A Context-Aware Loss Function for Action Spotting in Soccer Videos
This work addresses action localization in sports videos, with potential applications in automatic highlights generation, but it is incremental as it builds on existing methods with a novel loss function.
The paper tackled the problem of action spotting in videos by proposing a context-aware loss function that considers temporal context around actions, achieving a 12.8% improvement over the baseline on the SoccerNet dataset.
In video understanding, action spotting consists in temporally localizing human-induced events annotated with single timestamps. In this paper, we propose a novel loss function that specifically considers the temporal context naturally present around each action, rather than focusing on the single annotated frame to spot. We benchmark our loss on a large dataset of soccer videos, SoccerNet, and achieve an improvement of 12.8% over the baseline. We show the generalization capability of our loss for generic activity proposals and detection on ActivityNet, by spotting the beginning and the end of each activity. Furthermore, we provide an extended ablation study and display challenging cases for action spotting in soccer videos. Finally, we qualitatively illustrate how our loss induces a precise temporal understanding of actions and show how such semantic knowledge can be used for automatic highlights generation.