Papers › X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval

X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval

28 Mar 2022CVPR 2022 1arXiv:2203.15086archive 2025-07-28

Satya Krishna Gorti, Noel Vouitsis, Junwei Ma, Keyvan Golestan, Maksims Volkovs, Animesh Garg, Guangwei Yu

In text-video retrieval, the objective is to learn a cross-modal similarity function between a text and a video that ranks relevant text-video pairs higher than irrelevant pairs. However, videos inherently express a much wider gamut of information than texts. Instead, texts often capture sub-regions of entire videos and are most semantically similar to certain frames within videos. Therefore, for a given text, a retrieval model should focus on the text's most semantically similar video sub-regions to make a more relevant comparison. Yet, most existing works aggregate entire videos without directly considering text. Common text-agnostic aggregations schemes include mean-pooling or self-attention over the frames, but these are likely to encode misleading visual information not described in the given text. To address this, we propose a cross-modal attention model called X-Pool that reasons between a text and the frames of a video. Our core mechanism is a scaled dot product attention for a text to attend to its most semantically similar frames. We then generate an aggregated video representation conditioned on the text's attention weights over the frames. We evaluate our method on three benchmark datasets of MSR-VTT, MSVD and LSMDC, achieving new state-of-the-art results by up to 12% in relative improvement in Recall@1. Our findings thereby highlight the importance of joint text-video reasoning to extract important visual cues according to text. Full code and demo can be found at: https://layer6ai-labs.github.io/xpool/

PaperPDFConference PDFCodeCode 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="2203.15086")

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 with no contract checked.

By repository: official repository: 2 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

layer6ai-labs/xpool officialmentioned 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
1unverified

Licence: 2 of the 2 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 layer6ai-labs/xpool. “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.

BaselinePooling layer6ai-labs/xpool/modules/baseline_pooling.py official repository ran fingerprinted no licence file found · pointer only · f082c8f319e8ce4a · report
Config layer6ai-labs/xpool/modules/baseline_pooling.py official repository unverified no licence file found · pointer only · f0930dba90bc5cd5 · report

Tasks

RetrievalText to Video RetrievalVideo RetrievalVideo-Text Retrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Retrieval LSMDC X-Pool text-to-video Mean Rank 53.2 #17 of 38 Archive leaderboard report
Video Retrieval LSMDC X-Pool text-to-video Median Rank 8.0 #17 of 38 Archive leaderboard report
Video Retrieval LSMDC X-Pool text-to-video R@1 25.2 #17 of 38 Archive leaderboard report
Video Retrieval LSMDC X-Pool text-to-video R@10 53.5 #17 of 38 Archive leaderboard report
Video Retrieval LSMDC X-Pool text-to-video R@5 43.7 #17 of 38 Archive leaderboard report
Video Retrieval LSMDC X-Pool video-to-text Mean Rank 47.4 #17 of 38 Archive leaderboard report
Video Retrieval LSMDC X-Pool video-to-text Median Rank 10.0 #17 of 38 Archive leaderboard report
Video Retrieval LSMDC X-Pool video-to-text R@1 22.7 #17 of 38 Archive leaderboard report
Video Retrieval LSMDC X-Pool video-to-text R@10 51.2 #17 of 38 Archive leaderboard report
Video Retrieval LSMDC X-Pool video-to-text R@5 42.6 #17 of 38 Archive leaderboard report
Video Retrieval MSR-VTT-1kA X-Pool text-to-video Mean Rank 14.3 #30 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA X-Pool text-to-video Median Rank 2 #30 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA X-Pool text-to-video R@1 46.9 #30 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA X-Pool text-to-video R@10 82.2 #30 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA X-Pool text-to-video R@5 72.8 #30 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA X-Pool video-to-text Mean Rank 9.0 #30 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA X-Pool video-to-text Median Rank 2.0 #30 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA X-Pool video-to-text R@1 44.4 #30 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA X-Pool video-to-text R@10 84.0 #30 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA X-Pool video-to-text R@5 73.3 #30 of 63 Archive leaderboard report
Video Retrieval MSVD X-Pool text-to-video Mean Rank 9.3 #17 of 24 Archive leaderboard report
Video Retrieval MSVD X-Pool text-to-video Median Rank 2.0 #17 of 24 Archive leaderboard report
Video Retrieval MSVD X-Pool text-to-video R@1 47.2 #17 of 24 Archive leaderboard report
Video Retrieval MSVD X-Pool text-to-video R@10 86.0 #17 of 24 Archive leaderboard report
Video Retrieval MSVD X-Pool text-to-video R@5 77.4 #17 of 24 Archive leaderboard report
Video Retrieval MSVD X-Pool video-to-text Mean Rank 3.3 #17 of 24 Archive leaderboard report
Video Retrieval MSVD X-Pool video-to-text Median Rank 1.0 #17 of 24 Archive leaderboard report
Video Retrieval MSVD X-Pool video-to-text R@1 66.4 #17 of 24 Archive leaderboard report
Video Retrieval MSVD X-Pool video-to-text R@10 94.2 #17 of 24 Archive leaderboard report
Video Retrieval MSVD X-Pool video-to-text R@5 90.0 #17 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.

Methods

Softmax

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