-
[pdf]
[supp]
[bibtex]@InProceedings{Xu_2021_CVPR, author = {Xu, Li and Huang, He and Liu, Jun}, title = {SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning Over Traffic Events}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2021}, pages = {9878-9888} }
SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning Over Traffic Events
Abstract
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.
Related Material