Papers › UniVTG: Towards Unified Video-Language Temporal Grounding

UniVTG: Towards Unified Video-Language Temporal Grounding

31 Jul 2023ICCV 2023 1arXiv:2307.16715archive 2025-07-28

Kevin Qinghong Lin, Pengchuan Zhang, Joya Chen, Shraman Pramanick, Difei Gao, Alex Jinpeng Wang, Rui Yan, Mike Zheng Shou

Video Temporal Grounding (VTG), which aims to ground target clips from videos (such as consecutive intervals or disjoint shots) according to custom language queries (e.g., sentences or words), is key for video browsing on social media. Most methods in this direction develop taskspecific models that are trained with type-specific labels, such as moment retrieval (time interval) and highlight detection (worthiness curve), which limits their abilities to generalize to various VTG tasks and labels. In this paper, we propose to Unify the diverse VTG labels and tasks, dubbed UniVTG, along three directions: Firstly, we revisit a wide range of VTG labels and tasks and define a unified formulation. Based on this, we develop data annotation schemes to create scalable pseudo supervision. Secondly, we develop an effective and flexible grounding model capable of addressing each task and making full use of each label. Lastly, thanks to the unified framework, we are able to unlock temporal grounding pretraining from large-scale diverse labels and develop stronger grounding abilities e.g., zero-shot grounding. Extensive experiments on three tasks (moment retrieval, highlight detection and video summarization) across seven datasets (QVHighlights, Charades-STA, TACoS, Ego4D, YouTube Highlights, TVSum, and QFVS) demonstrate the effectiveness and flexibility of our proposed framework. The codes are available at https://github.com/showlab/UniVTG.

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="2307.16715")

Code

Syntology Ran 10 of 16 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · our draft was wrong; 1 ran · fixture could not drive it; 7 ran with no contract checked.

By repository: official repository: 16 samples from 1 repository, 10 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

showlab/univtg officialmentioned in papermentioned on GitHubpytorchMIT 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

16 samples harvested; 10 ran; 1 honoured the contract we drafted; 6 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 · honoured contract
1ran · our draft was wrong
1ran · fixture could not drive it
7ran
6unverified

Licence: 0 of the 16 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 showlab/UniVTG. “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.

Conv showlab/UniVTG/model/univtg.py official repository ran MIT (permissive) · fe525fce2ed45fdc · report
Model showlab/UniVTG/model/univtg.py official repository ran MIT (permissive) · 71a63e8e4005103c · report
PositionalEncoding showlab/univtg/model/position_encoding.py official repository ran fingerprinted MIT (permissive) · 94aab69ebd3439ec · report
build_position_encoding showlab/univtg/model/position_encoding.py official repository ran MIT (permissive) · 2912d21d62514265 · report
convert_to_hms showlab/univtg/main_gradio.py official repository ran fingerprinted MIT (permissive) · 0dc91e6607bb2ec1 · report
drop_path showlab/univtg/model/transformer_encoder_droppath.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 10e67144852e5fce · report
mask_logits showlab/univtg/model/univtg.py official repository ran · honoured contract fingerprinted MIT (permissive) · 60df4d5a1eee1b92 · report
process_mat showlab/univtg/eval/qfvs.py official repository ran MIT (permissive) · 4d2286148f711e02 · report
process_video_mat showlab/univtg/eval/qfvs.py official repository ran MIT (permissive) · b3a40dcb09d6a4a9 · report
sim_matrix showlab/univtg/model/univtg.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 185c7b880ca6135e · report
accuracy showlab/univtg/model/moment_detr.py official repository unverified MIT (permissive) · 081c8abd57d082fd · report
build_transformer showlab/univtg/model/transformer.py official repository unverified MIT (permissive) · a03d2e1a023a5c63 · report
build_transformer showlab/univtg/model/transformer_encoder_droppath.py official repository unverified MIT (permissive) · 141ae5fb5b4041f0 · report
count_parameters showlab/univtg/utils/model_utils.py official repository unverified MIT (permissive) · edb929dece68582e · report
init_weights showlab/UniVTG/model/univtg.py official repository unverified MIT (permissive) · 6846bf0b5c7629d7 · report
load_videos_tag showlab/univtg/eval/qfvs.py official repository unverified MIT (permissive) · 0581196da1c218b5 · report

Tasks

Highlight DetectionMoment RetrievalNatural Language Moment RetrievalRetrievalVideo Summarization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Highlight Detection QVHighlights UniVTG (w/ PT) Hit@1 66.28 #9 of 21 Archive leaderboard report
Highlight Detection QVHighlights UniVTG (w/ PT) mAP 40.54 #9 of 21 Archive leaderboard report
Highlight Detection QVHighlights UniVTG Hit@1 60.96 #16 of 21 Archive leaderboard report
Highlight Detection QVHighlights UniVTG mAP 38.20 #16 of 21 Archive leaderboard report
Moment Retrieval QVHighlights UniVTG (w/ PT) R@1 IoU=0.5 65.43 #17 of 32 Archive leaderboard report
Moment Retrieval QVHighlights UniVTG (w/ PT) R@1 IoU=0.7 50.06 #17 of 32 Archive leaderboard report
Moment Retrieval QVHighlights UniVTG (w/ PT) mAP 43.63 #17 of 32 Archive leaderboard report
Moment Retrieval QVHighlights UniVTG (w/ PT) mAP@0.5 64.06 #17 of 32 Archive leaderboard report
Moment Retrieval QVHighlights UniVTG (w/ PT) mAP@0.75 45.02 #17 of 32 Archive leaderboard report
Moment Retrieval QVHighlights UniVTG R@1 IoU=0.5 58.86 #28 of 32 Archive leaderboard report
Moment Retrieval QVHighlights UniVTG R@1 IoU=0.7 40.86 #28 of 32 Archive leaderboard report
Moment Retrieval QVHighlights UniVTG mAP 35.47 #28 of 32 Archive leaderboard report
Moment Retrieval QVHighlights UniVTG mAP@0.5 57.60 #28 of 32 Archive leaderboard report
Moment Retrieval QVHighlights UniVTG mAP@0.75 35.59 #28 of 32 Archive leaderboard report
Natural Language Moment Retrieval TACoS UniVTG R@1,IoU=0.3 51.44 #9 of 13 Archive leaderboard report
Natural Language Moment Retrieval TACoS UniVTG R@1,IoU=0.5 34.97 #9 of 13 Archive leaderboard report
Natural Language Moment Retrieval TACoS UniVTG R@1,IoU=0.7 21.07 #9 of 13 Archive leaderboard report
Natural Language Moment Retrieval TACoS UniVTG mIoU 35.76 #9 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