{"url":"/dataset/tgif-qa","name":"TGIF-QA","full_name":"TGIF-QA","description_markdown":"The TGIF-QA dataset contains 165K QA pairs for the animated GIFs from the TGIF dataset [Li et al. CVPR 2016]. The question & answer pairs are collected via crowdsourcing with a carefully designed user interface to ensure quality. The dataset can be used to evaluate video-based Visual Question Answering techniques.\r\n\r\nSource: [GitHub](https://github.com/YunseokJANG/tgif-qa)\r\nImage Source: [https://github.com/YunseokJANG/tgif-qa](https://github.com/YunseokJANG/tgif-qa)","description_withheld":null,"homepage":"https://github.com/YunseokJANG/tgif-qa","introduced_date":"2017-04-14","introduced_date_note":null,"introduced_by":{"paper":"/paper/tgif-qa-toward-spatio-temporal-reasoning-in","title":"TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering","first_author":"Yunseok Jang","url":null},"license":{"name":"Custom (research-only)","url":"https://github.com/YunseokJANG/tgif-qa"},"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":"Zero-Shot Video Question Answer","url":"/task/zeroshot-video-question-answer","datasets_with_task":"/datasets/task/zeroshot-video-question-answer"},{"name":"Zeroshot Video Question Answer","url":"/task/zeroshot-video-question-answer-1","datasets_with_task":"/datasets/task/zeroshot-video-question-answer-1"},{"name":"TGIF-Action","url":"/task/tgif-action","datasets_with_task":"/datasets/task/tgif-action"},{"name":"TGIF-Transition","url":"/task/tgif-transition","datasets_with_task":"/datasets/task/tgif-transition"},{"name":"TGIF-Frame","url":"/task/tgif-frame","datasets_with_task":"/datasets/task/tgif-frame"}],"languages":[],"variants":["TGIF-QA"],"data_loaders":[{"repo":"https://github.com/YunseokJANG/tgif-qa","url":"https://github.com/YunseokJANG/tgif-qa","frameworks":["tf"]}],"num_papers_in_archive":92,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/zeroshot-video-question-answer-on-tgif-qa","task":"Zero-Shot Video Question Answer","dataset_variant":"TGIF-QA","rows":14,"metrics":["Accuracy","Confidence Score"],"first_row_in_archive_order":{"model":"Tarsier (34B)","paper":"/paper/tarsier-recipes-for-training-and-evaluating-1","metrics":{"Accuracy":"82.5","Confidence Score":"4.4"},"code_links":[{"title":"bytedance/tarsier","url":"https://github.com/bytedance/tarsier"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-question-answering-on-tgif-qa","task":"Visual Question Answering (VQA)","dataset_variant":"TGIF-QA","rows":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"HiTeA","paper":"/paper/hitea-hierarchical-temporal-aware-video","metrics":{"Accuracy":"0.732"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-question-answering-on-tgif-qa","task":"Video Question Answering","dataset_variant":"TGIF-QA","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"LocVLM-Vid-B","paper":"/paper/learning-to-localize-objects-improves-spatial","metrics":{"Accuracy":"51.8"},"code_links":[{"title":"kahnchana/locvlm","url":"https://github.com/kahnchana/locvlm"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/linvt-empower-your-image-level-large-language","title":"LinVT: Empower Your Image-level Large Language Model to Understand Videos","date":"2024-12-06","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":4,"samples_unverified":8,"pointer_only_for_licence":12,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/ts-llava-constructing-visual-tokens-through","title":"TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models","date":"2024-11-17","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":5,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/slowfast-llava-a-strong-training-free","title":"SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models","date":"2024-07-22","rows_on_this_dataset":1,"code_links":1,"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."}},{"paper":"/paper/tarsier-recipes-for-training-and-evaluating-1","title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","date":"2024-06-30","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/videogpt-integrating-image-and-video-encoders","title":"VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding","date":"2024-06-13","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":6,"samples_unverified":2,"pointer_only_for_licence":8,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/pllava-parameter-free-llava-extension-from-1","title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning","date":"2024-04-25","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":0,"samples_unverified":2,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-to-localize-objects-improves-spatial","title":"Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs","date":"2024-04-11","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/minigpt4-video-advancing-multimodal-llms-for","title":"MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens","date":"2024-04-04","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":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/an-image-grid-can-be-worth-a-video-zero-shot","title":"An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM","date":"2024-03-27","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/elysium-exploring-object-level-perception-in","title":"Elysium: Exploring Object-level Perception in Videos via MLLM","date":"2024-03-25","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":7,"samples_unverified":1,"pointer_only_for_licence":8,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/video-llava-learning-united-visual-1","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","date":"2023-11-16","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":4,"samples_unverified":3,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/chat-univi-unified-visual-representation","title":"Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding","date":"2023-11-14","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/video-chatgpt-towards-detailed-video","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","date":"2023-06-08","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/videochat-chat-centric-video-understanding","title":"VideoChat: Chat-Centric Video Understanding","date":"2023-05-10","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hitea-hierarchical-temporal-aware-video","title":"HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training","date":"2022-12-30","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/internvideo-general-video-foundation-models","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","date":"2022-12-06","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/zero-shot-video-question-answering-via-frozen","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","date":"2022-06-16","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":34,"samples_ran":14,"samples_unverified":20,"pointer_only_for_licence":1,"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":12,"samples_harvested":98,"samples_ran":54,"samples_unverified":44,"pointer_only_for_licence":38,"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."}