{"url":"/dataset/zs-f-vqa","name":"ZS-F-VQA","full_name":null,"description_markdown":"The ZS-F-VQA dataset  is a new split of the F-VQA dataset for zero-shot problem.\r\nFirstly we obtain the original train/test split of F-VQA dataset and combine them together to filter out the triples whose answers appear in top-500 according to its occurrence frequency.\r\nNext, we randomly divide this set of answers into new training split (a.k.a. seen) $\\mathcal{A}_s$ and testing split (a.k.a. unseen) $\\mathcal{A}_u$ at the ratio of 1:1. \r\nWith reference to F-VQA standard dataset, the division process is repeated 5 times. \r\nFor each $(i,q,a)$ triplet in original F-VQA dataset, it is divided into training set if $a \\in \\mathcal{A}_s$. Else it is divided into testing set.\r\nThe overlap of answer instance between training and testing set in F-VQA are $2565$ compared to $0$ in ZS-F-VQA.","description_withheld":null,"homepage":"https://github.com/China-UK-ZSL/ZS-F-VQA","introduced_date":"2021-07-12","introduced_date_note":null,"introduced_by":{"paper":"/paper/zero-shot-visual-question-answering-using","title":"Zero-shot Visual Question Answering using Knowledge Graph","first_author":"Zhuo Chen","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Graphs","url":"/datasets/modality/graphs"}],"tasks":[{"name":"Visual Question Answering (VQA)","url":"/task/visual-question-answering","datasets_with_task":"/datasets/task/visual-question-answering"},{"name":"Factual Visual Question Answering","url":"/task/factual-visual-question-answering","datasets_with_task":"/datasets/task/factual-visual-question-answering"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["ZS-F-VQA"],"data_loaders":[],"num_papers_in_archive":6,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/visual-question-answering-on-zs-f-vqa","task":"Visual Question Answering (VQA)","dataset_variant":"ZS-F-VQA","rows":1,"metrics":["Top-1 Accuracy"],"first_row_in_archive_order":{"model":"SAN † - hard mask","paper":"/paper/zero-shot-visual-question-answering-using","metrics":{"Top-1 Accuracy":"29.39"},"code_links":[{"title":"Fangyin1994/KCL","url":"https://github.com/Fangyin1994/KCL"},{"title":"China-UK-ZSL/ZS-F-VQA","url":"https://github.com/China-UK-ZSL/ZS-F-VQA"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/zero-shot-visual-question-answering-using","title":"Zero-shot Visual Question Answering using Knowledge Graph","date":"2021-07-12","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"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."}