arXiv 2506.180712025-06-27cs.CVcs.AI

MUPA：迈向面向基于视觉基础的视频问答的多路径智能体推理

MUPA: Towards Multi-Path Agentic Reasoning for Grounded Video Question Answering

Lanzhou University（兰州大学）；National University of Singapore（新加坡国立大学）；Sun Yat-sen University（中山大学）；Jinan University（暨南大学）；Nanyang Technological University（南洋理工大学）；Peking University（北京大学）；University of Science and Technology of China（中国科学技术大学）；Hefei University of Technology（合肥工业大学）

Jisheng Dang, Huilin Song, Junbin Xiao, Bimei Wang, Han Peng, Haoxuan Li, Xun Yang, Meng Wang, Tat-Seng Chua

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出协作式多路径智能体方法MUPA，通过统一视频定位、问答、答案反思与聚合，在仅2B参数下即超越7B模型，显著提升了视频问答的视觉基础保真度与答案准确性。

摘要：

基于视觉基础的视频问答要求将文本答案与显式视觉证据相对齐。然而，现代多模态模型通常依赖语言先验和虚假相关性，导致基础预测效果不佳。在本研究中，我们提出了MUPA，这是一种协作式的多路径智能体方法，统一了视频定位、问答、答案反思与聚合以解决该问题。MUPA在定位智能体和QA智能体之间以不同时间顺序交互，设计了三种不同的推理路径，并配备专门的反思智能体来判断和聚合多路径结果，以实现一致的问答与定位。该设计在不牺牲答案准确性的情况下显著提升了定位保真度。尽管仅使用2B参数，我们的方法仍优于所有7B规模的竞争对手。当扩展至7B参数时，MUPA创造了新的最优结果，在NExT-GQA和DeVE-QA上的Acc@GQA分别达到30.3%和47.4%，证明了MUPA在可信视频语言理解方面的有效性。

英文摘要：

Grounded Video Question Answering (Grounded VideoQA) requires aligning textual answers with explicit visual evidence. However, modern multimodal models often rely on linguistic priors and spurious correlations, resulting in poorly grounded predictions. In this work, we propose MUPA, a cooperative MUlti-Path Agentic approach that unifies video grounding, question answering, answer reflection and aggregation to tackle Grounded VideoQA. MUPA features three distinct reasoning paths on the interplay of grounding and QA agents in different chronological orders, along with a dedicated reflection agent to judge and aggregate the multi-path results to accomplish consistent QA and grounding. This design markedly improves grounding fidelity without sacrificing answer accuracy. Despite using only 2B parameters, our method outperforms all 7B-scale competitors. When scaled to 7B parameters, MUPA establishes new state-of-the-art results, with Acc@GQA of 30.3% and 47.4% on NExT-GQA and DeVE-QA respectively, demonstrating MUPA' effectiveness towards trustworthy video-language understanding. Our code is available in https://github.com/longmalongma/MUPA.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。