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

Traffic event cognition and reasoning in videos is an important task that has a wide range of applications in intelligent transportation, assisted driving, and autonomous vehicles. In this paper, we create a novel dataset, SUTD-TrafficQA (Traffic Question Answering), which takes the form of video QA based on the collected 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, we propose 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. Moreover, we propose Eclipse, a novel Efficient glimpse network via dynamic inference, in order to achieve computation-efficient and reliable video reasoning. The experiments show that our method achieves superior performance while reducing the computation cost significantly. The project page: https://github. com/SUTDCV/ SUTD- TrafficQA.

Automated summary

This paper discusses the importance of traffic event cognition and reasoning in videos, and introduces a novel dataset SUTD-TrafficQA for benchmarking cognitive capability in complex traffic scenarios. By proposing 6 challenging reasoning tasks and introducing Eclipse method, the study achieves computation-efficient and reliable video reasoning with superior performance.