A Context-Aware Loss Function for Action Spotting in Soccer Videos
Droogenbroeck, Marc Van
Moeslund, Thomas B.
KAUST DepartmentVisual Computing Center (VCC)
Electrical Engineering Program
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
KAUST Grant NumberOSR-CRG2017-3405
Permanent link to this recordhttp://hdl.handle.net/10754/660728
MetadataShow full item record
AbstractIn video understanding, action spotting consists in temporally localizing human-induced events annotated with single timestamps. In this paper, we propose a novel loss function that specifically considers the temporal context naturally present around each action, rather than focusing on the single annotated frame to spot. We benchmark our loss on a large dataset of soccer videos, SoccerNet, and achieve an improvement of 12.8% over the baseline. We show the generalization capability of our loss for generic activity proposals and detection on ActivityNet, by spotting the beginning and the end of each activity. Furthermore, we provide an extended ablation study and display challenging cases for action spotting in soccer videos. Finally, we qualitatively illustrate how our loss induces a precise temporal understanding of actions and show how such semantic knowledge can be used for automatic highlights generation.
CitationCioppa, A., Deliege, A., Giancola, S., Ghanem, B., Van Droogenbroeck, M., Gade, R., & Moeslund, T. B. (2020). A Context-Aware Loss Function for Action Spotting in Soccer Videos. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). doi:10.1109/cvpr42600.2020.01314
SponsorsThis work is supported by the DeepSport project of the Walloon region and the FRIA (Belgium), as well as the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR) under Award No. OSR-CRG2017-3405.
Conference/Event name2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)