{"url":"/dataset/youtube-boundingboxes","name":"YT-BB","full_name":"YouTube-BoundingBoxes","description_markdown":"YouTube-BoundingBoxes (YT-BB) is a large-scale data set of video URLs with densely-sampled object bounding box annotations. The data set consists of approximately 380,000 video segments about 19s long, automatically selected to feature objects in natural settings without editing or post-processing, with a recording quality often akin to that of a hand-held cell phone camera. The objects represent a subset of the MS COCO label set. All video segments were human-annotated with high-precision classification labels and bounding boxes at 1 frame per second. \r\n\r\nSource: [YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video](https://arxiv.org/pdf/1702.00824.pdf)","description_withheld":null,"homepage":"https://research.google.com/youtube-bb/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/youtube-boundingboxes-a-large-high-precision","title":"YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video","first_author":"Esteban Real","url":null},"license":null,"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Object Detection","url":"/task/object-detection","datasets_with_task":"/datasets/task/object-detection"},{"name":"Visual Tracking","url":"/task/visual-tracking","datasets_with_task":"/datasets/task/visual-tracking"},{"name":"Video Object Detection","url":"/task/video-object-detection","datasets_with_task":"/datasets/task/video-object-detection"}],"languages":[],"variants":["YT-BB"],"data_loaders":[],"num_papers_in_archive":7,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/video-object-detection-on-yt-bb","task":"Video Object Detection","dataset_variant":"YT-BB","rows":1,"metrics":["mAP"],"first_row_in_archive_order":{"model":"","paper":"/paper/objects-do-not-disappear-video-object","metrics":{"mAP":"59.8"},"code_links":[{"title":"l-kid/video-object-detection-by-location-anticipation","url":"https://github.com/l-kid/video-object-detection-by-location-anticipation"},{"title":"Elstuhn/Video-object-detection-by-location-anticipation","url":"https://github.com/Elstuhn/Video-object-detection-by-location-anticipation"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/objects-do-not-disappear-video-object","title":"Objects do not disappear: Video object detection by single-frame object location anticipation","date":"2023-08-09","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"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."}