HCQA-1.5 @ Ego4D EgoSchema Challenge 2025

TL;DR

This paper presents an improved egocentric video question answering method that combines multi-source prediction, confidence filtering, and fine-grained reasoning, achieving third place in the Ego4D EgoSchema Challenge 2025.

Contribution

It introduces a novel multi-source aggregation and confidence-based filtering approach with a reasoning module for egocentric video QA.

Findings

Achieved 77% accuracy on EgoSchema test set

Outperformed last year's winning solution

Secured third place in the challenge

Abstract

In this report, we present the method that achieves third place for Ego4D EgoSchema Challenge in CVPR 2025. To improve the reliability of answer prediction in egocentric video question answering, we propose an effective extension to the previously proposed HCQA framework. Our approach introduces a multi-source aggregation strategy to generate diverse predictions, followed by a confidence-based filtering mechanism that selects high-confidence answers directly. For low-confidence cases, we incorporate a fine-grained reasoning module that performs additional visual and contextual analysis to refine the predictions. Evaluated on the EgoSchema blind test set, our method achieves 77% accuracy on over 5,000 human-curated multiple-choice questions, outperforming last year's winning solution and the majority of participating teams. Our code will be added at https://github.com/Hyu-Zhang/HCQA.