SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning Over Traffic Events

SUTD-TrafficQA is a dataset that takes the form of Video QA based on 10,080 in-the-wild videos and annotated 62,535 QA pairs, for benchmarking the cognitive capability of causal inference and event understanding models in complex traffic scenarios. Specifically, the dataset proposes 6 challenging reasoning tasks corresponding to various traffic scenarios, so as to evaluate the reasoning capability over different kinds of complex yet practical traffic events.