{"url":"/dataset/ted-vcr","name":"TED VCR","full_name":null,"description_markdown":"The TED VCR Video Retrieval Dataset is a multimodal collection derived from publicly available TED Talks. It contains thousands of talks filtered to retain only those with meaningful topic labels, producing a long-tail, multi-label taxonomy. For each talk the dataset provides automatic speech-recognition transcripts, slide- and scene-level OCR text, and frame-level visual captions—three textual channels used in VCR retrieval experiments. The data are split into 80 % train, 10 % validation, and 10 % test while preserving the original topic distribution, leaving 542 talks as a held-out test set. Two ready-to-download archives accompany the release: 4.2 GB of trimmed MP4 videos with metadata and 1.8 GB of pre-computed CLIP and Whisper embeddings, both shared under the non-commercial CC BY-NC-ND 4.0 license.","description_withheld":null,"homepage":"https://github.com/oronnir/VCR","introduced_date":"2024-02-12","introduced_date_note":null,"introduced_by":{"paper":"/paper/vcr-video-representation-for-contextual","title":"VCR: Video representation for Contextual Retrieval","first_author":"Oron Nir","url":null},"license":{"name":"CC BY--NC--ND4.0 International","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Cross-Modal Information Retrieval","url":"/task/cross-modal-information-retrieval","datasets_with_task":"/datasets/task/cross-modal-information-retrieval"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["TED VCR"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"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."}