News Archive


- Between 1.02.2008-31.07.2008 I will be a post-doc visitor at the IDIAP Research Institute in Martigny, Switzerland.


- Co-chair (together with prof. Jordi Vitrià and prof. Ales Leonardis) of the Special Session: Online Pattern Recognition and Machine Learning Techniques for Computer-Vision Applications (in conjunction with the VISAPP conference, 22-25 January 2008, Funchal, Island of Madeira, Portugal)


-  Invited talk “Incremental Subspace Learning for Cognitive Visual Processes” at the Institute for Artificial Intelligence (IIIA-CSIC), Barcelona, Spain

Abstract: In real life, visual learning is supposed to be a continuous process. Humans have an innate facility to recognize objects even under less-than-ideal conditions and to build robust representations of them. These representations can be altered with the arrival of new information and thus the model of the world is continuously updated. Inspired by the biological paradigm, we propose in this paper an incremental subspace representation for cognitive vision processes. The proposed approach has been applied to the problem of face recognition. The experiments performed on a custom database show that at the end of incremental learning process the recognition performance achieved converges towards the result obtained using an off-line learning strategy


-  Chairman of a Special Session on “Human Presence Detection for Context-aware Systems” as part of the VISAPP conference. CVC was co-organizer of 2007 VISAPP edition.


-  Visit to CICATA – IPN (Research Center for Applied Science and Advanced Technology – National Polytechnic Institute), Queretaro Unit, Mexico.


-  Opening ceremony of the ‘Apropa’t a la Ciència’ (‘Closer to Science’) Exhibition which takes place at Palau Robert (Barcelona, Spain) and whose aim is to bring people closer to different areas of science. Our group is one of the exhibitors with an application (‘AIBOFace’) for AIBO robots focused on interaction with persons (face detection). This is a real challenge because it is supposed that our system run uninterrupted for 7 months (the exhibition closes on July 31st, 2007). If you are interested in our work, take a few moments and visit our stand. You can download a media coverage of our application - broadcasted on TVE2 (January 2nd, 2007) as part of the ‘Redes’ (Networks) scientific magazine.


-  Invited talk “Face Detection and Tracking: First Steps Towards Human-Centered Technology” at a seminar organized by PREMIA (Pattern Recognition and Machine Intelligence Association from Singapore). The event was hosted at the NTU (Nanyang Technological University), Singapore.
The use of context can be a very relevant cue for computer vision-based systems, in order to eliminate a lot of ambiguity and uncertainty, otherwise inherent in the human-computer interaction. Despite of the fact that its obvious importance s widely acknowledged, the great majority of the systems nowadays still lack of this capability. In this paper, we propose faces as a primary contextual information for person detection and present face tracking as a basic procedure for context-driven focus of attention applications. Our proposal was implemented in a combined system, by integrating a motion-based approach ("Particle Filter") and a model-based approach ("Ada-Boost").