A Context-Aware Loss Function for Action Spotting in Soccer Videos
Name:
CVPR2020___Improvement_on_SoccerNet (10).pdf
Size:
5.164Mb
Format:
PDF
Description:
Accepted Manuscript
Type
Conference PaperAuthors
Cioppa, AnthonyDeliège, Adrien
Giancola, Silvio
Ghanem, Bernard

Droogenbroeck, Marc Van
Gade, Rikke
Moeslund, Thomas B.
KAUST Department
Visual Computing Center (VCC)Electrical Engineering Program
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
KAUST Grant Number
OSR-CRG2017-3405Date
2020Permanent link to this record
http://hdl.handle.net/10754/660728
Metadata
Show full item recordAbstract
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.Citation
Cioppa, 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/cvpr42600.2020.01314Sponsors
This 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 name
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)ISBN
978-1-7281-7169-2arXiv
1912.01326Additional Links
https://ieeexplore.ieee.org/document/9156359/https://ieeexplore.ieee.org/document/9156359/
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9156359
https://openaccess.thecvf.com/content_CVPR_2020/html/Cioppa_A_Context-Aware_Loss_Function_for_Action_Spotting_in_Soccer_Videos_CVPR_2020_paper.html
https://openaccess.thecvf.com/content_CVPR_2020/papers/Cioppa_A_Context-Aware_Loss_Function_for_Action_Spotting_in_Soccer_Videos_CVPR_2020_paper.pdf
ae974a485f413a2113503eed53cd6c53
10.1109/CVPR42600.2020.01314