# HCQA-1.5 @ Ego4D EgoSchema Challenge 2025

Source: [HCQA-1.5 @ Ego4D EgoSchema Challenge 2025](<https://www.sota2.com/research/paper/68fa78df1e209131cea7af1f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:49:02.530Z

Authors: Haoyu Zhang, Yisen Feng, Qiaohui Chu, Meng Liu, Weili Guan, Yaowei Wang, Liqiang Nie

Published: 2025-05-27T02:45:14.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2505.20644>)

[PDF](<https://arxiv.org/pdf/2505.20644.pdf>)
