Winning the CVPR'2021 Kinetics-GEBD Challenge: Contrastive Learning Approach
This work addresses the problem of detecting event boundaries in videos as perceived by humans, which is incremental as it builds on a newly introduced task with a novel method.
The paper tackles the Generic Event Boundary Detection (GEBD) task by introducing a contrastive learning approach that leverages feature similarity variations near event boundaries, achieving a significant performance boost compared to given baselines.
Generic Event Boundary Detection (GEBD) is a newly introduced task that aims to detect "general" event boundaries that correspond to natural human perception. In this paper, we introduce a novel contrastive learning based approach to deal with the GEBD. Our intuition is that the feature similarity of the video snippet would significantly vary near the event boundaries, while remaining relatively the same in the remaining part of the video. In our model, Temporal Self-similarity Matrix (TSM) is utilized as an intermediate representation which takes on a role as an information bottleneck. With our model, we achieved significant performance boost compared to the given baselines. Our code is available at https://github.com/hello-jinwoo/LOVEU-CVPR2021.