{"url":"/dataset/tvr","name":"TVR","full_name":"TV show Retrieval","description_markdown":"A new multimodal retrieval dataset. TVR requires systems to understand both videos and their associated subtitle (dialogue) texts, making it more realistic. The dataset contains 109K queries collected on 21.8K videos from 6 TV shows of diverse genres, where each query is associated with a tight temporal window. \r\n\r\nSource: [TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval](/paper/tvr-a-large-scale-dataset-for-video-subtitle)","description_withheld":null,"homepage":"https://github.com/jayleicn/TVRetrieval","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/tvr-a-large-scale-dataset-for-video-subtitle","title":"TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval","first_author":"Jie Lei","url":null},"license":null,"modalities":[],"tasks":[{"name":"Video Retrieval","url":"/task/video-retrieval","datasets_with_task":"/datasets/task/video-retrieval"},{"name":"Partially Relevant Video Retrieval","url":"/task/partially-relevant-video-retrieval","datasets_with_task":"/datasets/task/partially-relevant-video-retrieval"},{"name":"Video Corpus Moment Retrieval","url":"/task/video-corpus-moment-retrieval","datasets_with_task":"/datasets/task/video-corpus-moment-retrieval"}],"languages":[],"variants":["TVR"],"data_loaders":[{"repo":"https://github.com/jayleicn/TVRetrieval","url":"https://github.com/jayleicn/TVRetrieval","frameworks":["pytorch"]}],"num_papers_in_archive":34,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/video-retrieval-on-tvr","task":"Video Retrieval","dataset_variant":"TVR","rows":2,"metrics":["R@10","R@1","R@100"],"first_row_in_archive_order":{"model":"Hero w/ pre-training","paper":"/paper/hero-hierarchical-encoder-for-video-language","metrics":{"R@1":"4.34","R@10":"13.97","R@100":"21.78"},"code_links":[{"title":"linjieli222/HERO","url":"https://github.com/linjieli222/HERO"},{"title":"linjieli222/hero_video_feature_extractor","url":"https://github.com/linjieli222/hero_video_feature_extractor"},{"title":"grounded-sport-convai/goal-baselines","url":"https://gitlab.com/grounded-sport-convai/goal-baselines"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/partially-relevant-video-retrieval-on-tvr","task":"Partially Relevant Video Retrieval","dataset_variant":"TVR","rows":1,"metrics":["Recall@Sum"],"first_row_in_archive_order":{"model":"ms-sl","paper":"/paper/partially-relevant-video-retrieval","metrics":{"Recall@Sum":"172.3"},"code_links":[{"title":"HuiGuanLab/ms-sl","url":"https://github.com/HuiGuanLab/ms-sl"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/partially-relevant-video-retrieval","title":"Partially Relevant Video Retrieval","date":"2022-08-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hero-hierarchical-encoder-for-video-language","title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training","date":"2020-05-01","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":13,"samples_ran":5,"samples_unverified":8,"pointer_only_for_licence":8,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/tvr-a-large-scale-dataset-for-video-subtitle","title":"TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval","date":"2020-01-24","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":19,"samples_ran":8,"samples_unverified":11,"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":2,"samples_harvested":32,"samples_ran":13,"samples_unverified":19,"pointer_only_for_licence":8,"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."}