Papers › X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval

X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval

15 Jul 2022arXiv:2207.07285archive 2025-07-28

Yiwei Ma, Guohai Xu, Xiaoshuai Sun, Ming Yan, Ji Zhang, Rongrong Ji

Video-text retrieval has been a crucial and fundamental task in multi-modal research. The development of video-text retrieval has been considerably promoted by large-scale multi-modal contrastive pre-training, which primarily focuses on coarse-grained or fine-grained contrast. However, cross-grained contrast, which is the contrast between coarse-grained representations and fine-grained representations, has rarely been explored in prior research. Compared with fine-grained or coarse-grained contrasts, cross-grained contrast calculate the correlation between coarse-grained features and each fine-grained feature, and is able to filter out the unnecessary fine-grained features guided by the coarse-grained feature during similarity calculation, thus improving the accuracy of retrieval. To this end, this paper presents a novel multi-grained contrastive model, namely X-CLIP, for video-text retrieval. However, another challenge lies in the similarity aggregation problem, which aims to aggregate fine-grained and cross-grained similarity matrices to instance-level similarity. To address this challenge, we propose the Attention Over Similarity Matrix (AOSM) module to make the model focus on the contrast between essential frames and words, thus lowering the impact of unnecessary frames and words on retrieval results. With multi-grained contrast and the proposed AOSM module, X-CLIP achieves outstanding performance on five widely-used video-text retrieval datasets, including MSR-VTT (49.3 R@1), MSVD (50.4 R@1), LSMDC (26.1 R@1), DiDeMo (47.8 R@1) and ActivityNet (46.2 R@1). It outperforms the previous state-of-theart by +6.3%, +6.6%, +11.1%, +6.7%, +3.8% relative improvements on these benchmarks, demonstrating the superiority of multi-grained contrast and AOSM.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2207.07285")

Code

Syntology Ran 1 of 2 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · fixture could not drive it.

By repository: official repository: 1 sample from 1 repository, 0 ran; 1 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.

xuguohai/X-CLIP officialmentioned in papermentioned on GitHubpytorch 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

2 samples harvested; 1 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · fixture could not drive it
1unverified

Licence: 1 of the 2 samples is 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 xuguohai/X-CLIP. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

get_args xuguohai/X-CLIP/main_xclip.py official repository unverified MIT (permissive) · fe6c2cd80d97afae · report
init_device identical code first harvested elsewhere ran · fixture could not drive it licence of this copy not recorded · a0c23f10479a984e · report

Tasks

Contrastive LearningRetrievalText RetrievalVideo RetrievalVideo-Text Retrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Retrieval ActivityNet X-CLIP text-to-video Mean Rank 6.8 #21 of 31 Archive leaderboard report
Video Retrieval ActivityNet X-CLIP text-to-video R@1 46.2 #21 of 31 Archive leaderboard report
Video Retrieval ActivityNet X-CLIP text-to-video R@5 75.5 #21 of 31 Archive leaderboard report
Video Retrieval ActivityNet X-CLIP video-to-text Mean Rank 6.4 #21 of 31 Archive leaderboard report
Video Retrieval ActivityNet X-CLIP video-to-text R@1 46.4 #21 of 31 Archive leaderboard report
Video Retrieval ActivityNet X-CLIP video-to-text R@5 75.9 #21 of 31 Archive leaderboard report
Video Retrieval DiDeMo X-CLIP text-to-video Mean Rank 12.6 #29 of 40 Archive leaderboard report
Video Retrieval DiDeMo X-CLIP text-to-video R@1 47.8 #29 of 40 Archive leaderboard report
Video Retrieval DiDeMo X-CLIP text-to-video R@5 79.3 #29 of 40 Archive leaderboard report
Video Retrieval DiDeMo X-CLIP video-to-text Mean Rank 10.5 #29 of 40 Archive leaderboard report
Video Retrieval DiDeMo X-CLIP video-to-text R@1 47.8 #29 of 40 Archive leaderboard report
Video Retrieval DiDeMo X-CLIP video-to-text R@10 76.8 #29 of 40 Archive leaderboard report
Video Retrieval LSMDC X-CLIP text-to-video R@1 26.1 #14 of 38 Archive leaderboard report
Video Retrieval LSMDC X-CLIP video-to-text R@1 26.9 #14 of 38 Archive leaderboard report
Video Retrieval MSR-VTT-1kA X-CLIP text-to-video Mean Rank 12.2 #20 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA X-CLIP text-to-video Median Rank 2.0 #20 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA X-CLIP text-to-video R@1 49.3 #20 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA X-CLIP text-to-video R@10 84.8 #20 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA X-CLIP text-to-video R@5 75.8 #20 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA X-CLIP video-to-text Mean Rank 8.1 #20 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA X-CLIP video-to-text Median Rank 2.0 #20 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA X-CLIP video-to-text R@1 48.9 #20 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA X-CLIP video-to-text R@10 84.5 #20 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA X-CLIP video-to-text R@5 76.8 #20 of 63 Archive leaderboard report
Video Retrieval MSVD X-CLIP text-to-video Mean Rank 8.4 #12 of 24 Archive leaderboard report
Video Retrieval MSVD X-CLIP text-to-video R@1 50.4 #12 of 24 Archive leaderboard report
Video Retrieval MSVD X-CLIP text-to-video R@5 80.6 #12 of 24 Archive leaderboard report
Video Retrieval MSVD X-CLIP video-to-text Mean Rank 4.2 #12 of 24 Archive leaderboard report
Video Retrieval MSVD X-CLIP video-to-text R@1 66.8 #12 of 24 Archive leaderboard report
Video Retrieval MSVD X-CLIP video-to-text R@10 90.4 #12 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