Hi,<div><br></div><div>I am Herbert from the ECE department. We have invited Prof. Amit Roy-Chowdhury from UC Riverside to give a talk on human-machine collaboration for visual scene understanding. We think that this talk might be of interest to some of you.</div><div><br></div><div>Forwarded below please find the talk information.</div><div><br></div><div>Best,</div><div>Herbert<br><br>---------- Forwarded message ----------<br>From: <b>Joelle Dohrman</b> <<a href="javascript:_e(%7B%7D,'cvml','cao-admin@ece.ucsb.edu');" target="_blank">cao-admin@ece.ucsb.edu</a>><br>Date: Friday, June 3, 2016<br>Subject: [Seminar] Jun 6 (Mon): "Human-Machine Collaboration for Visual Scene ..., " Dr. Amit K. Roy-Chowdhury,<br>To: <a href="javascript:_e(%7B%7D,'cvml','seminar@ece.ucsb.edu');" target="_blank">seminar@ece.ucsb.edu</a><br><br><br>
<div bgcolor="#FFFFFF" text="#000000">
<hr size="2" width="100%">
<h1 align="center"><font color="#000066" face="Apple Braille">Human-Machine
Collaboration for Visual Scene Understanding</font></h1>
<hr size="2" width="100%">
<div>
<div align="center"><font face="Apple Braille">Dr. Amit K.
Roy-Chowdhury, Professor, ECE/CS, UC Riverside</font><br>
<font face="Apple Braille">Jun 6 (Mon) 3:00pm</font><br>
<font face="Apple Braille">Building 406, Room 216
</font><br>
</div>
<font face="Apple Braille"><br>
<u>ABSTRACT:</u><br>
Most computer vision methods work by having an initial,
labor-intensive training phase, followed by an operational phase
where the trained models are used. However, in many
applications, all the data may not be available at the outset
and the learned models need to be adapted continuously as new
data becomes available. This requires continuous learning
methods in visual scene understanding, where humans and the
machine vision system are working together collaboratively. In
this talk, we address some of the research issues that arise in
such a framework. First, we focus on active learning methods and
how they can be used for continuously updating learned models by
interacting with a human operator. We show results in object,
activity and scene recognition and show that results similar to
methods with a priori trained models can be obtained with
significantly less manual labeling. Second, we consider the
problem of summarizing large volumes of video data to present to
the human in a manner that allows efficient decision making
without being overwhelmed by the size of the data.
<br>
<br>
<u>BIO:</u><br>
Amit K. Roy-Chowdhury received Masters degree in systems science
and automation from the Indian Institute of Science, Bangalore,
India, and the Ph.D. degree in electrical engineering from the
University of Maryland, College Park. He is a Professor of
Electrical Engineering and a Cooperating Faculty in the
Department of Computer Science at the University of California,
Riverside. His broad research interests include the areas of
image processing and analysis, computer vision, and statistical
signal processing and pattern recognition. Together with his
students and collaborators, he has over 100 technical
publications in these areas. He is the first author of the book
- Camera Networks: The Acquisition and Analysis of Videos over
Wide Areas - the first research monograph on this topic. He has
been on the organizing and program committees of multiple
computer vision and image processing conferences and is serving
on the editorial boards of multiple journals in related areas.
<br>
<br>
</font>
<div align="center"><font face="Apple Braille">Hosted by: Dr.
Yasamin Mostofi II Submitted by: Arjun Muralidharan
<a><arjunm@ece.ucsb.edu></a>
</font><br>
</div>
<br>
</div>
<br>
</div>
<br></div>