Parsing Objects and Scenes in Two- and Three-Dimensions
Alan Yuille, Professor & Investigator, UCLA
Date: Friday, May 16, 2014
Time: 4:00 PM to 5:30 PM Note: all times are in the Eastern Time Zone
Location: Singleton Auditorium, MIT Bldg 46-3002
Host: Prof. Tomaso A. Poggio
Contact: Neelum Wong, email@example.com
Speaker URL: None
TALK: Parsing Objects and Scenes in Two- and Three-Dimensions
This talk is part of the Brains, Minds & Machines Seminar Series 2013-2014.
This talk presents three recent studies on detecting and parsing objects and scenes and discusses how they contribute to the Center for Brains, Minds and Machines (CBMM) research questions. We first address the "what?" problem of detecting animals and animal parts (in a newly labelled dataset) and show the advantages of part-sharing (X. Chen et al. 2014). Next, within the same "what?" problem, we describe an approach to parse humans and estimate their three-dimensional structure from single images (C. Chen et al. CVPR 2014). Finally, we describe "psychophysics in the wild" for rapid detection of objects in complex scenes in a newly labelled dataset (Y. Li et al, CVPR 2014). We conclude discussing how these approaches should be extended to meet the CBMM challenge and other efforts at CBMM.
Created by Neelum Wong at Monday, May 12, 2014 at 4:32 PM.