↑ Return to Projects


Scientific coordinator and contact : Radu Horaud, INRIA Grenoble Rhône-Alpes, France

The VISIONTRAIN proposal (19 November 2003) | The VISIONTRAIN technical annex (16 December 2004) | EU funding: 3.46M€

VISIONTRAIN (Computational and Cognitive Vision Systems) was an European Marie-Curie Research Training Network (MRTN-CT-2004-005439) granted for the period from 1 May 2005 to 30 April 2009.

Summary: The VISIONTRAIN research training network has addressed the problem of understanding vision from both computational and cognitive points of view. The research approach is based on formal mathematical models and tools and on the thorough experimental validation of these models. Under this framework the VISIONTRAIN researchers have contributed to reduce the gap existing today between the biological principles of visual perception and computational approaches to vision and image understanding. To achieve such an ambitious goal, the eleven partners involved in the network work cooperatively. These partners were: The Institut National de Recherche en Informatique et Automatique (Grenoble, France), Scuola Internazionale Superiore di Studi Avanzati (Trieste, Italy), The Malmo University (Sweden), University of Copenhagen (Denmark), The Technion (Haifa, Israel), The University of Oxford (United Kingdom), Univerza v Ljubljani (Slovenia), Ecole Polytechnique Federale de Lausanne (Switzerland), The Czech Technical University in Prague, Universiteit Utrecht (The Nederlands), and The University of Heidelberg (Germany). The targeted research topics were the followings: (i) computational theories and methods for low-level vision, (ii) motion understanding from image sequences, (iii) learning and recognition of shapes, objects, and categories, (iv) cognitive modelling of the action of seeing, and (v) functional imaging for observing and modelling brain activity.

The VISIONTRAIN network fully funded 11 PhD students (33 person-years) and 9 post-doctoral fellows (10 person-years). VISIONTRAIN researchers organized three thematic schools: Optimization Methods in Computer Vision, 12-17 March 2006; Computational and Neuro-physiological Models for Visual Perception, 25-30 March 2007, and Understanding Behavior from Video Sequences, 9-14 March 2008. All The schools were attended by all the VISIONTRAIN researchers as well as by researchers from other institutions. The thematic schools were organized at the prestigious Les Houches Physics School, France.


  • INRIA (France) – Coordinator
  • SISSA (Italy)
  • Malmo University (Sweden)
  • University of Copenhagen (Denmark)
  • Technion (Israel)
  • University of Oxford (United Kingdom)
  • Univerza v Ljubljani (Slovenia)
  • EPFL (Switzerland)
  • CTU Prague (Czech Republic)
  • Universiteit Utrecht (The Nederlands)
  • Universitat Heidelberg (Germany)