Attention-Pool: 9-Ball Game Video Analytics with Object Attention and Temporal Context Gated Attention

Abstract

The automated analysis of pool game videos presents significant challenges due to complex object interactions, precise rule requirements, and event-driven game dynamics that traditional computer vision approaches struggle to address effectively. This research introduces TCGA-Pool, a novel video analytics framework specifically designed for comprehensive 9-ball pool game understanding through advanced object attention mechanisms and temporal context modeling. Our approach addresses the critical gap in automated cue sports analysis by focusing on three essential classification tasks: Clear shot detection (successful ball potting without fouls), win condition identification (game-ending scenarios), and potted balls counting (accurate enumeration of successfully pocketed balls). The proposed framework leverages a Temporal Context Gated Attention (TCGA) mechanism that dynamically focuses on salient game elements while incorporating sequential dependencies inherent in pool game sequences. Through comprehensive evaluation on a dataset comprising 58,078 annotated video frames from diverse 9-ball pool scenarios, our TCGA-Pool framework demonstrates substantial improvements over existing video analysis methods, achieving accuracy gains of 4.7%, 3.2%, and 6.2% for clear shot detection, win condition identification, and potted ball counting tasks, respectively. The framework maintains computational efficiency with only 27.3 M parameters and 13.9 G FLOPs, making it suitable for real-time applications. Our contributions include the introduction of domain-specific object attention mechanisms, the development of adaptive temporal modeling strategies for cue sports, and the implementation of a practical real-time system for automated pool game monitoring. This work establishes a foundation for intelligent sports analytics in precision-based games and demonstrates the effectiveness of specialized deep learning approaches for complex temporal video understanding tasks.