Papers › UnLoc: A Unified Framework for Video Localization Tasks

UnLoc: A Unified Framework for Video Localization Tasks

21 Aug 2023ICCV 2023 1arXiv:2308.11062archive 2025-07-28

Shen Yan, Xuehan Xiong, Arsha Nagrani, Anurag Arnab, Zhonghao Wang, Weina Ge, David Ross, Cordelia Schmid

While large-scale image-text pretrained models such as CLIP have been used for multiple video-level tasks on trimmed videos, their use for temporal localization in untrimmed videos is still a relatively unexplored task. We design a new approach for this called UnLoc, which uses pretrained image and text towers, and feeds tokens to a video-text fusion model. The output of the fusion module are then used to construct a feature pyramid in which each level connects to a head to predict a per-frame relevancy score and start/end time displacements. Unlike previous works, our architecture enables Moment Retrieval, Temporal Localization, and Action Segmentation with a single stage model, without the need for action proposals, motion based pretrained features or representation masking. Unlike specialized models, we achieve state of the art results on all three different localization tasks with a unified approach. Code will be available at: https://github.com/google-research/scenic.

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

google-research/scenic officialmentioned in papermentioned on GitHubjaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to TokenLearner: What Can 8 Learned Tokens Do for Images and Videos? (arXiv:2106.11297; that paper's own run record: 3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified), Learning with Neighbor Consistency for Noisy Labels (arXiv:2202.02200; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified), Location-Aware Self-Supervised Transformers for Semantic Segmentation (arXiv:2212.02400; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified) and 3 more (every one in this page's JSON twin); 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

Action SegmentationMoment RetrievalNatural Language Moment RetrievalRetrievalTemporal Action LocalizationTemporal LocalizationZero-Shot Action Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Segmentation COIN UnLoc-L Frame accuracy 72.8 #1 of 9 Archive leaderboard report
Moment Retrieval Charades-STA UnLoc-L R@1 IoU=0.5 60.8 #11 of 25 Archive leaderboard report
Moment Retrieval Charades-STA UnLoc-L R@1 IoU=0.7 38.4 #11 of 25 Archive leaderboard report
Moment Retrieval Charades-STA UnLoc-L R@5 IoU=0.5 88.2 #11 of 25 Archive leaderboard report
Moment Retrieval Charades-STA UnLoc-L R@5 IoU=0.7 61.1 #11 of 25 Archive leaderboard report
Moment Retrieval Charades-STA UnLoc-B R@1 IoU=0.5 58.1 #17 of 25 Archive leaderboard report
Moment Retrieval Charades-STA UnLoc-B R@1 IoU=0.7 35.4 #17 of 25 Archive leaderboard report
Moment Retrieval Charades-STA UnLoc-B R@5 IoU=0.5 87.4 #17 of 25 Archive leaderboard report
Moment Retrieval Charades-STA UnLoc-B R@5 IoU=0.7 59.1 #17 of 25 Archive leaderboard report
Moment Retrieval QVHighlights UnLoc-L R@1 IoU=0.5 66.1 #30 of 32 Archive leaderboard report
Moment Retrieval QVHighlights UnLoc-L R@1 IoU=0.7 46.7 #30 of 32 Archive leaderboard report
Moment Retrieval QVHighlights UnLoc-B R@1 IoU=0.5 64.5 #31 of 32 Archive leaderboard report
Moment Retrieval QVHighlights UnLoc-B R@1 IoU=0.7 48.8 #31 of 32 Archive leaderboard report
Natural Language Moment Retrieval ActivityNet Captions UnLoc-L R@1,IoU=0.5 48.3 #4 of 8 Archive leaderboard report
Natural Language Moment Retrieval ActivityNet Captions UnLoc-L R@1,IoU=0.7 30.2 #4 of 8 Archive leaderboard report
Natural Language Moment Retrieval ActivityNet Captions UnLoc-L R@5,IoU=0.5 79.2 #4 of 8 Archive leaderboard report
Natural Language Moment Retrieval ActivityNet Captions UnLoc-L R@5,IoU=0.7 61.3 #4 of 8 Archive leaderboard report
Natural Language Moment Retrieval ActivityNet Captions UnLoc-B R@1,IoU=0.5 48.0 #5 of 8 Archive leaderboard report
Natural Language Moment Retrieval ActivityNet Captions UnLoc-B R@1,IoU=0.7 29.7 #5 of 8 Archive leaderboard report
Natural Language Moment Retrieval ActivityNet Captions UnLoc-B R@5,IoU=0.5 81.5 #5 of 8 Archive leaderboard report
Natural Language Moment Retrieval ActivityNet Captions UnLoc-B R@5,IoU=0.7 61.4 #5 of 8 Archive leaderboard report
Temporal Action Localization ActivityNet-1.3 UnLoc-L mAP IOU@0.5 59.3 #33 of 33 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

CLIP

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