-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Koshkina_2021_CVPR, author = {Koshkina, Maria and Pidaparthy, Hemanth and Elder, James H.}, title = {Contrastive Learning for Sports Video: Unsupervised Player Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {4528-4536} }
Contrastive Learning for Sports Video: Unsupervised Player Classification
Abstract
We address the problem of unsupervised classification of players in a team sport according to their team affiliation, when jersey colours and design are not known a priori. We adopt a contrastive learning approach in which an embedding network learns to maximize the distance between representations of players on different teams relative to players on the same team, in a purely unsupervised fashion, without any labelled data. We evaluate the approach using a new hockey dataset and find that it outperforms prior unsupervised approaches by a substantial margin, particularly for real-time application when only a small number of frames are available for unsupervised learning before team assignments must be made. Remarkably, we show that our contrastive method achieves 94% accuracy after unsupervised training on only a single frame, with accuracy rising to 97% within 500 frames (17 seconds of game time). We further demonstrate how accurate team classification allows accurate team-conditional heat maps of player positioning to be computed.
Related Material