VSB100:Video Segmentation Benchmark

We provide multiple ground truth annotations for the Berkeley Video Dataset. It contains 100 HD quality videos divided into train and test folders containing 40 and 60 videos respectively.

Evaluation Metric Code

The annotation comes together with evaluation software that allows to produce comparative numbers. [Download code]


Full frame annotation - General Benchmark. Four different annotations per frame
(a) Train Set [Full Res] [Half Res]
(b) Test Set [Full Res] [Half Res]


Motion - objects which undergo significant motion. Objects such as snow, fire are excluded.
(a) Train Set [Full Res] [Half Res]
(b) Test Set [Full Res] [Half Res]

Non-rigid motion - subset of Motion subtask, objects which undergo signficant articulated motion
(a) Train Set [Full Res] [Half Res]
(b) Test Set [Full Res] [Half Res]

Camera motion - sequences where the camera moves
(a) Train Set [Full Res] [Half Res]
(b) Test Set [Full Res] [Half Res]

Terms of use

The dataset is provided for research purposes only and without any warranty. Any commercial use is prohibited. When using the dataset in your research work, you should cite the following papers:

F. Galasso, N.S. Nagaraja, T.J. Cardenas, T. Brox, B. Schiele
A Unified Video Segmentation Benchmark: Annotation, Metrics and Analysis,
International Conference on Computer Vision (ICCV), December 2013.

P. Sundberg, T. Brox, M. Maire, P. Arbelaez, and J. Malik
Occlusion Boundary Detection and Figure/Ground Assignment from Optical Flow,
Computer Vision and Pattern Recognition (CVPR), 2011

External links

Links to the Train and Test set videos of Berkeley Video Dataset.
(a) Train Set [40 Videos]
(b) Test Set [60 Videos]


Fabio Galasso
Naveen Shankar Nagaraja

Activity on VSB and bug reports

We appreciate your consideration of our work. In order to keep the benchmark a lively comparison arena, we will maintain below a brief log of activities, bug reports and critics. Please email us for any comments.

28.02.14 video naming and subfolders: the benchmark annotations and the source code of version 1.0 used a simplified naming for the BVDS videos. To reduce confusion we adopted the naming of the original BVDS. Note: the new code is compatible with the previous name notation and video structure, so you can keep using the (previously) downloaded labels with the new code. We are available to provide support.

15.02.14 we have corrected a naming issue (frame number) for the training sequence "galapagos", which only applied to motion and non-rigid motion labels.

13.02.14 bug report by Pablo Arbelaez: the ultrametric contour maps (UCM) which we computed from the annotations (just used in the BPR) were not thinned. That resulted in a slower boundary metric computation and slightly different BPR measures. We have now corrected the issue and will soon post an update of the BPR measures.