It is well known that relationships between data points (i.e., context) in structured data can be exploited to obtain better recognition performance. In our recent work, we have explored a different, but related, problem: how can these inter-relationships be used to efficiently learn and continuously update a recognition model, with minimal human labeling effort. Towards this goal, we have proposed an active learning framework to select an optimal subset of data points for manual labeling by exploiting the relationships between them, which will be the focus of the first part of the talk. We will show how information theoretic measures, using ideas of entropy, mutual information and typicality, can be used to identify the optimal subsets. In the second part, we will demonstrate how context can be exploited in a camera network for target re-identification, even as the camera network topology can change over time. This is a critical step towards addressing open world dynamic camera network scenarios, which is only starting to receive interest in the research community.
Amit Roy-Chowdhury received his PhD from the University of Maryland, College Park in Electrical and Computer Engineering in 2002 and joined the University of California, Riverside in 2003 where he is a Professor of Electrical and Computer Engineering and a Cooperating Faculty in the department of Computer Science and Engineering. He leads the Video Computing Group at UCR, with research interests in computer vision, image processing, pattern recognition, and statistical signal processing. Prof. Roy-Chowdhury's research has been supported by various agencies including the NSF, DoD, IARPA, NEH, and private industries like Google, NVDIA, and CISCO. He has published over 150 papers in peer-reviewed journals and top conferences. He is the first author of the book Camera Networks: The Acquisition and Analysis of Videos Over Wide Areas, the first monograph on the topic. He is a Fellow of the IAPR.