{"url":"/dataset/dramaqa","name":"DramaQA","full_name":null,"description_markdown":"The DramaQA focuses on two perspectives: 1) Hierarchical QAs as an evaluation metric based on the cognitive developmental stages of human intelligence. 2) Character-centered video annotations to model local coherence of the story. The dataset is built upon the TV drama \"Another Miss Oh\" and it contains 17,983 QA pairs from 23,928 various length video clips, with each QA pair belonging to one of four difficulty levels.\r\n\r\nSource: [DramaQA: Character-Centered Video Story Understanding with Hierarchical QA](/paper/dramaqa-character-centered-video-story)","description_withheld":null,"homepage":"https://dramaqa.snu.ac.kr/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/dramaqa-character-centered-video-story","title":"DramaQA: Character-Centered Video Story Understanding with Hierarchical QA","first_author":"Seong-Ho Choi","url":null},"license":null,"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Video Question Answering","url":"/task/video-question-answering","datasets_with_task":"/datasets/task/video-question-answering"},{"name":"Video Understanding","url":"/task/video-understanding","datasets_with_task":"/datasets/task/video-understanding"},{"name":"Video Question Answering (Level 3)","url":"/task/video-question-answering-level-3","datasets_with_task":"/datasets/task/video-question-answering-level-3"},{"name":"Video Question Answering (Level 4)","url":"/task/video-question-answering-level-4","datasets_with_task":"/datasets/task/video-question-answering-level-4"}],"languages":[],"variants":["DramaQA"],"data_loaders":[],"num_papers_in_archive":12,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/video-question-answering-on-dramaqa","task":"Video Question Answering","dataset_variant":"DramaQA","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"LLaMA-VQA","paper":"/paper/large-language-models-are-temporal-and-causal","metrics":{"Accuracy":"84.1"},"code_links":[{"title":"mlvlab/Flipped-VQA","url":"https://github.com/mlvlab/Flipped-VQA"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/large-language-models-are-temporal-and-causal","title":"Large Language Models are Temporal and Causal Reasoners for Video Question Answering","date":"2023-10-24","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":0,"samples_unverified":4,"pointer_only_for_licence":0,"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":1,"samples_harvested":4,"samples_ran":0,"samples_unverified":4,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":1,"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."}