GazeNLQ @ Ego4D Natural Language Queries Challenge 2025

TL;DR

This paper introduces GazeNLQ, a novel method that uses gaze data and contrastive learning to improve natural language query-based video retrieval in egocentric videos, achieving state-of-the-art localization accuracy.

Contribution

We propose GazeNLQ, a new approach that leverages gaze estimation and contrastive pretraining to enhance video segment retrieval from egocentric videos based on natural language queries.

Findings

Achieves R1@IoU0.3 of 27.82

Achieves R1@IoU0.5 of 18.68

Demonstrates improved localization accuracy using gaze data

Abstract

This report presents our solution to the Ego4D Natural Language Queries (NLQ) Challenge at CVPR 2025. Egocentric video captures the scene from the wearer's perspective, where gaze serves as a key non-verbal communication cue that reflects visual attention and offer insights into human intention and cognition. Motivated by this, we propose a novel approach, GazeNLQ, which leverages gaze to retrieve video segments that match given natural language queries. Specifically, we introduce a contrastive learning-based pretraining strategy for gaze estimation directly from video. The estimated gaze is used to augment video representations within proposed model, thereby enhancing localization accuracy. Experimental results show that GazeNLQ achieves R1@IoU0.3 and R1@IoU0.5 scores of 27.82 and 18.68, respectively. Our code is available at https://github.com/stevenlin510/GazeNLQ.