Special Issue of the International Journal of Computer Vision (IJCV): Learning for vision and vision for learning.
Computational Vision and Machine Learning have become synergetic fields of research. Modern machine learning techniques have permitted large experimental improvements as well as a re-thinking of key problems such as recognition. On the other hand, vision has broadened the scope of machine learning offering rich and challenging new problems.
We solicit papers describing machine learning methods developed for or adapted to vision tasks and representations (and vice versa), such as
- priors and kernels useful for particular tasks
- machine learning algorithms addressing vision problems, e.g. fast detection, multi class categorization, semi supervised learning etc
- representations learned from images or videos, or optimized for visual inference
We wish to make the ideas and experiments presented in this special issue very easily accessible to other researchers. We will therefore require all authors to: a) Post their data (training and testing) on the web. b) Make their code available in a form that allows other researchers to repeat easily the experiments, as well as run the code on different data and test modified versions of the algorithms. The form (executable, sources, libraries) and level of documentation is up to the authors. The editors and the referees are allowed to make use of the code and database in their review of the manuscript.
The editors will encourage some of the referees to write a short commentary on the paper and on their experience in testing the code. The authors will be allowed a rebuttal if appropriate.
As a second category of paper, we solicit submissions describing non-proprietary vision databases created for benchmarking or for training. Such databases are proving to be crucial for progress in both machine learning and computer vision. The creation of a good database requires much thought, effort, and care. We want to recognize that scientific contribution by assigning the status of a journal paper to a good training set or database. We expect that such a paper will describe the motivation and intellectual contributions of the database (e.g. by comparing with previously available databases and perhaps pointing out their shortcomings), as well as details of the collection and labelling. The ideal database is one that can be augmented by other researchers.
Submissions should be marked "Special Issue: Learning for Vision" and sent to: Monique Fier / IJCV / Springer Monique.Fier@springer-sbm.com, +1 781 681 0607 Please indicate who of the three special issue editors should handle your paper (try to match the subject areas with the expertise of the editor).
We will return without review submissions that we feel are not well aligned with our goals for the issue. We will be happy to take a look at abstracts and drafts ahead of time, to let you know whether we feel that the paper would fit with the issue. In this case, please send your material to one of the editors of the special issue ahead of time.
Submission deadline: August 15, 2005
Scheduled publication date: Fall 2006
Editors:
Bill Freeman (billf@mit.edu)
Pietro Perona (perona@caltech.edu)
Bernhard Schlkopf (bernhard.schoelkopf@tuebingen.mpg.de)