RefineLoc: Iterative Refinement for Weakly-Supervised Action Localization
RefineLoc is a weakly-supervised action detector that aims to approximate the true foreground-background labels through iteratively generating pseudo ground truth. Our key idea is to use the pseudo ground truth from iteration n-1 to supervise the detection model at iteration n
Abstract
Video action detectors are usually trained using datasets with fully-supervised temporal annotations. Building such datasets is an expensive task. To alleviate this problem, recent methods have tried to leverage weak labeling, where videos are untrimmed and only a video-level label is available. In this paper, we propose RefineLoc, a novel weakly-supervised temporal action localization method. RefineLoc uses an iterative refinement approach by estimating and training on snippet-level pseudo ground truth at every iteration. We show the benefit of this iterative approach and present an extensive analysis of five different pseudo ground truth generators. We show the effectiveness of our model on two standard action datasets, ActivityNet v1.2 and THUMOS14. RefineLoc shows competitive results with the state-of-the-art in weakly-supervised temporal localization. Additionally, our iterative refinement process is able to significantly improve the performance of two state-of-the-art methods, setting a new state-of-the-art on THUMOS14.
BibTex
@InProceedings{pardo_2021_refineloc,
title={RefineLoc: Iterative Refinement for Weakly-Supervised Action Localization},
author={Pardo, Alejandro and Alwassel, Humam and Heilbron, Fabian Caba and
Thabet, Ali and Ghanem, Bernard},
booktitle={Proceedings of the IEEE/CVF Winter Conference on Applications of
Computer Vision (WACV)},
year={2021}
}