Papers › Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding

Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding

15 Nov 2023arXiv:2311.08835archive 2025-07-28

WonJun Moon, Sangeek Hyun, SuBeen Lee, Jae-Pil Heo

Temporal Grounding is to identify specific moments or highlights from a video corresponding to textual descriptions. Typical approaches in temporal grounding treat all video clips equally during the encoding process regardless of their semantic relevance with the text query. Therefore, we propose Correlation-Guided DEtection TRansformer (CG-DETR), exploring to provide clues for query-associated video clips within the cross-modal attention. First, we design an adaptive cross-attention with dummy tokens. Dummy tokens conditioned by text query take portions of the attention weights, preventing irrelevant video clips from being represented by the text query. Yet, not all words equally inherit the text query's correlation to video clips. Thus, we further guide the cross-attention map by inferring the fine-grained correlation between video clips and words. We enable this by learning a joint embedding space for high-level concepts, i.e., moment and sentence level, and inferring the clip-word correlation. Lastly, we exploit the moment-specific characteristics and combine them with the context of each video to form a moment-adaptive saliency detector. By exploiting the degrees of text engagement in each video clip, it precisely measures the highlightness of each clip. CG-DETR achieves state-of-the-art results on various benchmarks for temporal grounding. Codes are available at https://github.com/wjun0830/CGDETR.

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="2311.08835")

Code

Syntology Ran 2 of 11 code samples harvested from 2 repositories linked to this paper; 9 have no recorded run. Of those that ran: 1 ran · violated contract; 1 ran · our draft was wrong.

By repository: official repository: 10 samples from 1 repository, 1 ran; community (archive-listed): 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/cgdetr officialmentioned in papermentioned on GitHubpytorchNOASSERTION report
wjun0830/qd-detr mentioned 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

11 samples harvested; 2 ran; 0 honoured the contract we drafted; 9 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 · violated contract
1ran · our draft was wrong
9unverified

Licence: 11 of the 11 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

span_cxw_to_xx wjun0830/cgdetr/cg_detr/span_utils.py official repository ran · violated contract fingerprinted no licence file found · pointer only · b7639c2e8b83837b · report
accuracy wjun0830/cgdetr/cg_detr/misc.py official repository unverified no licence file found · pointer only · 081c8abd57d082fd · report
build_position_encoding wjun0830/cgdetr/cg_detr/position_encoding.py official repository unverified no licence file found · pointer only · 1affbf903fa3204b · report
count_parameters wjun0830/cgdetr/utils/model_utils.py official repository unverified no licence file found · pointer only · edb929dece68582e · report
element_wise_list_equal wjun0830/cgdetr/cg_detr/model.py official repository unverified no licence file found · pointer only · 6d07870656ce939e · report
find_nth wjun0830/cgdetr/cg_detr/model.py official repository unverified no licence file found · pointer only · f2157348a4ae2f51 · report
multi_head_attention_forward wjun0830/cgdetr/cg_detr/attention.py official repository unverified no licence file found · pointer only · a82091666b9db8cf · report
multi_head_attention_forward wjun0830/cgdetr/cg_detr/crossattention.py official repository unverified no licence file found · pointer only · 5d7fc668e3b608cf · report
span_xx_to_cxw wjun0830/cgdetr/cg_detr/span_utils.py official repository unverified no licence file found · pointer only · 7114f025044af9b4 · report
temporal_iou wjun0830/cgdetr/cg_detr/span_utils.py official repository unverified no licence file found · pointer only · e4ae5582a2533cdb · report
inverse_sigmoid wjun0830/qd-detr/qd_detr/model.py community (archive-listed) ran · our draft was wrong fingerprinted licence not identified · pointer only · 6897880b6ce14c94 · report

Tasks

Highlight DetectionMoment RetrievalNatural Language Moment RetrievalRepresentation LearningSentence

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Highlight Detection QVHighlights CG-DETR (w/ PT) Hit@1 66.60 #7 of 21 Archive leaderboard report
Highlight Detection QVHighlights CG-DETR (w/ PT) mAP 40.71 #7 of 21 Archive leaderboard report
Highlight Detection QVHighlights CG-DETR Hit@1 66.21 #10 of 21 Archive leaderboard report
Highlight Detection QVHighlights CG-DETR mAP 40.33 #10 of 21 Archive leaderboard report
Highlight Detection TvSum CG-DETR mAP 86.8 #3 of 7 Archive leaderboard report
Highlight Detection YouTube Highlights CG-DETR mAP 75.9 #4 of 7 Archive leaderboard report
Moment Retrieval Charades-STA CG-DETR R@1 IoU=0.5 58.44 #15 of 25 Archive leaderboard report
Moment Retrieval Charades-STA CG-DETR R@1 IoU=0.7 36.34 #15 of 25 Archive leaderboard report
Moment Retrieval QVHighlights CG-DETR (w/ PT) R@1 IoU=0.5 68.48 #6 of 32 Archive leaderboard report
Moment Retrieval QVHighlights CG-DETR (w/ PT) R@1 IoU=0.7 53.11 #6 of 32 Archive leaderboard report
Moment Retrieval QVHighlights CG-DETR (w/ PT) mAP 47.97 #6 of 32 Archive leaderboard report
Moment Retrieval QVHighlights CG-DETR (w/ PT) mAP@0.5 69.40 #6 of 32 Archive leaderboard report
Moment Retrieval QVHighlights CG-DETR (w/ PT) mAP@0.75 49.12 #6 of 32 Archive leaderboard report
Moment Retrieval QVHighlights CG-DETR R@1 IoU=0.5 65.43 #19 of 32 Archive leaderboard report
Moment Retrieval QVHighlights CG-DETR R@1 IoU=0.7 48.38 #19 of 32 Archive leaderboard report
Moment Retrieval QVHighlights CG-DETR mAP 42.86 #19 of 32 Archive leaderboard report
Moment Retrieval QVHighlights CG-DETR mAP@0.5 64.51 #19 of 32 Archive leaderboard report
Moment Retrieval QVHighlights CG-DETR mAP@0.75 42.77 #19 of 32 Archive leaderboard report
Natural Language Moment Retrieval TACoS CG-DETR R@1,IoU=0.3 52.23 #8 of 13 Archive leaderboard report
Natural Language Moment Retrieval TACoS CG-DETR R@1,IoU=0.5 39.61 #8 of 13 Archive leaderboard report
Natural Language Moment Retrieval TACoS CG-DETR R@1,IoU=0.7 22.23 #8 of 13 Archive leaderboard report
Natural Language Moment Retrieval TACoS CG-DETR mIoU 36.48 #8 of 13 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