Welcome to the VSEM Website!

VSEM is a novel toolkit which allows the extraction of image-based representations of concepts in an easy fashion.

VSEM is equipped with state-of-the-art algorithms, from low-level feature detection and description up to the BoVW representation of images, together with a set of new routines necessary to move from an image-wise to a concept-wise representation of image content.





  • October 15, 2013

    VSEM 0.1.1 released

    A first minor upgrade of VSEM has been realeased! It contains some bug fixes and new options. Major release next.
    April 8, 2013

    VSEM 0.1 released

    The first version of VSEM has been released!
    April 6, 2013

    VSEM tutorials

    The Bag of Visual Words, Concepts and Similarity Benchmark tutorials are now online.
  • April 5, 2013

    VSEM website

    The official VSEM website is now online!
    October 1, 2012

    VLFeat 0.9.16 released

    Important updates include covariant feature detector such as DoG, Hessian, Harris Laplace, Hessian Laplace,Multiscale Hessian, Multiscale Harris.


Author = {E. Bruni, U. Ulisse, A. Liska, J. Uijlings and I. Sergienya},         
Title = {VSEM: An open library for visual semantics representation},
Journal = {Proceedings of ACL, Sofia, Bulgaria},
Year = {2013}