Papers › UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection

UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection

23 Mar 2022CVPR 2022 1arXiv:2203.12745archive 2025-07-28

Ye Liu, Siyuan Li, Yang Wu, Chang Wen Chen, Ying Shan, XiaoHu Qie

Finding relevant moments and highlights in videos according to natural language queries is a natural and highly valuable common need in the current video content explosion era. Nevertheless, jointly conducting moment retrieval and highlight detection is an emerging research topic, even though its component problems and some related tasks have already been studied for a while. In this paper, we present the first unified framework, named Unified Multi-modal Transformers (UMT), capable of realizing such joint optimization while can also be easily degenerated for solving individual problems. As far as we are aware, this is the first scheme to integrate multi-modal (visual-audio) learning for either joint optimization or the individual moment retrieval task, and tackles moment retrieval as a keypoint detection problem using a novel query generator and query decoder. Extensive comparisons with existing methods and ablation studies on QVHighlights, Charades-STA, YouTube Highlights, and TVSum datasets demonstrate the effectiveness, superiority, and flexibility of the proposed method under various settings. Source code and pre-trained models are available at https://github.com/TencentARC/UMT.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page 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

tencentarc/umt officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
MS-P3/code7 mindsporeApache-2.0Syntology: not harvested report
MindCode-4/code-5 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ViTamin: Designing Scalable Vision Models in the Vision-Language Era (arXiv:2404.02132; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified); 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

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

Tasks

DecoderHighlight DetectionMoment RetrievalNatural Language QueriesRetrievalVideo Grounding

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Highlight Detection QVHighlights UMT (w. PT) mAP 39.12 #12 of 21 Archive leaderboard report
Highlight Detection QVHighlights UMT mAP 38.18 #17 of 21 Archive leaderboard report
Highlight Detection TvSum UMT mAP 83.1 #7 of 7 Archive leaderboard report
Highlight Detection YouTube Highlights UMT mAP 74.9 #7 of 7 Archive leaderboard report
Moment Retrieval Charades-STA UMT (VO) R@1 IoU=0.5 49.35 #22 of 25 Archive leaderboard report
Moment Retrieval Charades-STA UMT (VO) R@1 IoU=0.7 26.16 #22 of 25 Archive leaderboard report
Moment Retrieval Charades-STA UMT (VO) R@5 IoU=0.5 89.41 #22 of 25 Archive leaderboard report
Moment Retrieval Charades-STA UMT (VO) R@5 IoU=0.7 54.95 #22 of 25 Archive leaderboard report
Moment Retrieval Charades-STA UMT (VA) R@1 IoU=0.5 48.31 #24 of 25 Archive leaderboard report
Moment Retrieval Charades-STA UMT (VA) R@1 IoU=0.7 29.25 #24 of 25 Archive leaderboard report
Moment Retrieval Charades-STA UMT (VA) R@5 IoU=0.5 88.79 #24 of 25 Archive leaderboard report
Moment Retrieval Charades-STA UMT (VA) R@5 IoU=0.7 56.08 #24 of 25 Archive leaderboard report
Moment Retrieval QVHighlights UMT (w/ audio + PT ASR Cpations) mAP 38.08 #25 of 32 Archive leaderboard report
Moment Retrieval QVHighlights UMT mAP 36.12 #27 of 32 Archive leaderboard report
Video Grounding QVHighlights UMT R@1,IoU=0.5 56.23 #6 of 7 Archive leaderboard report
Video Grounding QVHighlights UMT R@1,IoU=0.7 41.18 #6 of 7 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