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...
0123

Notice

AISB event Bulletin Item

CFP: Online Learning for Classification, CVPR 2007


Online Learning for Classification Workshop, CVPR 2007


OLC workshop will bring together computer vision researchers interested in providing solid foundations to this promising and challenging area. There will be an OLC Challenge with a benchmark classification data as an extension of this workshop in 2008. The topics of interest include:
Online methods for automatic object detection and tracking,

Active learning for object identification and recognition,

Incremental fusion of multi-modal data for classification tasks,

Online and adaptive event detection,

Applications using online classification methods, and

Theoretical characterizations and various forms of performance bounds.

In addition, we encourage work towards a solid framework for benchmarking OLC algorithms.



Rationale:
Online learning for classification is becoming essential for many real-world vision tasks. Amount of the available training data is increasingly rapidly, which makes the offline training times much longer, sometimes up to weeks. Online algorithms process one example at a time, thus, such methods are more adequate for large data sets. The performance of most offline classification methods is bounded with the amount of the priori information at the beginning since they assume the learner plays no role in obtaining information about the unknown classes. However, online algorithms can adapt to new information. In conventional methods, the training samples are simply drawn independently from some probability distribution. On the other hand, recent online works show more powerful oracles. Offline methods imply that the training and testing are separate steps. To our advantage, training the classifier online as new data arrives enables combining these stages.



Submission deadlines:

Submission of full paper:          April 5th, 2007

Notification of acceptance:      April 15th, 2007

Camera ready:                          April 25th, 2007

Workshop:                                 June 18, 2007



You can submit full papers (formatted using the CVPR style files) at OLA submission website. Reviews will be double-blind according to CVPR guidelines.

 

Organizers:

Fatih Porikli, MERL

Matthew Brand, MERL



Program Committee:

Ahmed Elgammal, Rutgers University

Andrew Zisserman, Univ. Oxford

Aaron F. Bobick, Georgia Tech

Baback Moghaddam, MERL

Carlo Regazzoni, Univ. Genoa

Chris Wren, MERL

Daniel Gatica-Perez, IDIAP

David Kriegman, UCSD

Horst Bischof, TU-Gratz

James Clark, McGill University

James Ferryman, Univ. of Reading

James Rehg, Georgia Tech

Larry Davis, Univ. Maryland

Mubarak Shah, Univ. Central Florida

Peter Meer, Rutgers University

Philip Torr, Univ. Oxford

Rama Chellappa, Univ. Maryland

Shai Avidan, MERL

Stuart Russell, UC Berkeley

Swarup Medasani, HRL

Tsuhan Chen, Carnegie-Mellon

Yuri Ivanov, MERL