Papers › Boundary-Denoising for Video Activity Localization
Boundary-Denoising for Video Activity Localization
Mengmeng Xu, Mattia Soldan, Jialin Gao, Shuming Liu, Juan-Manuel Pérez-Rúa, Bernard Ghanem
Video activity localization aims at understanding the semantic content in long untrimmed videos and retrieving actions of interest. The retrieved action with its start and end locations can be used for highlight generation, temporal action detection, etc. Unfortunately, learning the exact boundary location of activities is highly challenging because temporal activities are continuous in time, and there are often no clear-cut transitions between actions. Moreover, the definition of the start and end of events is subjective, which may confuse the model. To alleviate the boundary ambiguity, we propose to study the video activity localization problem from a denoising perspective. Specifically, we propose an encoder-decoder model named DenoiseLoc. During training, a set of action spans is randomly generated from the ground truth with a controlled noise scale. Then we attempt to reverse this process by boundary denoising, allowing the localizer to predict activities with precise boundaries and resulting in faster convergence speed. Experiments show that DenoiseLoc advances %in several video activity understanding tasks. For example, we observe a gain of +12.36% average mAP on QV-Highlights dataset and +1.64% mAP@0.5 on THUMOS'14 dataset over the baseline. Moreover, DenoiseLoc achieves state-of-the-art performance on TACoS and MAD datasets, but with much fewer predictions compared to other current methods.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Moment Retrieval | QVHighlights | DenoiseLoc | R@1 IoU=0.5 | 59.27 | #32 of 32 | Archive leaderboard | report |
| Moment Retrieval | QVHighlights | DenoiseLoc | R@1 IoU=0.7 | 45.07 | #32 of 32 | Archive leaderboard | report |
| Video Grounding | MAD | DenoiseLoc | R@1,IoU=0.1 | 11.59 | #2 of 2 | Archive leaderboard | report |
| Video Grounding | MAD | DenoiseLoc | R@10,IoU=0.1 | 41.44 | #2 of 2 | Archive leaderboard | report |
| Video Grounding | MAD | DenoiseLoc | R@100,IoU=0.1 | 73.62 | #2 of 2 | Archive leaderboard | report |
| Video Grounding | MAD | DenoiseLoc | R@5,IoU=0.1 | 30.35 | #2 of 2 | Archive leaderboard | report |
| Video Grounding | MAD | DenoiseLoc | R@50,IoU=0.1 | 66.07 | #2 of 2 | 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