BoxMAC -- A Boxing Dataset for Multi-label Action Classification

TL;DR

BoxMAC is a comprehensive, annotated boxing dataset designed to facilitate multi-label action classification, enabling improved performance analysis and model development for boxing sports.

Contribution

The paper introduces BoxMAC, a new real-world boxing dataset with multi-label annotations and proposes a novel architecture for recognizing multiple actions in images and videos.

Findings

Baseline deep learning models evaluated on BoxMAC.

The dataset captures realistic boxing scenarios with diverse actions.

Proposed architecture effectively recognizes multiple simultaneous actions.

Abstract

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