AIM & SCOPE

In real life, visual learning is supposed to be a continuous process. Opposite to this, in machine vision, learning has been so far considered in a limited and isolated way. Most of the nowadays approaches, with very few exceptions, require the intervention of the human operator to collect, segment and store hand-picked data and train pattern classifiers with them. However, for real world scenarios, it is unlikely to know beforehand the number of total classes or the exact number of instances per class. There is a recent trend in pattern recognition represented by online learning approaches, which treat to continuously update the data representation when new information arrives. Starting with a minimal set, the initial knowledge is expanded, by incorporating incoming instances, some of them which have not been previously available or foreseen at the application creation stage. An interesting characteristic of this strategy is that the train and test phases take place simultaneously. Given the increasing interest on this subject, the aim of this special issue is to be a landmark event in the development of online learning techniques and their applications with the hope that will capture the interest of a wider audience and will attract even more researchers.

TOPICS COVERED

Topics of interest include, but are not limited to the following:

- feature extraction and representation
- incremental/decremental learning strategies
- online classification
- unsupervised clustering
- novelty detection
- knowledge discovery
- optimal data representation to manage large datasets
- extraction and creation of semantic content from data
- contextual representation and reasoning
- developmental architectures
- modelling of cognitive processes

SUBMISSIONS

Manuscripts should be prepared according to the instructions of the “Guide for Authors” section of the journal found online at: http://www.elsevier.com/locate/imavis and the submission should be made online at the journal website. 

When making a submission authors should select “OPRMLT Special Issue” on the Article Type dropdown list in the first of the steps in the submission sequence.

Submission of a manuscript implies that it is the authors’ original unpublished work and is not being submitted for possible publication elsewhere.

Manuscripts will be assigned to international reviewers and the review processes will be managed by the Guest Editors working with the Editor-in-Chief, Professor K.D. Baker. For any clarification please contact Dr. Bogdan Raducanu, Prof. Jordi Vitrià or Prof. Ales Leonardis at the addresses below.

IMPORTANT DATES

     * Paper Submission deadline: 31 August 2008

     * Approximate Decision Notification date: 30 November 2008

     * Revised Paper Submission (if applicable): January, 2009

     * Approximate Final Decision Notification: February, 2009

     Tentative publication date: June 2009

GUEST EDITORS

Dr. Bogdan Raducanu, Prof. Jordi Vitrià

Computer Vision Center
Edifici “O” – Campus UAB
08193 Bellaterra (Barcelona)
SPAIN
Tel.: +34.93.581.1828
Fax: +34.93.581.1670
E-mail: {bogdan,jordi}@cvc.uab.es
URL: http://www.cvc.uab.es/~bogdan,  http://www.cvc.uab.es/~jordi

Prof. Ales Leonardis

Visual Cognitive Systems Laboratory 

Faculty of Computer and Information Science

University of Ljubljana

Tržaška 25

SI-1001 Ljubljana

SLOVENIA

Tel: +386 (1) 4768 868

Fax: +386 (1) 4264 647    

E-mail: ales.leonardis@fri.uni-lj.si

URL: http://vicos.fri.uni-lj.si/alesl/