Datasets › BURST
BURST
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.
Class-guided
- Common: Track and segment all objects belonging to a set of 78 common classes (based on the COCO class set)
- Long-tail: Track and segment all objects belonging to an extended set of 482 object classes (based on the LVIS class set)
- 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)
Exemplar-guided
- 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).
- Box: Track and segment all objects in the video for which the first-frame object bounding-boxes are given.
- 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.
An illustration of the task hierarchy is given here and a detailed explanation is given in Sec. 5 of the dataset paper
Benchmarks archive 2025-07-28
All 5 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.
| First row (archive order) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| Long-tail Video Object Segmentation | BURST-val | GLEE-Pro HOTA (all) 31.2 | General Object Foundation Model for Images and Videos at Scale | FoundationVision/GLEE | 5 | Compare |
| Open-World Video Segmentation | BURST-val | DEVA (Mask2Former) OWTA (all) 69.9 | Tracking Anything with Decoupled Video Segmentation | hkchengrex/Tracking-Anything-with-DEVA | 3 | Compare |
| Semi-Supervised Video Object Segmentation | BURST-val | Cutie (base, MEGA, 600 pixels) HOTA (all) 61.2 | Putting the Object Back into Video Object Segmentation | hkchengrex/Cutie | 2 | Compare |
| Semi-Supervised Video Object Segmentation | BURST-test | Cutie (base, MEGA, 600 pixels) HOTA (all) 66.0 | Putting the Object Back into Video Object Segmentation | hkchengrex/Cutie | 2 | Compare |
| Long-tail Video Object Segmentation | BURST | GLEE-Lite HOTA (all) 22.6 | General Object Foundation Model for Images and Videos at Scale | FoundationVision/GLEE | 1 | Compare |
Papers archive 2025-07-28
papers with a benchmark row: 5 · with a code link: 4 · where Syntology ran a sample: 3 (3 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all papers with a benchmark rowonly where code ran (3 of 5 with a benchmark row: 3 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 5 of 5 with a leaderboard row on this dataset's benchmarks, newest first by the archive's date (ties by slug; undated papers last).
The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset, not that list; the archive's count for this dataset is 18. The Syntology column is from Syntology's graph, stated per sample; it is not part of any archive number. A line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified” (C is a part of N, never taken away from it); the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. When the archive marks a repository official for the paper, the cell starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.
Dataset loaders archive 2025-07-28
No loader listed in the archive.
Tasks archive 2025-07-28
License archive 2025-07-28
Modalities archive 2025-07-28
Languages archive 2025-07-28
No language tagged.
Variants archive 2025-07-28
- 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
28 variant names, as the archive lists them.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections