</> Code with Papers by Syntology

Papers › Multi-shot Temporal Event Localization: a Benchmark

Multi-shot Temporal Event Localization: a Benchmark

17 Dec 2020CVPR 2021 1arXiv:2012.09434archive 2025-07-28

Xiaolong Liu, Yao Hu, Song Bai, Fei Ding, Xiang Bai, Philip H. S. Torr

Current developments in temporal event or action localization usually target actions captured by a single camera. However, extensive events or actions in the wild may be captured as a sequence of shots by multiple cameras at different positions. In this paper, we propose a new and challenging task called multi-shot temporal event localization, and accordingly, collect a large scale dataset called MUlti-Shot EventS (MUSES). MUSES has 31,477 event instances for a total of 716 video hours. The core nature of MUSES is the frequent shot cuts, for an average of 19 shots per instance and 176 shots per video, which induces large intrainstance variations. Our comprehensive evaluations show that the state-of-the-art method in temporal action localization only achieves an mAP of 13.1% at IoU=0.5. As a minor contribution, we present a simple baseline approach for handling the intra-instance variations, which reports an mAP of 18.9% on MUSES and 56.9% on THUMOS14 at IoU=0.5. To facilitate research in this direction, we release the dataset and the project code at https://songbai.site/muses/ .

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

xlliu7/muses officialmentioned 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

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

Tasks

Action LocalizationTemporal Action Localization

Datasets

Introduced by this paper, per the archive.

MUSES

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Temporal Action Localization MUSES MUSES mAP 18.6 #2 of 2 Archive leaderboard report
Temporal Action Localization MUSES MUSES mAP@0.3 25.9 #2 of 2 Archive leaderboard report
Temporal Action Localization MUSES MUSES mAP@0.4 22.6 #2 of 2 Archive leaderboard report
Temporal Action Localization MUSES MUSES mAP@0.5 18.9 #2 of 2 Archive leaderboard report
Temporal Action Localization MUSES MUSES mAP@0.6 15.0 #2 of 2 Archive leaderboard report
Temporal Action Localization MUSES MUSES mAP@0.7 10.6 #2 of 2 Archive leaderboard report
Temporal Action Localization THUMOS’14 MUSES Avg mAP (0.3:0.7) 53.4 #21 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 MUSES mAP IOU@0.3 68.9 #21 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 MUSES mAP IOU@0.4 64.0 #21 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 MUSES mAP IOU@0.5 56.9 #21 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 MUSES mAP IOU@0.6 46.3 #21 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 MUSES mAP IOU@0.7 31.0 #21 of 42 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