SUTD-TrafficQA (Singapore University of Technology and Design - Traffic Question Answering) is a dataset which 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.
Variants: SUTD-TrafficQA
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Video Question Answering | Tem-adapter | Tem-adapter: Adapting Image-Text Pretraining for … | 2023-08-16 |
| Video Question Answering | Eclipse | SUTD-TrafficQA: A Question Answering Benchmark … | 2021-03-29 |
| Video Question Answering | HCRN | Hierarchical Conditional Relation Networks for … | 2020-02-25 |
| Video Question Answering | TVQA | TVQA: Localized, Compositional Video Question … | 2018-09-05 |
| Video Question Answering | VIS+LST | Exploring Models and Data for … | 2015-05-08 |
Recent papers with results on this dataset: