From Image Analysis to Content Extraction: Are We There Yet? 6/22
IEEE Signal Processing Society Distinguished Lecture
1:30 p.m., 402 Walter Library.
Tsuhan Chen, Department of Electrical and Computer Engineering, Carnegie Mellon University
Based on the bag-of-words representation, topic models have recently become a popular approach to object discovery, i.e., extracting the "object of interest" from a set of images in a completely unsupervised manner. The talk will outline this approach, and extend it from still images to motion videos.