{"url":"/dataset/clevr-humans","name":"CLEVR-Humans","full_name":null,"description_markdown":"We collect  a  new  dataset  of  human-posed  free-form  natural  language  questions  about  CLEVR  images.    Many  of  these questions have out-of-vocabulary words and require reasoning skills that are absent from our model’s repertoire","description_withheld":null,"homepage":"https://cs.stanford.edu/people/jcjohns/iep/","introduced_date":"2017-05-10","introduced_date_note":null,"introduced_by":{"paper":"/paper/inferring-and-executing-programs-for-visual","title":"Inferring and Executing Programs for Visual Reasoning","first_author":"Justin Johnson","url":null},"license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Visual Question Answering (VQA)","url":"/task/visual-question-answering","datasets_with_task":"/datasets/task/visual-question-answering"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["CLEVR-Humans"],"data_loaders":[],"num_papers_in_archive":18,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/visual-question-answering-on-clevr-humans","task":"Visual Question Answering (VQA)","dataset_variant":"CLEVR-Humans","rows":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"MDETR","paper":"/paper/mdetr-modulated-detection-for-end-to-end","metrics":{"Accuracy":"81.7"},"code_links":[{"title":"facebookresearch/multimodal","url":"https://github.com/facebookresearch/multimodal"},{"title":"ashkamath/mdetr","url":"https://github.com/ashkamath/mdetr"},{"title":"thunlp/pevl","url":"https://github.com/thunlp/pevl"},{"title":"b-faye/lightmdetr","url":"https://github.com/b-faye/lightmdetr"},{"title":"AleDella/mdter_eval","url":"https://github.com/AleDella/mdter_eval"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/mdetr-modulated-detection-for-end-to-end","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","date":"2021-04-26","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":6,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/neural-symbolic-vqa-disentangling-reasoning","title":"Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding","date":"2018-10-04","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/compositional-attention-networks-for-machine","title":"Compositional Attention Networks for Machine Reasoning","date":"2018-03-08","rows_on_this_dataset":1,"code_links":10,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":1,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/film-visual-reasoning-with-a-general","title":"FiLM: Visual Reasoning with a General Conditioning Layer","date":"2017-09-22","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":9,"samples_unverified":1,"pointer_only_for_licence":7,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/inferring-and-executing-programs-for-visual","title":"Inferring and Executing Programs for Visual Reasoning","date":"2017-05-10","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":4,"samples_unverified":2,"pointer_only_for_licence":6,"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":5,"samples_harvested":36,"samples_ran":22,"samples_unverified":14,"pointer_only_for_licence":15,"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."}