Program

09.00Opening
09.15Invited talk: Silvio Savarese (University of Michigan) Understanding human interactions from videos
10.15Coffee break
10:45Online Social Behavior Modeling for Multi-Target TrackingShu Zhang and Amit Roy-Chowdhury
11:15Learning to Detect Carried Objects with Minimal SupervisionRadu Dondera, Vlad Morariu and Larry Davis
11:45Semi-parametric Scan Statistic for Unsupervised Abnormal Crowd Activity DetectionYang Hu, Yangmuzi Zhang and Larry Davis
12.15Lunch Break
14.00 Invited talk: Amit Roy-Chowdhury (University of California Riverside) Context in Video Analysis
15.00 Using 3D Models to Recognize 2D Faces in the Wild Iacopo Masi, Andrew Bagdanov, Giuseppe Lisanti, Alberto Del Bimbo and Pietro Pala
15.30 Coffee break
16.00 Dynamic Multi-Vehicle Detection and Tracking from a Moving Platform Chung-Ching Lin and Marilyn Wolf
16.30MultiClass Object ClassiŞcation in Video Surveillance Systems - An Experimental StudyMohamed Elhoseiny, Amr Bakry and Ahmed Elgammal
17.00 Discussion
17:15 Closing

Invited Speakers

Silvio Savarese (University of Michigan)

He is the director of the Computer Vision Group at the University of Michigan. His group explores a number of critical problems in the area of computer vision. We focus on the analysis and modeling of visual scenes from static images as well as video sequences. His research goals include: i) the semantic understanding of materials, objects, and actions within a scene; ii) modeling the spatial organization and layout of the scene and its behavior in time. His group develops algorithms that enable the design of machines that can perform real-world visual tasks such as autonomous navigation, visual surveillance, or content-based image and video indexing. His research is sponsored by US government agencies such as NSF and Navy as well as industrial partners such as Ford, Toyota, Google, TWR and KLA-Tencor.

Amit Roy-Chowdhury (University of California Riverside)

Dr. Roy-Chowdhury leads the Video Computing Group at UCR. His group is involved in research projects related to camera networks, human behavior modeling, face recognition, and bioimage anaysis. Application domains include national and homeland security, commercial multimedia, home infrastructure, computational biology, and digital arts. The underlying approach of his research is to harness various methods in systems theory, signal processing, machine learning, mathematics and statistics to the analysis of images and videos in order to obtain an understanding of their content. This scientific understanding can lead to machine vision technologies that can provide an automated/semi-automated analysis of the 3D environment from images/videos, analogous to the capabilities of biological visual systems. Prof. Roy-Chowdhury's research has been supported by various agencies including the National Science Foundation, Office of Naval Research, Army Research Office, DARPA, National Endowment for the Humanities, and private industries like CISCO and Lockheed-Martin. His recent book on Camera Networks, the first monograph on the topic, provides an overview of current research in the field.