Visiotrain addresses the problem of understanding vision from both computational and cognitive points of view. The research approach will be based on formal mathematical models and on the thorough experimental validation of these models. Under this framework, we intend to reduce the gap that exists today between biological vision (which is by large not yet understood) and computer vision (which is biologically inspired and whose flexibility, robustness and autonomy remain to be demonstrated).

In order to achieve these ambitious goals, 11 academic partners plan to work cooperatively on a number of targeted research objectives:

1. computational theories and methods for low-level vision,
2. motion understanding from image sequences,
3. learning and recognition of shapes, objects and categories,
4. cognitive modelling of the action of seeing, and
5. functional imaging for observing and modelling brain activity.

In practice, these objectives will be achieved under the form of 11 PhD theses, each of one achieved collaboratively between three teams, as well as within-network mobility of 12 person-years of experienced researchers, each one of theses researchers having the opportunity to visit 2 other teams in the network for 6-month periods of time. The training programme includes participation to proof-of-concept achievements, annual thematic schools, industrial meetings, application of patents, attendance at conferences, and a women and science activity.