We invite submission of extended abstracts to the workshop. Extended abstracts should be 2-4 pages, formatted in the NIPS style. Unlike the main NIPS conference, identities of authors do not need to be removed from the extended abstracts.
Extended abstracts should be sent in .PDF or .PS file format by email, to either D.Hardoon@cs.ucl.ac.uk or gleen@cis.hut.fi. Acceptance to the workshop will be determined based on peer review of each extended abstract.
Submissions are expected to represent high-quality, novel contributions in theory/methods of learning from multiple sources, or high-quality, novel contributions in application of learning from multiple sources to robotics (see below).
Submitted extended abstracts may be accepted either as an oral presentation or as a poster presentation; there will be only a limited number of oral presentations in the morning and afternoon sessions.
Accepted extended abstracts will be made available online at the workshop website.
Evaluation data set for robotics papers. To
encourage participants from the machine learning community to test their
algorithms in the domain of robotics, we describe below a dataset, with
computed features, representative of open research issues in robotics.
Robotics-oriented papers submitted to the workshop are strongly
encouraged to contain an experimental evaluation on the database described
below. The obtained results will be presented by the organizers during
the workshop.
The provided robot database is the IDOL2 database, which is focused on the robot localization task, and is available at http://cogvis.nada.kth.se/IDOL2/.
A complete baseline multiple cues integration system running on this dataset is available in the following paper: L. Jie, F. Orabona, and B. Caputo. An online framework for learning novel concepts over multiple cues. Accepted in Asian Conference on Computer Vision (ACCV), 2009, Xi'an, China. The features used in that paper are also available: contact Francesco Orabona (francesco.orabona AT idiap.ch) or Barbara Caputo (bcaputo AT idiap.ch) to obtain the features.
Possible special issue. Depending on the quality of submissions, we will consider preparing a special issue of a journal or a collected volume on the topic of the workshop. A separate call for papers will then be issued after the workshop for the special issue/collected volume. Last year's "Learning from Multiple Sources" workshop led to a special issue in Machine Learning (currently in progress).
Submission of extended abstracts: October 27, 2009 - Deadline extended - November 2nd, 2009
Notification of acceptance: >November 6, 2009 - 10th November 2009
Workshop registration: See below
Workshop takes place: December 12, 2009
For questions about the workshop, contact David R. Hardoon at D.Hardoon AT cs.ucl.ac.uk.
For questions about the website, contact Simon Rogers at srogers AT dcs.gla.ac.uk.