Identifying players in broadcast videos using graph convolutional network. (April 2022)

• Record Type: Journal Article
• Authors: Feng, Tao; Ji, Kaifan; Bian, Ang; Liu, Chang; Zhang, Jianzhou
• Is Part Of: Pattern recognition. Volume 124(2022)
• Publication Date: 2022-04
• Subjects: Graph representation learning -- Graph embedding -- Pre-trained model -- Player identification; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2021.108503
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: A novel person representation method using graph convolutional network at the level of relational induction bias is presented. We innovatively embed implicit pose structure information into the deep features to form high-level features. To the best of our knowledge, the proposed method is the first work utilizing graph convolutional network for player identification. Extensive experiments on real-world game scenarios show that the proposed method captures a better person representation and achieves state-of-the-art performance. Abstract: The person representation problem is a critical bottleneck in the player identification task. However, the current approaches for player identification utilizing the entire image features only are not sufficient to preserve identities due to the reliance on visible visual representations. In this paper, we propose a novel player representation method using a graph-powered pose representation to resolve this bottleneck problem. Our framework consists of three modules: (i.) a novel pose-guided representation module that is able to capture the pose changes dynamically and their associated effects; (ii.) a pose-guided graph embedding module using both the image deep features and the pose structure information for a better player representation inference; (iii.) an identification module as a player classifier. Experiment results on the real-world sport game scenarios demonstrate that our method achieves state-of-the-art identification performance, together with a better player representation.