Datasets › MOSE

MOSE (Complex Video Object Segmentation)

Introduced by Henghui Ding et al. in MOSE: A New Dataset for Video Object Segmentation in Complex Scenes3 Feb 2023 archive 2025-07-28

CoMplex video Object SEgmentation (MOSE) is a dataset to study the tracking and segmenting objects in complex environments. MOSE contains 2,149 video clips and 5,200 objects from 36 categories, with 431,725 high-quality object segmentation masks. The most notable feature of MOSE dataset is complex scenes with crowded and occluded objects.

Source: MOSE: A New Dataset for Video Object Segmentation in Complex Scenes

Homepage Benchmarks Papers JSON

Benchmarks archive 2025-07-28

All 2 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
Semi-Supervised Video Object Segmentation	MOSE	SAM2 J&F 77.9	SAM 2: Segment Anything in Images and Videos	facebookresearch/segment-anything +10	17	Compare
Video Object Segmentation	MOSE	Cutie J&F 68.3	Putting the Object Back into Video Object Segmentation	hkchengrex/Cutie	1	Compare

Papers archive 2025-07-28

9 shown of 9 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 49. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

			Date	Samples run Syntology
SAM 2: Segment Anything in Images and Videos	11	1	1 Aug 2024	ran 28 of 49 samples (21 unverified)
Putting the Object Back into Video Object Segmentation	1	9	19 Oct 2023	ran 3 of 5 samples (2 unverified)
Tracking Anything with Decoupled Video Segmentation	1	2	7 Sep 2023	ran 7 of 10 samples (3 unverified; 10 pointer-only for licence)
Decoupling Features in Hierarchical Propagation for Video Object Segmentation	2	1	18 Oct 2022	not harvested
SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-Maximization	1	1	22 Aug 2022	not harvested
XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model	2	1	14 Jul 2022	ran 1 of 3 samples (2 unverified; 2 pointer-only for licence)
Recurrent Dynamic Embedding for Video Object Segmentation	1	1	8 May 2022	not harvested
Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation	3	1	9 Jun 2021	ran 6 of 10 samples (4 unverified; 2 pointer-only for licence)
Associating Objects with Transformers for Video Object Segmentation	2	1	4 Jun 2021	not harvested

Dataset loaders archive 2025-07-28

henghuiding/MOSE-apipytorch

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

Video Object Segmentation Semi-Supervised Video Object Segmentation Unsupervised Video Object Segmentation Video Semantic Segmentation Interactive Video Object Segmentation

License archive 2025-07-28

No licence recorded in the archive. Absence here is not a statement about the dataset's terms.

Modalities archive 2025-07-28

Videos

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

MOSE

1 variant name, 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