Domain-Guided Masked Autoencoders for Unique Player Identification

arXiv:2403.11328v1 Announce Type: new
Abstract: Unique player identification is a fundamental module in vision-driven sports analytics. Identifying players from broadcast videos can aid with various downstream tasks such as player assessment, in-game analysis, and broadcast production. However, automatic detection of jersey numbers using deep features is challenging primarily due to: a) motion blur, b) low resolution video feed, and c) occlusions. With their recent success in various vision tasks, masked autoencoders (MAEs) have emerged as a superior alternative to conventional …

abstract analysis analytics arxiv assessment autoencoders broadcast cs.ai cs.cv detection domain features game however identification numbers production sports tasks type videos vision