In this report, we present our champion solutions for the three egocentric video localization tracks of the Ego4D Episodic Memory Challenge at CVPR 2025. All tracks require precise localization of the interval within an untrimmed egocentric video. Previous unified video localization approaches often rely on late fusion strategies, which tend to yield suboptimal results. To address this, we adopt an early fusion-based video localization model to tackle all three tasks, aiming to enhance localization accuracy. Ultimately, our method achieved first place in the Natural Language Queries, Goal Step, and Moment Queries tracks, demonstrating its effectiveness. Our code can be found at https://github.com/Yisen-Feng/OSGNet.
@article{arxiv.2506.03710,
title = {OSGNet @ Ego4D Episodic Memory Challenge 2025},
author = {Yisen Feng and Haoyu Zhang and Qiaohui Chu and Meng Liu and Weili Guan and Yaowei Wang and Liqiang Nie},
journal= {arXiv preprint arXiv:2506.03710},
year = {2025}
}
Comments
The champion solutions for the three egocentric video localization tracks(Natural Language Queries, Goal Step, and Moment Queries tracks) of the Ego4D Episodic Memory Challenge at CVPR EgoVis Workshop 2025