[Colloquium] TTIC Talk: Leo Zhu, MIT

[Julia MacGlashan]

*REMINDER*

When:             *Thursday, May 27 @ 11:00am
*

Where:           * TTIC Conference Room #526*, 6045 S Kenwood Ave, 5th Floor


Who:              * **Leo Zhu*, MIT


Title:          *      **Recursive Compositional Models for Computer Vision*
******



 Recursive compositional models (RCMs) are hierarchical models which enable
us to represent the shape/geometry and visual appearance of objects and
images at different scales. The key design principle is recursive
compositionality. Objects are represented by RCMs in a hierarchical form
where complex structures are composed of more elementary structures.
Formally, they are represented by probability distributions defined over
graphs with variable topology. Learning techniques are used to learn these
models from a limited number of examples of the object by exploiting the
recursive structure. In addition, we can exploit this structure to develop
algorithms that can perform inference on these RCMs to rapidly detect and
recognize objects. This differs from more standard ”flat models” of objects
which have much less representational power if they wish to maintain
efficient learning and inference. RCMs give a rich hierarchical description
of objects and images and can be applied to a range of tasks including
object detection, segmentation, parsing and image parsing.

Host:              Greg Shakhnarovich, greg at ttic.edu
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20100526/bae30fbd/attachment.htm