Blocks is an open source modular MATLAB framework which allows the user to avoid needlessly repeating computation.
Download Blocks 0.1.1 (Windows, Mac, Linux)
Blocks may be easily used for your own experiments, and comes with some useful modules for computer vision experiments: an implementation of a simple image level bag-of-features (BoF) classifier, a fast agglomerative information bottleneck (AIB) sliding window localization scheme, and a class segmentation scheme using superpixel neighborhoods and a conditional random field (CRF). It also provides support for running experiments on clusters of computers.
Documentation
Tutorials
- Blocks – Getting started with Blocks
- Bag of Features – Bag-of-features image categorization
- AIB Localization – Agglomerative Information Bottleneck Localization
- Superpixel Class Segmentation – Class segmentation with superpixels and a conditional random field (CRF).
BibTeX entry
@inproceedings{fulkerson09class, Author = {B. Fulkerson and A. Vedaldi and S. Soatto}, Booktitle = {Proc. {ICCV}}, Title = {Class Segmentation and Object Localization with Superpixel Neighborhoods}, Year = {2009} }
Acknowledgments
Part of this work was supported by the UCLA Vision Lab and the Oxford VGG Lab. The authors would like to thank the many colleagues that have contributed to Blocks by testing and providing helpful suggestions and comments.