{"url":"/dataset/usc-grad-stddb","name":"USC-GRAD-STDdb","full_name":"Small Target Detection database","description_markdown":"USC-GRAD-STDdb comprises 115 video segments containing more than 25,000 annotated frames of HD 720p resolution (≈1280x720) with small objects of interest from 16 (≈4x4) to 256 (≈16x16) as pixel area. The length of the videos changes from 150 up to 500 frames. The size of every object is determined through the bounding box, so that a good annotation is of utmost importance for reliable performance metrics. As it may seem obvious, the smaller the object, the harder the annotation. The annotation has been carried out with the ViTBAT tool, adjusting the boxes as much as possible to the objects of interest in each video frame. In total, more than 56,000 ground truth labels have been generated.","description_withheld":null,"homepage":"https://gitlab.citius.usc.es/brais.bosquet/USC-GRAD-STDdb","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Video Object Detection","url":"/task/video-object-detection","datasets_with_task":"/datasets/task/video-object-detection"},{"name":"Small Object Detection","url":"/task/small-object-detection","datasets_with_task":"/datasets/task/small-object-detection"}],"languages":[],"variants":["USC-GRAD-STDdb"],"data_loaders":[{"repo":"https://github.com/smallblcak/USC-GRAD-STDdb","url":"https://github.com/smallblcak/USC-GRAD-STDdb","frameworks":["pytorch"]}],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/video-object-detection-on-usc-grad-stddb","task":"Video Object Detection","dataset_variant":"USC-GRAD-STDdb","rows":1,"metrics":["AP","AP 0.5"],"first_row_in_archive_order":{"model":"SLTnet FPN-X101","paper":"/paper/short-term-anchor-linking-and-long-term-self","metrics":{"AP":"16.6","AP 0.5":"44.9"},"code_links":[{"title":"daniel-cores/SLTnet","url":"https://github.com/daniel-cores/SLTnet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/short-term-anchor-linking-and-long-term-self","title":"Short-term anchor linking and long-term self-guided attention for video object detection","date":"2021-04-18","rows_on_this_dataset":1,"code_links":1,"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."}