Feature Combination Meets Attention: Baidu Soccer Embeddings and Transformer based Temporal Detection
This work addresses the need for efficient video editing in sports broadcasting, but it is incremental as it builds on existing action recognition and transformer methods.
The authors tackled the problem of automating sports video editing by precisely recognizing and locating events in untrimmed soccer broadcast videos, achieving state-of-the-art performance in action spotting and replay grounding tasks in the SoccerNet-v2 Challenge.
With rapidly evolving internet technologies and emerging tools, sports related videos generated online are increasing at an unprecedentedly fast pace. To automate sports video editing/highlight generation process, a key task is to precisely recognize and locate the events in the long untrimmed videos. In this tech report, we present a two-stage paradigm to detect what and when events happen in soccer broadcast videos. Specifically, we fine-tune multiple action recognition models on soccer data to extract high-level semantic features, and design a transformer based temporal detection module to locate the target events. This approach achieved the state-of-the-art performance in both two tasks, i.e., action spotting and replay grounding, in the SoccerNet-v2 Challenge, under CVPR 2021 ActivityNet workshop. Our soccer embedding features are released at https://github.com/baidu-research/vidpress-sports. By sharing these features with the broader community, we hope to accelerate the research into soccer video understanding.