{"url":"/dataset/burst","name":"BURST","full_name":null,"description_markdown":"BURST is a benchmark suite built upon TAO that requires tracking and segmenting multiple objects from camera video. The benchmark contains 6 different sub-tasks divided into 2 groups that all share the same data for training/validation/testing.\r\n\r\n#####  Class-guided\r\n1. **Common:**  Track and segment all objects belonging to a set of 78 common classes (based on the COCO class set)\r\n2. **Long-tail**: Track and segment all objects belonging to an extended set of 482 object classes (based on the LVIS class set)\r\n3. **Open-world**: Methods are only allowed to use the annotations of the 78 common classes during training, but during inference they are expected  to track and segment all 482 object classes (class label predictions are not required)\r\n\r\n#####  Exemplar-guided\r\n4. **Mask**: Track and segment all objects in the video for which the first-frame object masks are  given. This task is identical to Video Object Segmentation  (VOS).\r\n5. **Box**: Track and segment all objects in the video for which the first-frame object bounding-boxes are  given.\r\n6. **Point**: Track and segment all objects in the video for which we are only given the (x,y) point coordinates of the mask centroid in the first-frame in which the objects appear.\r\n\r\nAn illustration of the task hierarchy is given [here](https://github.com/Ali2500/BURST-benchmark/blob/main/.images/task_taxonomy.PNG) and a detailed explanation is given in Sec. 5 of the dataset  paper","description_withheld":null,"homepage":"https://github.com/Ali2500/BURST-benchmark","introduced_date":"2022-09-25","introduced_date_note":null,"introduced_by":{"paper":"/paper/burst-a-benchmark-for-unifying-object","title":"BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video","first_author":"Ali Athar","url":null},"license":{"name":"MIT","url":"https://github.com/Ali2500/BURST-benchmark/blob/main/LICENSE"},"modalities":[{"name":"RGB Video","url":"/datasets/modality/rgb-video"}],"tasks":[{"name":"Semi-Supervised Video Object Segmentation","url":"/task/semi-supervised-video-object-segmentation","datasets_with_task":"/datasets/task/semi-supervised-video-object-segmentation"},{"name":"Video Instance Segmentation","url":"/task/video-instance-segmentation","datasets_with_task":"/datasets/task/video-instance-segmentation"},{"name":"Multi-Object Tracking and Segmentation","url":"/task/multi-object-tracking-and-segmentation","datasets_with_task":"/datasets/task/multi-object-tracking-and-segmentation"},{"name":"Long-tail Video Object Segmentation","url":"/task/long-tail-video-object-segmentation","datasets_with_task":"/datasets/task/long-tail-video-object-segmentation"},{"name":"Open-World Video Segmentation","url":"/task/open-world-video-segmentation","datasets_with_task":"/datasets/task/open-world-video-segmentation"}],"languages":[],"variants":["BURST-test","BURST-val","BURST Point Exemplar-guided (test)","BURST Point Exemplar-guided (val)","BURST Box Exemplar-guided (test) ","BURST Box Exemplar-guided (val)","BURST Mask Exemplar-guided (test)","BURST Mask Exemplar-guided (val)","BURST Open-world Class-guided (test)","BURST Open-world Class-guided (val)","BURST Long-tail Class-guided (test)","BURST Long-tail Class-guided (val)","BURST Common Class-guided (test)","BURST Common Class-guided (val)","Exemplar-guided - point - test","Exemplar-guided - box - test","Exemplar-guided - mask - test","Class-guided - open-world - test","Class-guided - long-tail - test","Class-guided - common - test","Exemplar-guided - point - val","Exemplar-guided - box - val","Exemplar-guided - mask - val","Class-guided - open-world - val","Class-guided - long-tail - val","Class-guided - common - val","Class-guided (common)","BURST"],"data_loaders":[],"num_papers_in_archive":18,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/long-tail-video-object-segmentation-on-burst-1","task":"Long-tail Video Object Segmentation","dataset_variant":"BURST-val","rows":5,"metrics":["HOTA (all)","mAP (all)","HOTA (com)","mAP (com)","HOTA (unc)","mAP (unc)"],"first_row_in_archive_order":{"model":"GLEE-Pro","paper":"/paper/general-object-foundation-model-for-images","metrics":{"HOTA (all)":"31.2","HOTA (com)":"48.7","HOTA (unc)":"26.9","mAP (all)":"19.2","mAP (com)":"24.8","mAP (unc)":"17.7"},"code_links":[{"title":"FoundationVision/GLEE","url":"https://github.com/FoundationVision/GLEE"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/open-world-video-segmentation-on-burst-val","task":"Open-World Video Segmentation","dataset_variant":"BURST-val","rows":3,"metrics":["OWTA (all)","OWTA (com)","OWTA (unc)"],"first_row_in_archive_order":{"model":"DEVA (Mask2Former)","paper":"/paper/tracking-anything-with-decoupled-video","metrics":{"OWTA (all)":"69.9","OWTA (com)":"75.2","OWTA (unc)":"41.5"},"code_links":[{"title":"hkchengrex/Tracking-Anything-with-DEVA","url":"https://github.com/hkchengrex/Tracking-Anything-with-DEVA"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-22","task":"Semi-Supervised Video Object Segmentation","dataset_variant":"BURST-val","rows":2,"metrics":["HOTA (all)","HOTA (common)","HOTA (uncommon)"],"first_row_in_archive_order":{"model":"Cutie (base, MEGA, 600 pixels)","paper":"/paper/putting-the-object-back-into-video-object","metrics":{"HOTA (all)":"61.2","HOTA (common)":"65.0","HOTA (uncommon)":"60.3"},"code_links":[{"title":"hkchengrex/Cutie","url":"https://github.com/hkchengrex/Cutie"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-23","task":"Semi-Supervised Video Object Segmentation","dataset_variant":"BURST-test","rows":2,"metrics":["HOTA (all)","HOTA (common)","HOTA (uncommon)"],"first_row_in_archive_order":{"model":"Cutie (base, MEGA, 600 pixels)","paper":"/paper/putting-the-object-back-into-video-object","metrics":{"HOTA (all)":"66.0","HOTA (common)":"66.5","HOTA (uncommon)":"65.9"},"code_links":[{"title":"hkchengrex/Cutie","url":"https://github.com/hkchengrex/Cutie"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/long-tail-video-object-segmentation-on-burst","task":"Long-tail Video Object Segmentation","dataset_variant":"BURST","rows":1,"metrics":["HOTA (all)","mAP (all)","HOTA (com)","mAP (com)","HOTA (unc)","mAP (unc)"],"first_row_in_archive_order":{"model":"GLEE-Lite","paper":"/paper/general-object-foundation-model-for-images","metrics":{"HOTA (all)":"22.6","HOTA (com)":"36.4","HOTA (unc)":"19.1","mAP (all)":"12.6","mAP (com)":"18.9","mAP (unc)":"11.0"},"code_links":[{"title":"FoundationVision/GLEE","url":"https://github.com/FoundationVision/GLEE"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/general-object-foundation-model-for-images","title":"General Object Foundation Model for Images and Videos at Scale","date":"2023-12-14","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":13,"samples_ran":8,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/putting-the-object-back-into-video-object","title":"Putting the Object Back into Video Object Segmentation","date":"2023-10-19","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":5,"samples_ran":3,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/tracking-anything-with-decoupled-video","title":"Tracking Anything with Decoupled Video Segmentation","date":"2023-09-07","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":10,"samples_ran":7,"samples_unverified":3,"pointer_only_for_licence":10,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/burst-a-benchmark-for-unifying-object","title":"BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video","date":"2022-09-25","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/opening-up-open-world-tracking-1","title":"Opening Up Open World Tracking","date":"2022-01-01","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":3,"samples_harvested":28,"samples_ran":18,"samples_unverified":10,"pointer_only_for_licence":10,"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."}