OSGNet with MLLM Reranking @ Ego4D Episodic Memory Challenge 2026

TL;DR

This paper introduces a reranking framework combining OSGNet and multimodal large language models to improve temporal localization in egocentric videos, achieving top results in the Ego4D challenge.

Contribution

The novel integration of OSGNet with MLLM reranking significantly enhances localization accuracy in egocentric video tasks.

Findings

Achieved first place in both challenge tracks.

Effective combination of existing localization and reasoning models.

Improved candidate selection accuracy.

Abstract

In this report, we present our champion solutions for the Natural Language Queries and GoalStep tracks of the Ego4D Episodic Memory Challenge at CVPR 2026. Both tracks require accurately localizing temporal segments from long untrimmed egocentric videos. To address these tasks, we propose a reranking-based framework that effectively leverages the strong video-language reasoning capability of multimodal large language model (MLLM) while preserving the efficiency and candidate recall of conventional localization pipelines. Specifically, we first obtain a set of candidate segments from existing localization model OSGNet, and then employ MLLM to select the segment that best matches the given query, thereby refining the final prediction. Ultimately, our method achieved first place in both the Natural Language Queries and GoalStep tracks. Our code can be found at https://github.com/iLearn-Lab/CVPR25-OSGNet.