Bishop and AI news

Stephen Hawking thinks computers may surpass human intelligence and take over the world. This view is based on the ideology that all aspects of human mentality will eventually be realised by a program running on a suitable compu...


Connection Science

All individual members of The Society for the Study of Artificial Intelligence and Simulation of Behaviour have a personal subscription to the Taylor Francis journal Connection Science as part of their membership. How to Acce...


Al-Rifaie on BBC

AISB Committee member and Research Fellow at Goldsmiths, University of London, Dr Mohammad Majid al-Rifaie was interviewed by the BBC (in Farsi) along with his colleague Mohammad Ali Javaheri Javid on the 6 November 2014. He was a...


Rose wins the Loebne...

After 2 hours of judging at Bletchley Park, 'Rose' by Bruce Wilcox was declared the winner of the Loebner Prize 2014, held in conjunction with the AISB.  The event was well attended, film live by Sky News and the special guest jud...


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...


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...


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...


AISB YouTube Channel

The AISB has launched a YouTube channel: ( The channel currently holds a number of videos from the AISB 2010 Convention. Videos include the AISB round t...



AISB event Bulletin Item

CFP: Workshop on 3D Representation for Recognition (3dRR-07)


Workshop on 3D Representation for Recognition (3dRR-07)   

(in conjunction with ICCV 2007, Rio de Janeiro, Brasil)

Deadline for paper submission: June 15th, 2007  

Object and scene categorization has been a central topic of computer 
vision research in recent years. The problem is a highly challenging one. 
A single object or scene may show tremendous variability in appearance and 
structure under various photometric and geometric conditions. In addition, 
members of the same class may differ from each other due to various 
degrees of intra-class variability.

Recently, researchers have proposed new powerful models as well as 
sophisticated mathematical tools for handling object and scene class 
recognition. However, much work still needs to be done towards the goal 
of: i) finding a suitable representation that can efficiently capture the 
three-dimensional nature of objects and scenes; ii) taking  advantage of 
this representation to help the recognition task.

This workshop represents a great opportunity for bringing together experts 
from multiple areas of computer vision (3D reconstruction, recognition, 
etc.) and providing a common playground for a stimulating debate.  We are 
soliciting original contributions which can provide both theoretical and 
experimental insight on this fundamental problem. Specific questions we 
would like to address include, but are not  limited, to:

- What are suitable representations of the 3D geometry of object instances 
or classes which can be exploited for recognition?

Reconstruction and Recognition:
- Can recognition and reconstruction be run simultaneously to enhance each 
- How much does 3D information help? How detailed does the 3D
representation need to be in order to achieve satisfactory recognition?

Spatial constraints and contextual recognition:
- How can we use/explore different degrees of 3D spatial constraints (e.g. 
ground plane) for recognition?  
- Can we expand known 2D spatial models (e.g. constellation models) to 3D?
- How can 3D spatial constraints be used for joint recognition of scenes 
and the objects within?

Human vision:
- What can we learn from what we know about our own visual system? How do 
we represent a 3D object or environment in our brain? Can this inspire 
computational work?

- Leonardo da Vinci used to say that for a painting to look right its (3D) 
geometry had to be right. But Drer did not agree. Who is right?  
- Cubist art demonstrates that incorrect 3D geometry does not impair our 
capability of recognizing objects in paintings. Can cubism inspire us to 
find minimal geometric models for recognition?

Accepted papers will be published in the ICCV 2007 CD-ROM Proceedings. A 
prize will be awarded to the best paper of the workshop. The prize is 
sponsored by Microsoft Research Redmond. Double submissions to 3dRR-07 
workshop and the main ICCV07 conference are allowed (but not to any other 
conference, workshop or journal). In case of acceptance to both, the 
authors will have to decide where the paper should appear (that is, main 
conference or workshop).

Submitted papers must have a maximum length of 8 pages and must adhere to 
the same ICCV 2007 layout specifications as papers submitted to the main 
conference (except for the summary page). Please refer to ICCV 2007 
relevant webpage for instructions on the submission format.

For any additional information please refer to:

Important dates:

Deadline for paper submission           June 15th, 2007  
Notification of acceptance              July 27th 2007  
Camera-ready copies due to              Aug (Parallel to ICCV)
Workshop date                           October 20th, 2007

Organizing Committee:  

 Silvio Savarese, University of Illinois at Urbana-Champaign
 Tinne Tuytelaars, K.U. Leuven
 Antonio Criminisi, Microsoft Research
 Fei-Fei Li, Princeton University

Program Committee:

M. Brown, Microsoft Research
R. Cipolla, University of Cambridge
A. Efros, Carnegie Mellon University
V. Ferrari, Oxford University  
D. Hoiem, Carnegie Mellon University
S. Lazebnik, University of Illinois at Urbana Champaign
B. Leibe, ETH Zurich
D. Lowe, University of British Columbia
D. Metaxas, Rutgers
P. Moreels, CalTech
V. Pavlovic, Rutgers
P. Perona, CalTech
E. Sudderth, UC Berkeley
S. Todorovic, University of Illinois at Urbana Champaign
L. Van Gool, ETH Zurich and K.U. Leuven
J. Winn, Microsoft Research