OSGNet @ Ego4D Episodic Memory Challenge 2025

TL;DR

This paper presents OSGNet, a novel early fusion-based model that achieved first place in all three tracks of the Ego4D Episodic Memory Challenge 2025, advancing egocentric video localization accuracy.

Contribution

The paper introduces an early fusion approach for egocentric video localization, outperforming previous late fusion methods and setting new state-of-the-art results in the challenge.

Findings

Achieved first place in all three challenge tracks

Outperformed previous late fusion methods

Demonstrated effectiveness of early fusion approach

Abstract

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.