AI RESEARCH
OSGNet with MLLM Reranking @ Ego4D Episodic Memory Challenge 2026
arXiv CS.CV
•
ArXi:2605.20818v1 Announce Type: new 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.