Datasets › FBMS-59

FBMS-59 (Freiburg-Berkeley Motion Segmentation)

1 Jan 2010 archive 2025-07-28

The Freiburg-Berkeley Motion Segmentation Dataset (FBMS-59) is a dataset for motion segmentation, which extends the BMS-26 dataset with 33 additional video sequences. A total of 720 frames is annotated. FBMS-59 comes with a split into a training set and a test set. Typical challenges appear in both sets.

Source: https://lmb.informatik.uni-freiburg.de/resources/datasets/moseg.en.html Image Source: https://lmb.informatik.uni-freiburg.de/resources/datasets/moseg.en.html

Homepage Benchmarks Papers JSON

Benchmarks archive 2025-07-28

All 3 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
Video Salient Object Detection	FBMS-59	RealFlow S-Measure 0.926	Transforming Static Images Using Generative Models for...	—	16	Compare
Unsupervised Object Segmentation	FBMS-59	RCF (with post-processing) mIoU 72.4	Bootstrapping Objectness from Videos by Relaxed Common...	TonyLianLong/RCF-UnsupVideoSeg	7	Compare
Video Object Segmentation	FBMS-59	LOCATE mIoU 68.8	LOCATE: Self-supervised Object Discovery via Flow-guided...	silky1708/locate	1	Compare

Papers archive 2025-07-28

18 shown of 18 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 19. 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
Transforming Static Images Using Generative Models for Video Salient Object Detection	0	1	21 Nov 2024	not harvested
LOCATE: Self-supervised Object Discovery via Flow-guided Graph-cut and Bootstrapped Self-training	1	1	22 Aug 2023	ran 5 of 6 samples (1 unverified; 6 pointer-only for licence)
Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual Grouping	1	2	17 Apr 2023	not harvested
Motion-inductive Self-supervised Object Discovery in Videos	0	1	1 Oct 2022	not harvested
TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cut	0	1	1 Sep 2022	not harvested
Segmenting Moving Objects via an Object-Centric Layered Representation	1	1	5 Jul 2022	ran 16 of 21 samples (5 unverified)
Guess What Moves: Unsupervised Video and Image Segmentation by Anticipating Motion	0	1	16 May 2022	not harvested
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection	1	1	9 Mar 2022	ran 0 of 13 samples (13 unverified)
The Emergence of Objectness: Learning Zero-Shot Segmentation from Videos	1	1	11 Nov 2021	not harvested
Semi-Supervised Video Salient Object Detection Using Pseudo-Labels	1	1	12 Aug 2019	not harvested
Shifting More Attention to Video Salient Object Detection	1	1	1 Jun 2019	not harvested
Unsupervised Video Object Segmentation with Motion-based Bilateral Networks	0	1	1 Sep 2018	not harvested
Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection	0	1	1 Sep 2018	not harvested
Flow Guided Recurrent Neural Encoder for Video Salient Object Detection	0	1	1 Jun 2018	not harvested
Real-Time Salient Object Detection With a Minimum Spanning Tree	1	1	1 Jun 2016	not harvested
Minimum Barrier Salient Object Detection at 80 FPS	0	1	1 Dec 2015	not harvested
Saliency-Aware Geodesic Video Object Segmentation	0	1	1 Jun 2015	not harvested
Time-Mapping Using Space-Time Saliency	0	1	1 Jun 2014	not harvested

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

Video Object Segmentation Video Salient Object Detection Unsupervised Object Segmentation Unsupervised 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

Images Videos

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

FBMS-59

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