Comprehensive basketball video understanding requires resolving not only what event occurs but also who is responsible and when the key evidence appears. However, existing methods typically treat spatial perception and semantic recognition as isolated tasks, failing to ground events to individual players or pinpoint their temporal boundaries within complex collective dynamics.
To bridge this gap, we introduce BasketEvent, a player-centric basketball event understanding dataset curated from real NBA broadcasts. In BasketEvent, event labels are grounded to the responsible players, and a manually annotated subset of 1,000 samples with precise event intervals is provided to evaluate temporal evidence localization.
Based on this data, we propose PlayNet, a player-centric reasoning framework that maps basketball videos to player-level event predictions with temporal evidence. Concretely, PlayNet tracks key entities, associates player identities, and reasons about events by modeling player-player, player-ball, and global court interactions, while aggregating sparse temporal evidence via gated pooling.
Extensive experiments demonstrate that PlayNet significantly outperforms representative video-level and crop-based baselines, proving the superiority of player-centric modeling for fine-grained sports video understanding. Our data, code, and models will be made publicly available.
Blogger's Review: The BasketEvent dataset and PlayNet framework presented in this paper offer a fresh perspective on basketball video analysis, emphasizing the importance of players in event understanding. This approach not only enhances the accuracy of event recognition but also lays the groundwork for future sports video analysis. By focusing on individual player behaviors and interactions, researchers can gain deeper insights into the dynamics of the game.