Speaker | Prof. Shimon Ullman |
Affiliation | Weizmann Institute |
Date and Time | Oct. 6, 2009, 10:15 p.m. - Nov. 3, 2009, 11:15 p.m. |
Location | Singleton Auditorium, Bldg 46 Room 3002 |
The first two talks will be on 'classification', the next two on 'beyond'. The first part will examine visual recognition at different levels: natural classes, individual objects, as well as their parts and sub-parts at multiple levels. Related issues will include object segmentation, and the integration of bottom-up with top-down processing in recognition. The second part will discuss the use of vision to understand the world beyond the recognition of single objects, for example, people's actions and goals. Current methods for object classification are insufficient for dealing with broader aspects of visual interpretations. These limitations will be examined, and some extensions and future directions will be outlined.
There will be four talks in this series:
Additional readings:
Learning model complexity in an online environment, Dan Levi, Shimon Ullman, CRV 2009
Combined Top-Down/Bottom-Up Segmentation, Eran Borenstein and Shimon Ullman, IEEE Transactions on Pattern Analysis And Machine Intelligence, Vol. 30, No. 12, December 2008
Feature Hierarchies for Object Classification, Boris Epshtein and Shimon Ullman, ICCV 2005 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) 1550-5499/05
Mutual information of image fragments predicts categorization in humans: Electrophysiological and behavioral evidence, Assaf Harel, Shimon Ullman, Boris Epshtein, Shlomo Bentin, Vision Research, 47 (2007) 2010–2020m March 28, 2007, doi:10.1016/j.visres.2007.04.004
Distinctive and compact features, Ayelet Akselrod-Ballin, Shimon Ullman, Image and Vision Computing, 2008, 26 (9), p.1269-1276, Sep 2008, doi:10.1016/ j.imavis.2008.03.005
Class Information Predicts Activation by Object Fragments in Human Object Areas, Yulia Lerner1, Boris Epshtein1, Shimon Ullman1, and Rafael Malach,Journal of Cognitive Neuroscience 20:7, pp. 1–18 MIT, 2008
Visual features of intermediate complexity and their use in classification, Shimon Ullman, Michel Vidal-Naquet & Erez Sali, Nature Neuroscience, 5, 682 - 687 (2002), doi:10.1038/nn870
Semantic Hierarchies for Recognizing Objects and Parts, Boris Epshtein, Shimon Ullman
Class-Specific, Top-Down Segmentation, Eran Borenstein and Shimon Ullman, ECCV 2002, LNCS 2351, pp. 109 - 122, 2002
Object recognition and segmentation by a fragment-based hierarchy, Shimon Ullman, Trends in Cognitive Sciences, Vol.11 No.2, 2007
Unsupervised Feature Optimization (UFO): simultaneous selection of multiple features with their detection parameters, Leonid Karlinsky Michael Dinerstein Shimon Ullman, 2009
Image interpretation by a single bottom-up top-down cycle, Boris Epshtein, Ita Lifshitz, and Shimon Ullman, PNAS, vol. 105, no. 38 14298-14303, July 2008
This lecture series is part of the Brains and Machines Seminar Series 2009, and is sponsored by Intelligence Initiative (I²)
Center for Biological & Computational Learning (CBCL)
http://cbcl.mit.edu/
There are no comments yet
Post a new comment...