Event Location: NSH 1507
Bio: Jianbo Shi studied Computer Science and Mathematics as an undergraduate
at Cornell University where he received his B.A. in 1994. He received
his Ph.D. degree in Computer Science from University of California at
Berkeley in 1998, for his thesis on Normalize Cuts image segmentation
algorithm. He joined The Robotics Institute at Carnegie Mellon
University in 1999 as a research faculty, where he led the Human
Identification at Distance(HumanID) project, developing vision
techniques for human identification and activity inference. In January
2003, he joined the Department of Computer & Information Science at
University of Pennsylvania where he is currently an Associate Professor.

Abstract: We introduce a method for ‘packing’ salient image contours/segments into
recognizable object shapes. A key distinction of our approach is that we
use long, salient, bottom-up image contours to learn object shape, and
to achieve object detection with the learned shape. Most learning
methods rely on one-to-one matching of contours to a model. However,
bottom-up image contours often fragment unpredictably. We resolve this
difficulty by using many-to-one matching of image contours to a model.

In operation, our system achieves three goals: it locates an object,
identifies its parts, and segments out its contours. To learn a
descriptive object shape model, we combine bottom-up contours from a few
representative images. The goal is to allow most of the contours in the
training images to be many-to-one matched to the model. For detection,
our challenges are inferring the object contours and part locations, in
addition to object location. Because the locations of object parts and
matches of contours are not annotated, they appear as latent variables
during training. We use the latent SVM learning formulation to
discriminatively tune the many-to-one matching score using the
max-margin criterion.

There are several computational implementations, using Linear
Programming (LP) or Semi-Definite Programming (SDP). We evaluate on the
challenging ETHZ shape categories dataset and outperform all existing
methods.

This is joint work with Qihui Zhu, Praveen Srinivasan, Liming Wang, Yang
Wu.