affect the performance? 3) What is the practical mechanism to model temporal dependency between video frames? And 4) The Hyper-parameters sensitivity of the model on video-text retrieval task. Extensive experimental results present that the CLIP4Clip model transferred from the CLIP can achieve SOTA results on various video-text retrieval datasets, including MSR-VTT, MSVC, LSMDC, ActivityNet, and DiDeMo. We release our code at https://github.com/ArrowLuo/CLIP4Clip.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 4 code samples: 1 from 1 repository linked to this paper, 3 identical to code harvested from another paper's repository. Across all 4: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 0 ran (0 with no instrument failure; 0 where Syntology's instrument failed); 3 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ArrowLuo/CLIP4Clip officialmentioned in papermentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
facebookresearch/EgoTV mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
roudimit/AVLnet mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
willard-yuan/video-text-retrieval-papers mentioned on GitHubSyntology: not harvested report
towhee-io/towhee pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Perceiver: General Perception with Iterative Attention (arXiv:2103.03206; that paper's own run record: 41 ran (of which 20 constructed an object rather than computing a result; 30 with no instrument failure: 0 honoured, 2 violated, 28 with no contract checked; 11 where Syntology's instrument failed) · 14 unverified), LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval (arXiv:2103.08784; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified) and 9 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

4 samples harvested: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
1ran · our draft was wrong
1ran; the contract check could not run
1unverified

Licence: 3 of the 4 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from ArrowLuo/CLIP4Clip. 3 samples are listed last, in a group without a repository. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

ArrowLuo/CLIP4Clip official repository 1 sample, 0 ran · 1 unverified
get_args in 84 papers main_task_retrieval.py unverified MIT (permissive) · 5dad69c6b079e518 · report
Repository not located 3 samples, 3 ran (2 instrument-failed) · 0 unverified
3 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
check_attr in 12 papers repository not located ran · violated contract licence of this copy not recorded · 47c2715feba5fd6b · report fixture: signature target_name:str/0/str, task_config:TaskConfig/0/? · returned bool · level recorded 2026-09-22
init_device in 20 papers repository not located ran; the contract check could not run (RAISES) licence of this copy not recorded · a0c23f10479a984e · report fixture: returned tuple · level recorded 2026-09-22
update_attr in 10 papers repository not located ran · our draft was wrong licence of this copy not recorded · d34a2226d2cf142e · report fixture: signature target_name:str/0/str, target_config:TargetConfig/0/?, target_attr_name:str/0/str, source_config:SourceConfig/0/?, source_attr_name:str/0/str, default_value:NoneType/0/? · returned TargetConfig · level recorded 2026-09-22

Tasks

RetrievalText RetrievalText to Video RetrievalVideo RetrievalVideo UnderstandingVideo-Text RetrievalZero-Shot Video Retrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text to Video Retrieval MSR-VTT CLIP4Clip text-to-video R@1 44.5 #1 of 1 Archive leaderboard report
Video Retrieval ActivityNet CLIP4Clip text-to-video Mean Rank 7.5 #25 of 31 Archive leaderboard report
Video Retrieval ActivityNet CLIP4Clip text-to-video Median Rank 2 #25 of 31 Archive leaderboard report
Video Retrieval ActivityNet CLIP4Clip text-to-video R@1 40.5 #25 of 31 Archive leaderboard report
Video Retrieval ActivityNet CLIP4Clip text-to-video R@5 73.4 #25 of 31 Archive leaderboard report
Video Retrieval ActivityNet CLIP4Clip text-to-video R@50 98.2 #25 of 31 Archive leaderboard report
Video Retrieval DiDeMo CLIP4Clip text-to-video Mean Rank 17.5 #34 of 40 Archive leaderboard report
Video Retrieval DiDeMo CLIP4Clip text-to-video Median Rank 2.0 #34 of 40 Archive leaderboard report
Video Retrieval DiDeMo CLIP4Clip text-to-video R@1 43.4 #34 of 40 Archive leaderboard report
Video Retrieval DiDeMo CLIP4Clip text-to-video R@10 80.6 #34 of 40 Archive leaderboard report
Video Retrieval DiDeMo CLIP4Clip text-to-video R@5 70.2 #34 of 40 Archive leaderboard report
Video Retrieval LSMDC CLIP4Clip text-to-video Mean Rank 58.0 #24 of 38 Archive leaderboard report
Video Retrieval LSMDC CLIP4Clip text-to-video R@1 21.6 #24 of 38 Archive leaderboard report
Video Retrieval LSMDC CLIP4Clip text-to-video R@10 49.8 #24 of 38 Archive leaderboard report
Video Retrieval LSMDC CLIP4Clip text-to-video R@5 41.8 #24 of 38 Archive leaderboard report
Video Retrieval MSR-VTT CLIP4Clip-seqTransf text-to-video R@1 44.5 #14 of 40 Archive leaderboard report
Video Retrieval MSR-VTT CLIP4Clip-seqTransf text-to-video R@10 81.6 #14 of 40 Archive leaderboard report
Video Retrieval MSR-VTT CLIP4Clip-seqTransf text-to-video R@5 71.4 #14 of 40 Archive leaderboard report
Video Retrieval MSR-VTT-1kA CLIP4Clip text-to-video Mean Rank 15.3 #61 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA CLIP4Clip text-to-video Median Rank 2 #61 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA CLIP4Clip text-to-video R@10 81.6 #61 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA CLIP4Clip video-to-text Median Rank 2 #61 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA CLIP4Clip video-to-text R@1 42.7 #61 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA CLIP4Clip video-to-text R@10 80.6 #61 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA CLIP4Clip video-to-text R@5 70.9 #61 of 63 Archive leaderboard report
Video Retrieval MSVD CLIP4Clip text-to-video Mean Rank 10.0 #19 of 24 Archive leaderboard report
Video Retrieval MSVD CLIP4Clip text-to-video Median Rank 2 #19 of 24 Archive leaderboard report
Video Retrieval MSVD CLIP4Clip text-to-video R@1 46.2 #19 of 24 Archive leaderboard report
Video Retrieval MSVD CLIP4Clip text-to-video R@10 84.6 #19 of 24 Archive leaderboard report
Video Retrieval MSVD CLIP4Clip text-to-video R@5 76.1 #19 of 24 Archive leaderboard report
Video Retrieval MSVD CLIP4Clip video-to-text Median Rank 1 #19 of 24 Archive leaderboard report
Video Retrieval MSVD CLIP4Clip video-to-text R@1 62.0 #19 of 24 Archive leaderboard report
Video Retrieval MSVD CLIP4Clip video-to-text R@10 92.6 #19 of 24 Archive leaderboard report
Video Retrieval MSVD CLIP4Clip video-to-text R@5 87.3 #19 of 24 Archive leaderboard report
Zero-Shot Video Retrieval LSMDC CLIP4Clip text-to-video Mean Rank 117 #12 of 16 Archive leaderboard report
Zero-Shot Video Retrieval LSMDC CLIP4Clip text-to-video Median Rank 28 #12 of 16 Archive leaderboard report
Zero-Shot Video Retrieval LSMDC CLIP4Clip text-to-video R@1 15.1 #12 of 16 Archive leaderboard report
Zero-Shot Video Retrieval LSMDC CLIP4Clip text-to-video R@10 36.4 #12 of 16 Archive leaderboard report
Zero-Shot Video Retrieval LSMDC CLIP4Clip text-to-video R@5 28.5 #12 of 16 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT CLIP4Clip text-to-video Mean Rank 34.0 #21 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT CLIP4Clip text-to-video Median Rank 4 #21 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT CLIP4Clip text-to-video R@1 32.0 #21 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT CLIP4Clip text-to-video R@10 66.9 #21 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT CLIP4Clip text-to-video R@5 57.0 #21 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSVD CLIP4Clip text-to-video Mean Rank 17.8 #12 of 14 Archive leaderboard report
Zero-Shot Video Retrieval MSVD CLIP4Clip text-to-video Median Rank 2 #12 of 14 Archive leaderboard report
Zero-Shot Video Retrieval MSVD CLIP4Clip text-to-video R@1 38.5 #12 of 14 Archive leaderboard report
Zero-Shot Video Retrieval MSVD CLIP4Clip text-to-video R@10 76.8 #12 of 14 Archive leaderboard report
Zero-Shot Video Retrieval MSVD CLIP4Clip text-to-video R@5 66.9 #12 of 14 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.

Methods

CLIP

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