HCQA-1.5 @ Ego4D EgoSchema Challenge 2025
This work addresses the challenge of accurate video QA for egocentric applications, representing an incremental improvement over prior methods.
The paper tackles the problem of improving answer prediction reliability in egocentric video question answering by extending the HCQA framework with multi-source aggregation and confidence-based filtering, achieving 77% accuracy on the EgoSchema test set.
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.