Biomechanical-phase based Temporal Segmentation in Sports Videos: a Demonstration on Javelin-Throw
This work addresses the need for scalable and cost-effective motion analysis in sports analytics, particularly for elite javelin-throw, though it is incremental as it builds on existing methods.
The paper tackles the problem of automatic temporal segmentation of biomechanical phases in sports videos, specifically for javelin-throw, by proposing an unsupervised framework that combines structured optimal transport with an attention-based spatio-temporal graph convolutional network, achieving 71.02% mAP and 74.61% F1-score on test data.
Precise analysis of athletic motion is central to sports analytics, particularly in disciplines where nuanced biomechanical phases directly impact performance outcomes. Traditional analytics techniques rely on manual annotation or laboratory-based instrumentation, which are time-consuming, costly, and lack scalability. Automatic extraction of relevant kinetic variables requires a robust and contextually appropriate temporal segmentation. Considering the specific case of elite javelin-throw, we present a novel unsupervised framework for such a contextually aware segmentation, which applies the structured optimal transport (SOT) concept to augment the well-known Attention-based Spatio-Temporal Graph Convolutional Network (ASTGCN). This enables the identification of motion phase transitions without requiring expensive manual labeling. Extensive experiments demonstrate that our approach outperforms state-of-the-art unsupervised methods, achieving 71.02% mean average precision (mAP) and 74.61% F1-score on test data, substantially higher than competing baselines. We also release a new dataset of 211 manually annotated professional javelin-throw videos with frame-level annotations, covering key biomechanical phases: approach steps, drive, throw, and recovery.