English

Motion Aware Self-Supervision for Generic Event Boundary Detection

Computer Vision and Pattern Recognition 2022-10-13 v2 Artificial Intelligence Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.2210.05574,
  title  = {Motion Aware Self-Supervision for Generic Event Boundary Detection},
  author = {Ayush K. Rai and Tarun Krishna and Julia Dietlmeier and Kevin McGuinness and Alan F. Smeaton and Noel E. O'Connor},
  journal= {arXiv preprint arXiv:2210.05574},
  year   = {2022}
}

Comments

Accepted in IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2023

R2 v1 2026-06-28T03:15:53.540Z