RefineLoc: Iterative Refinement for Weakly-Supervised Action Localization
KAUST DepartmentKing Abdullah University of Science and Technology (KAUST)
Computer Science Program
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Visual Computing Center (VCC)
Electrical Engineering Program
KAUST Grant NumberOSRCRG2017-3405
Permanent link to this recordhttp://hdl.handle.net/10754/660670
MetadataShow full item record
AbstractVideo 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 weaklysupervised 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 stateof-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.
CitationPardo, A., Alwassel, H., Heilbron, F. C., Thabet, A., & Ghanem, B. (2021). RefineLoc: Iterative Refinement for Weakly-Supervised Action Localization. 2021 IEEE Winter Conference on Applications of Computer Vision (WACV). doi:10.1109/wacv48630.2021.00336
SponsorsThis work is supported the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR) under Award No. OSRCRG2017-3405.
Conference/Event name2021 IEEE Winter Conference on Applications of Computer Vision (WACV)
RelationsIs Supplemented By: