AISB Convention 2015

The AISB Convention is an annual conference covering the range of AI and Cognitive Science, organised by the Society for the Study of Artificial Intelligence and Simulation of Behaviour. The 2015 Convention will be held at the Uni...


Read More...

Yasemin Erden on BBC

AISB Committee member, and Philosophy Programme Director and Lecturer, Dr Yasemin J. Erden interviewed for the BBC on 29 October 2013. Speaking on the Today programme for BBC Radio 4, as well as the Business Report for BBC world N...


Read More...

Mark Bishop on BBC ...

Mark Bishop, Chair of the Study of Artificial Intelligence and the Simulation of Behaviour, appeared on Newsnight to discuss the ethics of ‘killer robots’. He was approached to give his view on a report raising questions on the et...


Read More...

AISB YouTube Channel

The AISB has launched a YouTube channel: http://www.youtube.com/user/AISBTube (http://www.youtube.com/user/AISBTube). The channel currently holds a number of videos from the AISB 2010 Convention. Videos include the AISB round t...


Read More...

Lighthill Debates

The Lighthill debates from 1973 are now available on YouTube. You need to a flashplayer enabled browser to view this YouTube video  


Read More...
01234

Notice

AISB event Bulletin Item

CFP: Workshop on Non-rigid Registration and Tracking through Learning (NRTL 2007)

http://express.hid.ri.cmu.edu/NRTL2007/index.html

  Call for Papers

Workshop on Non-rigid Registration and Tracking through Learning - NRTL 2007
          http://express.hid.ri.cmu.edu/NRTL2007/index.html

                       Rio de Janeiro, Brazil
                           14 October 2007
                  (In conjunction with ICCV 2007)

In the past decade, the issues of registering / tracking non-rigid 
objects in image / video and recovering their structure have received 
much attention in the computer vision, pattern recognition, and medical 
imaging communities. Many of these methods are based on well founded 
statistical models and machine learning techniques. Such methods include 
active appearance models, active shape models, active blobs, 3D 
morphable models, etc. On the workshop webpages, we shall employ the 
loose term "learned object models (LOMs)" to encompass this broad body 
of work. Interestingly, all these approaches share similar frameworks 
and, unfortunately, suffer from similar problems.

In recent years, many extensions to LOMs have been proposed, including 
extensions to 3D, more efficient computational models, denser feature 
points, and improvements to generalization (i.e. dealing with 
intra-class object variations). The goal of this one-day workshop is to 
provide a forum for the presentation and discussion of recent ideas and 
results as well as an overview of the state of the art in LOMs.

Prospective participants are invited to submit papers describing 
high-quality, original research to the workshop. Relevant topics include 
(but are not limited to):

     * Non-rigid object tracking
     * Non-rigid structure from motion
     * Extensions and improvements to optimization methods
     * Generalised object vs. specific object models
     * Machine learning methods for alignment
     * Applications of non-rigid registration and tracking, e.g. 
detection and recognition,
     * Non-traditional applications (e.g. not faces or medical images)
     * Employing offline 3D data to aid in 2D registration / tracking.
     * Alternate representations for improved registration / tracking 
(e.g. filter-based, patch-based, sparse representations).

PAPER SUBMISSION

All submissions will be handled electronically. Submission instructions 
are available on the Submission webpage 
(http://express.hid.ri.cmu.edu/NRTL2007/submission.html). Reviewing will 
be double-blind. Each submitted paper will be reviewed by at least two 
members of the international program committee. Please note that for 
ICCV 2007, double submissions to ICCV 2007 workshops and the main 
conference will be allowed (but not to any other conference, workshop or 
journal). In case of acceptance to both, the author(s) will have to 
decide where the paper should appear (main conference or workshop).

Accepted papers will be published in the ICCV 2007 CD-ROM Proceedings. 
Submitted papers may have a maximum length of 8 pages and must adhere to 
the same ICCV 2007 layout specifications as papers submitted to the main 
conference. Prospective authors should read the instructions for 
formatting, double-blind review and dual submission carefully, and are 
strongly encouraged to make use of the Latex and Word template files 
provided at the ICCV 2007 Submission webpage.

IMPORTANT DATES

Paper submission:    22 June 2007
Notification:        20 July 2007
Camera-ready papers: 27 July 2007
Workshop:            14 October 2007

ORGANISATION

Workshop Co-Chairs
     Roland Goecke, Simon Lucey, Iain Matthews

Program committee
     Shai Avidan, MERL
     Simon Baker, Microsoft Research
     Volker Blanz, University of Siegen
     Tim Cootes, University of Manchester
     David Cristinacce, University of Manchester
     Clinton Fookes, Qeensland University of Technology
     Ralph Gross, Carnegie Mellon University
     Xiaoming Liu, GE
     Dimitris Metaxas, Rutgers University
     Sami Romdhani, University of Basel
     Fernando de la Torre, Carnegie Mellon University
     Jing Xiao, Epson R&D, Inc.


Regards,

Roland, Simon and Iain