| We are pleased to invite you to the following seminar talk jointly organized by Pattern Recognition and Machine Intelligence Association (PREMIA) and Singapre-MIT Alliance Computer Science (SMACS): |
| Learning Three-Dimensional Shape Models for Objects (joint work with Prof. Leslie Kaelbling, MIT) |
Prof. Tomas Lozano-Perez
Department of Electrical Engineering and Computer Science, MIT and
Computer Science and Artificial Intelligence Laboratory, MIT |
| |
| Date: Friday, 22/10/2004 |
| Time: 3.00 pm - 4.00 pm |
| Venue: Lecture Theatre 19A (LT19A), NTU.
For those traveling by car, the lecture theatre is accessible from Car Park A (Pay Car Park, entry by Cashcard) which is located at Level 1 of the North Spine of NTU. The car park entrance is opposite the Administration Building.
An interactive location map is available here.
|
| |
| Admission: Admission is free |
Registration: Please register online via http://www.premia-sg.org/index.php?option=com_events&event_id=2&task=register
(Registration is closed now). |
Synopsis:
This talk introduces a representation for generative models of the gross three-dimensional structure of classes of objects in terms of the spatial relationships among their parts. We show how this representation naturally leads to a recognition algorithm and demonstrate its use in interpreting sketches of objects and also uncluttered images.
Please register your attendance by 20 Oct 2004, Wednesday. |
Biography:
Prof. Tomas Lozano-Perez is the TIBCO Professor of Computer Science and Engineering at MIT, where he is a member of the Computer Science and Artificial Intelligence Laboratory. Professor Lozano-Perez has all his degrees (SB '73, SM '76, PhD '80) from MIT in Computer Science. He has been Associate Director of the Computer Science and Artificial Intelligence Laboratory and Associate Head for Computer Science of MIT's Department of Electrical Engineering and Computer Science. Professor Lozano-Perez's research has been in robotics (configuration-space approach to motion planning), computer vision (interpretation-tree approach to object recognition), machine learning (multiple-instance learning), medical imaging (computer-assisted surgery) and computational chemistry (drug activity prediction and protein structure determination from NNR & X-ray data).
Prof. Tomas Lozano-Perez's homepage is at http://www.ai.mit.edu/people/tlp/tlp.html. |
