# OSGNet with MLLM Reranking @ Ego4D Episodic Memory Challenge 2026

arXiv: https://arxiv.org/abs/2605.20818 · HTML: https://mlsanity.com/paper/2605.20818/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 15 references that are in the map.
- First posted on arXiv 20 May 2026.

## Builds on (most cited first, 9 of 9)

- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding](https://mlsanity.com/paper/2503.13377/) (2025)
- [Spatial Understanding from Videos: Structured Prompts Meet Simulation Data](https://mlsanity.com/paper/2506.03642/) (2025)
- [Universal Video Temporal Grounding with Generative Multi-modal Large Language Models](https://mlsanity.com/paper/2506.18883/) (2025)
- [Exo2Ego: Exocentric Knowledge Guided MLLM for Egocentric Video Understanding](https://mlsanity.com/paper/2503.09143/) (2025)
- [GroundNLQ @ Ego4D Natural Language Queries Challenge 2023](https://mlsanity.com/paper/2306.15255/) (2023)
- [Object-Shot Enhanced Grounding Network for Egocentric Video](https://mlsanity.com/paper/2505.04270/) (2025)
- [ObjectNLQ @ Ego4D Episodic Memory Challenge 2024](https://mlsanity.com/paper/2406.15778/) (2024)
- [OSGNet @ Ego4D Episodic Memory Challenge 2025](https://mlsanity.com/paper/2506.03710/) (2025)

## Abstract (arXiv)

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.