Traffic-Domain Video Question Answering with Automatic Captioning (2307.09636v1)

Abstract: 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-LLMs. Empirical findings obtained from the SUTD-TrafficQA task highlight the substantial enhancements achieved by TRIVIA, elevating the accuracy of representative video-LLMs 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-LLMs in traffic-related applications.