结合自动字幕生成的交通域视频问答
Traffic-Domain Video Question Answering with Automatic Captioning
AI总结：
针对交通域VidQA缺乏场景知识融合的问题，提出弱监督方法TRIVIA将交通知识注入大视频语言模型，在SUTD-TrafficQA任务上使模型准确率提升6.5个百分点（19.88%）。
摘要：
视频问答（VidQA）在赋能智能交通监控与智能交通系统领域的高级机器推理能力方面展现出显著潜力。然而，以往研究对将城市场景知识融入VidQA系统的关注较为有限。本研究提出了一种名为Traffic-domain Video Question Answering with Automatic Captioning（TRIVIA，带自动字幕的交通域视频问答）的新方法，它是一种将交通领域知识注入大型视频语言模型的弱监督技术。在SUTD-TrafficQA任务上的实验结果表明，TRIVIA带来了显著提升，与基线设置相比，代表性视频语言模型的准确率提升了6.5个百分点（19.88%）。这一开创性方法有望推动该领域的发展，启发研究人员与从业者充分挖掘新兴视频语言模型在交通相关应用中的潜力。
英文摘要：
Video Question Answering (VidQA) exhibits remarkable potential in facilitating advanced machine reasoning capabilities within the domains of Intelligent Traffic Monitoring and Intelligent Transportation Systems. Nevertheless, the integration of urban traffic scene knowledge into VidQA systems has received limited attention in previous research endeavors. In this work, we present a novel approach termed Traffic-domain Video Question Answering with Automatic Captioning (TRIVIA), which serves as a weak-supervision technique for infusing traffic-domain knowledge into large video-language models. Empirical findings obtained from the SUTD-TrafficQA task highlight the substantial enhancements achieved by TRIVIA, elevating the accuracy of representative video-language models by a remarkable 6.5 points (19.88%) compared to baseline settings. This pioneering methodology holds great promise for driving advancements in the field, inspiring researchers and practitioners alike to unlock the full potential of emerging video-language models in traffic-related applications.
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。
