BoxMAC -- A Boxing Dataset for Multi-label Action Classification
This work addresses performance analysis in boxing for coaches and researchers, but it is incremental as it focuses on dataset creation and baseline methods.
The authors tackled the problem of analyzing boxers' performance by introducing BoxMAC, a real-world boxing dataset with over 60,000 frames and 13 action labels, and proposed a novel architecture for multi-label action classification in images and videos.
In competitive combat sports like boxing, analyzing a boxers's performance statics is crucial for evaluating the quantity and variety of punches delivered during bouts. These statistics provide valuable data and feedback, which are routinely used for coaching and performance enhancement. We introduce BoxMAC, a real-world boxing dataset featuring 15 professional boxers and encompassing 13 distinct action labels. Comprising over 60,000 frames, our dataset has been meticulously annotated for multiple actions per frame with inputs from a boxing coach. Since two boxers can execute different punches within a single timestamp, this problem falls under the domain of multi-label action classification. We propose a novel architecture for jointly recognizing multiple actions in both individual images and videos. We investigate baselines using deep neural network architectures to address both tasks. We believe that BoxMAC will enable researchers and practitioners to develop and evaluate more efficient models for performance analysis. With its realistic and diverse nature, BoxMAC can serve as a valuable resource for the advancement of boxing as a sport