DIVE通过迭代推理提升复杂视频问答准确率，获CVPR 2025挑战赛冠军。
DIVE: Deep-search Iterative Video Exploration A Technical Report for the CVRR Challenge at CVPR 2025
- 采用分步推理机制，将问题逐步拆解并逐层求解
- 在CVRR-ES基准上达81.44%测试准确率，排名第一
- 适合需要高鲁棒性视频理解的场景，如智能监控与医疗分析
本文介绍在2025年复杂视频推理与鲁棒性评估挑战赛中获得第一名的解决方案。该挑战旨在评估模型对多样化真实视频片段进行自然语言问答的准确性，使用包含214个独特视频和2,400个问答对的复杂视频推理与鲁棒性评估套件（CVRR-ES）基准，涵盖11个类别。我们的方法DIVE（Deep-search Iterative Video Exploration）采用迭代推理策略，将每个输入问题进行语义分解，并通过逐步推理与渐进式推断求解，使系统能够对最复杂的查询生成高度准确且上下文恰当的回答。在CVRR-ES基准上，该方法在测试集上达到81.44%的准确率，位居所有参赛者首位。本报告详细阐述了方法设计，并提供了实验结果的全面分析，验证了迭代推理框架在实现鲁棒视频问答方面的有效性。代码已开源：https://github.com/PanasonicConnect/DIVE。
原文摘要 · Abstract (English)
In this report, we present the winning solution that achieved the 1st place in the Complex Video Reasoning & Robustness Evaluation Challenge 2025. This challenge evaluates the ability to generate accurate natural language answers to questions about diverse, real-world video clips. It uses the Complex Video Reasoning and Robustness Evaluation Suite (CVRR-ES) benchmark, which consists of 214 unique videos and 2,400 question-answer pairs spanning 11 categories. Our method, DIVE (Deep-search Iterative Video Exploration), adopts an iterative reasoning approach, in which each input question is semantically decomposed and solved through stepwise reasoning and progressive inference. This enables our system to provide highly accurate and contextually appropriate answers to even the most complex queries. Applied to the CVRR-ES benchmark, our approach achieves 81.44% accuracy on the test set, securing the top position among all participants. This report details our methodology and provides a comprehensive analysis of the experimental results, demonstrating the effectiveness of our iterative reasoning framework in achieving robust video question answering. The code is available at https://github.com/PanasonicConnect/DIVE
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。