Motion Aware Self-Supervision for Generic Event Boundary Detection
This work addresses the need for simplified approaches in GEBD, which is important for video analysis applications, but it is incremental as it builds on existing self-supervised methods.
The paper tackles the problem of Generic Event Boundary Detection (GEBD) in videos by augmenting a simple self-supervised method with a differentiable motion feature learning module to handle spatial and temporal diversities, achieving efficacy demonstrated on Kinetics-GEBD and TAPOS datasets compared to other self-supervised state-of-the-art methods.
The task of Generic Event Boundary Detection (GEBD) aims to detect moments in videos that are naturally perceived by humans as generic and taxonomy-free event boundaries. Modeling the dynamically evolving temporal and spatial changes in a video makes GEBD a difficult problem to solve. Existing approaches involve very complex and sophisticated pipelines in terms of architectural design choices, hence creating a need for more straightforward and simplified approaches. In this work, we address this issue by revisiting a simple and effective self-supervised method and augment it with a differentiable motion feature learning module to tackle the spatial and temporal diversities in the GEBD task. We perform extensive experiments on the challenging Kinetics-GEBD and TAPOS datasets to demonstrate the efficacy of the proposed approach compared to the other self-supervised state-of-the-art methods. We also show that this simple self-supervised approach learns motion features without any explicit motion-specific pretext task.