提升第一人称视频问答可靠性，多源聚合+置信度筛选获第三名
HCQA-1.5 @ Ego4D EgoSchema Challenge 2025
- 多源预测聚合生成多样答案，再用置信度筛选高可信结果
- 低置信度时引入细粒度推理模块，结合视觉与上下文优化判断
- 在超5000题测试集上达77%准确率，优于去年冠军和多数团队
本文报告了在CVPR 2025年Ego4D EgoSchema挑战赛中取得第三名的方法。为提升第一人称视频问答中答案预测的可靠性，我们对先前提出的HCQA框架进行了有效扩展。方法包括：引入多源聚合策略生成多样化预测，随后通过基于置信度的过滤机制直接选取高置信答案；对于低置信情况，加入细粒度推理模块，进行额外的视觉与上下文分析以优化预测。在EgoSchema盲测集上，该方法在超过5,000道人工标注的多选题上达到77%的准确率，超越去年冠军方案及多数参赛队伍。代码将发布于https://github.com/Hyu-Zhang/HCQA。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。