{"url":"/dataset/st-vqa","name":"ST-VQA","full_name":"Scene Text Visual Question Answering","description_markdown":"ST-VQA aims to highlight the importance of exploiting high-level semantic information present in images as textual cues in the VQA process. \r\n\r\nSource: [Scene Text Visual Question Answering](/paper/scene-text-visual-question-answering)","description_withheld":null,"homepage":"https://rrc.cvc.uab.es/?ch=11","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/scene-text-visual-question-answering","title":"Scene Text Visual Question Answering","first_author":"Ali Furkan Biten","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"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":"Optical Character Recognition (OCR)","url":"/task/optical-character-recognition","datasets_with_task":"/datasets/task/optical-character-recognition"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["ST-VQA"],"data_loaders":[],"num_papers_in_archive":90,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"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."}