Conferences, Lectures, & Seminars
Events for November
-
Special Seminar: Can Distributed Local Saliency Computations Solve the Feature Binding
Wed, Nov 02, 2005 @ 03:00 PM - 04:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
TITLE: Can Distributed Local Saliency Computations Solve the Feature Binding
Problem?John K. TsotsosYork University, Toronto, Canada
Director, Center for Vision Research
Professor, Department of Computer Science & Engineering
Canada Research Chair in Computational VisionHOST: Laurent itti Abstract:
Computational vision has a long history of proposing methods for
decomposing a visual signal into components. For example, many good
strategies have appeared for decomposing visual motion signals (such as
Heeger, Sperling). What has been far more elusive is how to recombine
those components into a whole. This problem has even merited its own name
- the binding problem. To date no realizable process has appeared to solve
the binding problem, even in part, although several proposals have
appeared. This paper proposes a novel solution for a significant portion
of the binding problem, namely, the re-combination of visual features into
larger patterns and their localization in the image. The solution requires
the abandonment of the nearly ubiquitous saliency map and adoption of a
distributed, localized computation of saliency that is dependent on local
neural selectivity constraints. This strategy is demonstrated within a
fully implemented model that attends to simple motion patterns in image
sequences.
-------------------------------------------------Location: Hedco Neurosciences Building (HNB) - -107
Audiences: Everyone Is Invited
Contact: Vishal Thakkar
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
Neurobotics: An Interdisciplinary Approach to Understanding and Assisting Humans
Tue, Nov 29, 2005 @ 03:00 PM - 04:30 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker
Yoky Matsuoka
http://www.ri.cmu.edu/people/matsuoka_yoky.htmlAbstractNeurobotics is a new field that lies at the intersection of Robotics and Neuroscience. Neurobotics is currently a small community but is growing rapidly in both engineering and science. In the Neurobotics Laboratory at Carnegie Mellon University, robotic models and environments are used to understand the biomechanics and neuromuscular control of human limbs. In parallel, robotic systems are developed to augment, replace and rehabilitate damaged sensorimotor functions. In this talk, an overview of the Neurobotics Lab is presented and two example projects are addressed in more detail. First, the Anatomically Correct Testbed (ACT) Hand, a prototype of a seamlessly integrated prosthetic hand, is introduced. A description of how the ACT Hand is used to understand the neural control strategy of the high-degree-of-freedom redundant human hand will follow. As a second example, a robotic rehabilitation environment with distorted feedback is presented. To enrich this therapeutic environment, a patientÕs adaptation and other neuromuscular states are monitored using a dynamic system identification technique, and a safe whole-body interaction environment is constructed. Finally, there will be a brief description of the Neurobotics Lab outreach and educational programs for minority and disabled students.Short BiographyProfessor Yoky Matsuoka is an Anna Loomis McCandless Assistant Professor in the Robotics Institute, Mechanical Engineering, Biomedical Engineering, and the Center for the Neural Basis of Cognition at Carnegie Mellon University. She is also a Clinical Assistant Professor in the Department of Physical Medicine and Rehabilitation at the University of Pittsburgh. She received her Ph.D. at MIT in Electrical Engineering and Computer Science in the fields of Artificial Intelligence and Computational Neuroscience in 1998. She received an M.S. from MIT in 1995 and a B.S. from UC Berkeley in 1993, both in EECS. Prior to joining CMU, she was a Postdoctoral Fellow in the Brain and Cognitive Sciences Department at MIT and in Mechanical Engineering at Harvard University. Her work at CMU earned a Presidential Early Career Award for Scientists and Engineers in 2004, Anna Loomis McCandless Chair in 2004, and IEEE Robotics and Automation Society Early Academic Career Award in 2005.
Location: Hedco Neurosciences Building (HNB) - 107
Audiences: Everyone Is Invited
Contact: Nancy Levien
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
Model-Based Face Analysis
Wed, Nov 30, 2005 @ 01:00 PM - 02:30 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Model-Based Face AnalysisSimon Baker, Research Scientist
Robotics Institute, Carnegie Mellon University, Pittsburgh, PA1:00- 2:30 pm
November 30, 2005
OHE Studio CAbstract:A face model is a mapping from a set of parameters to an image of a face. The most well-known face models are Active Appearance Models and 3D Morphable Models. Computer vision applications of face models include head pose estimation for user interfaces, gaze estimation, pose normalization for face recognition, lip-reading, expression recognition, and face coding for low bandwidth video-conferencing. In all of these applications, the key task is to fit the face model to an input image; i.e. to find the parameters of the model that match the input image as well as possible.In this talk I will describe how face model fitting, a non-linear optimization, can be posed as an image alignment problem. Image alignment is a standard computer vision technique, with applications to optical flow, tracking, mosaic construction, layered scene representations, and medical image registration. I will describe an efficient image alignment algorithm and show how it relates to others in a unifying framework. Applying our algorithm to faces results in real time 2D, 3D, and multi-view face model fitting algorithms.
Bio:
Simon Baker is a Research Scientist in the Robotics Institute at Carnegie Mellon University where he conducts research in Computer Vision. Before joining the Robotics Institute in September 1998, he was a Graduate Research Assistant at Columbia University, where he obtained his Ph.D. in the Department of Computer Science. He also spent a summer visiting the Vision Technology Group at Microsoft Research. He received a B.A. in Mathmematics from Trinity College, Cambridge University in 1991, a M.Sc. in Computer Science from the University of Edinburgh in 1992, and a M.S. in Mathematics from Trinity College, Cambridge University in 1995. His current research interests include: face analysis (recognition, tracking, model building, and resolution enhancement), 3D reconstruction and vision/graphics, vision theory, vision for automotive applications, and projector-camera systems. For more details of his research, see his webpage: http://www.ri.cmu.edu/people/baker_simon.html
List Host: Dr. Gerard Medioni
Location: Olin Hall of Engineering (OHE) - Studio C
Audiences: Everyone Is Invited
Contact: Nancy Levien
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor.