Papers › Query-Dependent Video Representation for Moment Retrieval and Highlight Detection

Query-Dependent Video Representation for Moment Retrieval and Highlight Detection

24 Mar 2023CVPR 2023 1arXiv:2303.13874archive 2025-07-28

WonJun Moon, Sangeek Hyun, Sanguk Park, Dongchan Park, Jae-Pil Heo

Recently, video moment retrieval and highlight detection (MR/HD) are being spotlighted as the demand for video understanding is drastically increased. The key objective of MR/HD is to localize the moment and estimate clip-wise accordance level, i.e., saliency score, to the given text query. Although the recent transformer-based models brought some advances, we found that these methods do not fully exploit the information of a given query. For example, the relevance between text query and video contents is sometimes neglected when predicting the moment and its saliency. To tackle this issue, we introduce Query-Dependent DETR (QD-DETR), a detection transformer tailored for MR/HD. As we observe the insignificant role of a given query in transformer architectures, our encoding module starts with cross-attention layers to explicitly inject the context of text query into video representation. Then, to enhance the model's capability of exploiting the query information, we manipulate the video-query pairs to produce irrelevant pairs. Such negative (irrelevant) video-query pairs are trained to yield low saliency scores, which in turn, encourages the model to estimate precise accordance between query-video pairs. Lastly, we present an input-adaptive saliency predictor which adaptively defines the criterion of saliency scores for the given video-query pairs. Our extensive studies verify the importance of building the query-dependent representation for MR/HD. Specifically, QD-DETR outperforms state-of-the-art methods on QVHighlights, TVSum, and Charades-STA datasets. Codes are available at github.com/wjun0830/QD-DETR.

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="2303.13874")

Code

Syntology Ran 1 of 1 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 1 ran with no contract checked.

By repository: official repository: 1 sample 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.

wjun0830/qd-detr 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

1 sample harvested; 1 ran; 0 honoured the contract we drafted; 0 have 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

Licence: 1 of the 1 sample 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 wjun0830/QD-DETR. “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.

QDDETR wjun0830/QD-DETR/qd_detr/model.py official repository ran licence not identified · pointer only · 32a0a976c1ecbbd0 · report

Tasks

Highlight DetectionMoment RetrievalNatural Language QueriesRetrievalVideo GroundingVideo Understanding

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Highlight Detection QVHighlights QD-DETR Hit@1 62.87 #13 of 21 Archive leaderboard report
Highlight Detection QVHighlights QD-DETR mAP 39.04 #13 of 21 Archive leaderboard report
Highlight Detection QVHighlights QD-DETR (only Video) Hit@1 62.40 #14 of 21 Archive leaderboard report
Highlight Detection QVHighlights QD-DETR (only Video) mAP 38.94 #14 of 21 Archive leaderboard report
Highlight Detection QVHighlights QD-DETR (w/ PT) Hit@1 62.27 #15 of 21 Archive leaderboard report
Highlight Detection QVHighlights QD-DETR (w/ PT) mAP 38.52 #15 of 21 Archive leaderboard report
Highlight Detection QVHighlights QD-DETR (only Video w/ PT) Hit@1 61.91 #21 of 21 Archive leaderboard report
Highlight Detection TvSum QD-DETR mAP 86.6 #4 of 7 Archive leaderboard report
Highlight Detection TvSum QD-DETR (only Video) mAP 85.0 #6 of 7 Archive leaderboard report
Moment Retrieval Charades-STA QD-DETR (Only Video) R@1 IoU=0.5 57.31 #18 of 25 Archive leaderboard report
Moment Retrieval Charades-STA QD-DETR (Only Video) R@1 IoU=0.7 32.55 #18 of 25 Archive leaderboard report
Moment Retrieval QVHighlights QD-DETR (w/ PT) R@1 IoU=0.5 64.1 #20 of 32 Archive leaderboard report
Moment Retrieval QVHighlights QD-DETR (w/ PT) R@1 IoU=0.7 46.1 #20 of 32 Archive leaderboard report
Moment Retrieval QVHighlights QD-DETR (w/ PT) mAP 40.62 #20 of 32 Archive leaderboard report
Moment Retrieval QVHighlights QD-DETR (w/ PT) mAP@0.5 64.3 #20 of 32 Archive leaderboard report
Moment Retrieval QVHighlights QD-DETR (w/ PT) mAP@0.75 40.5 #20 of 32 Archive leaderboard report
Moment Retrieval QVHighlights QD-DETR (w/ audio) R@1 IoU=0.5 63.06 #21 of 32 Archive leaderboard report
Moment Retrieval QVHighlights QD-DETR (w/ audio) R@1 IoU=0.7 45.10 #21 of 32 Archive leaderboard report
Moment Retrieval QVHighlights QD-DETR (w/ audio) mAP 40.19 #21 of 32 Archive leaderboard report
Moment Retrieval QVHighlights QD-DETR (w/ audio) mAP@0.5 63.04 #21 of 32 Archive leaderboard report
Moment Retrieval QVHighlights QD-DETR (w/ audio) mAP@0.75 40.10 #21 of 32 Archive leaderboard report
Moment Retrieval QVHighlights QD-DETR (only Video w/ PT ASR Captions) R@1 IoU=0.5 63.2 #23 of 32 Archive leaderboard report
Moment Retrieval QVHighlights QD-DETR (only Video w/ PT ASR Captions) R@1 IoU=0.7 45.2 #23 of 32 Archive leaderboard report
Moment Retrieval QVHighlights QD-DETR (only Video w/ PT ASR Captions) mAP 40.0 #23 of 32 Archive leaderboard report
Moment Retrieval QVHighlights QD-DETR (only Video w/ PT ASR Captions) mAP@0.5 63.4 #23 of 32 Archive leaderboard report
Moment Retrieval QVHighlights QD-DETR (only Video w/ PT ASR Captions) mAP@0.75 40.4 #23 of 32 Archive leaderboard report
Moment Retrieval QVHighlights QD-DETR (only Video) R@1 IoU=0.5 62.40 #24 of 32 Archive leaderboard report
Moment Retrieval QVHighlights QD-DETR (only Video) R@1 IoU=0.7 44.98 #24 of 32 Archive leaderboard report
Moment Retrieval QVHighlights QD-DETR (only Video) mAP 39.86 #24 of 32 Archive leaderboard report
Moment Retrieval QVHighlights QD-DETR (only Video) mAP@0.5 62.52 #24 of 32 Archive leaderboard report
Moment Retrieval QVHighlights QD-DETR (only Video) mAP@0.75 39.88 #24 of 32 Archive leaderboard report
Video Grounding QVHighlights QD-DETR R@1,IoU=0.5 62.40 #4 of 7 Archive leaderboard report
Video Grounding QVHighlights QD-DETR R@1,IoU=0.7 44.98 #4 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.

Methods

Absolute Position EncodingsAdamAttentionBPEConvolutionDense ConnectionsDetrDropoutFeedforward NetworkLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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