IEEE Conference on Computer Vision and Pattern Recognition
from 14-06-2020 to 19-06-2020
IEEE
Seattle
WA
[en] action spotting ; artificial intelligence ; soccer videos ; deep learning ; context-aware loss ; highlights generation
[en] In 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.
Montefiore Institute of Electrical Engineering and Computer Science - Montefiore Institute ; Telim
DGTRE - Région wallonne. Direction générale des Technologies, de la Recherche et de l'Energie ; FRIA - Fonds pour la Formation à la Recherche dans l'Industrie et dans l'Agriculture ; KAUST Office of Sponsored Research
[Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Télécommunications >]
