{"url":"/dataset/trafficqa","name":"SUTD-TrafficQA","full_name":null,"description_markdown":"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.","description_withheld":null,"homepage":"https://sutdcv.github.io/SUTD-TrafficQA","introduced_date":"2021-03-29","introduced_date_note":null,"introduced_by":{"paper":"/paper/trafficqa-a-question-answering-benchmark-and","title":"SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events","first_author":"Li Xu","url":null},"license":{"name":"Custom (research-only, non-commercial)","url":"https://sutdcv.github.io/SUTD-TrafficQA/#/download"},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Visual Question Answering (VQA)","url":"/task/visual-question-answering","datasets_with_task":"/datasets/task/visual-question-answering"},{"name":"Video Question Answering","url":"/task/video-question-answering","datasets_with_task":"/datasets/task/video-question-answering"},{"name":"Logical Reasoning Question Answering","url":"/task/logical-reasoning-question-ansering","datasets_with_task":"/datasets/task/logical-reasoning-question-ansering"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["SUTD-TrafficQA"],"data_loaders":[{"repo":"https://github.com/SUTDCV/SUTD-TrafficQA","url":"https://github.com/SUTDCV/SUTD-TrafficQA","frameworks":[]}],"num_papers_in_archive":19,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/video-question-answering-on-sutd-trafficqa","task":"Video Question Answering","dataset_variant":"SUTD-TrafficQA","rows":6,"metrics":["1/4","1/2"],"first_row_in_archive_order":{"model":"CFMMC-Align","paper":null,"metrics":{"1/4":"50.2"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/tem-adapter-adapting-image-text-pretraining","title":"Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer","date":"2023-08-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/trafficqa-a-question-answering-benchmark-and","title":"SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events","date":"2021-03-29","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":1,"samples_unverified":8,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/hierarchical-conditional-relation-networks","title":"Hierarchical Conditional Relation Networks for Video Question Answering","date":"2020-02-25","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/tvqa-localized-compositional-video-question","title":"TVQA: Localized, Compositional Video Question Answering","date":"2018-09-05","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":3,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/exploring-models-and-data-for-image-question","title":"Exploring Models and Data for Image Question Answering","date":"2015-05-08","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":3,"samples_harvested":20,"samples_ran":6,"samples_unverified":14,"pointer_only_for_licence":4,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}