Boundary-Denoising for Video Activity Localization
Mengmeng Xu, Mattia Soldan, Jialin Gao, Shuming Liu, Juan-Manuel, P\'erez-R\'ua, Bernard Ghanem

TL;DR
This paper introduces DenoiseLoc, a novel encoder-decoder model that improves video activity localization by treating boundary detection as a denoising task, leading to more precise boundaries and faster training convergence.
Contribution
It proposes a boundary denoising approach with a new model, DenoiseLoc, that enhances localization accuracy and efficiency in video activity detection tasks.
Findings
+12.36% average mAP on QV-Highlights dataset
+1.64% [email protected] on THUMOS'14 dataset
State-of-the-art performance on TACoS and MAD datasets
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHuman Pose and Action Recognition · Anomaly Detection Techniques and Applications · Video Surveillance and Tracking Methods
