DIVE: Deep-search Iterative Video Exploration A Technical Report for the CVRR Challenge at CVPR 2025
This addresses the challenge of robust video question answering for AI systems, though it is incremental as it builds on existing iterative reasoning methods.
The paper tackled the problem of generating accurate natural language answers to complex questions about real-world videos, achieving 81.44% accuracy on the CVRR-ES benchmark and winning first place in the CVPR 2025 challenge.
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