2007 IEEE
International Workshop on
Analysis and Modeling of Faces
and Gestures (AMFG)
October 20, 2007
Rio de Janeiro, Brazil
(in conjunction with ICCV 2007)
1. Face Recognition in the Industry: State of the Art and Current Challenges
Frank Weber
Director of Algorithm Development, Cognitec Systems GmbH,
Grossenhainer Str. 101, D-01127 Dresden, Germany
Abstract
An overview of the state of the art in face recognition in the industry
is given. Then some typical application scenarios such as search in
large portrait photo databases, photo indexing, and video surveillance
are presented, and their particular technical challenges are discussed.
Speaker Bio
Frank Weber received the diploma degree in computer science from
University of Bonn, Germany, in 1992. He then worked at GMD German
National Research Center for Information Technology (now part of the
Fraunhofer-Gesellschaft) in the field of artificial neural networks,
applied to control tasks and optimal design of experiments. In 1996, he
joined Siemens Nixdorf Advanced Technologies GmbH and started working on
the development of face recognition algorithms. He has been continuing
that work until today, and he has been one of the main developers of
those algorithms forming the core of the FaceVACS technology. Currently,
he heads the algorithm development group of Cognitec Systems GmbH.
2. Human Movement and Activity Analysis - Beyond Trajectories
Larry Davis
Chair of Computer Science Department, University of
Maryland; ICCV 2007 general chair
Abstract
Research on human movement and activity analysis in computer vision has
emphasized the recovery of trajectories –of body parts for movement
analysis and of people through the world for activity analysis. In this
talk, I will discuss two projects at the University of Maryland that
look “beyond” trajectories for movement and activity analysis.
Humans are highly adept at executing movements associated with everyday activities. The movements are fast and efficient. The high speeds result in impulsive propulsion, with characteristic acceleration and deceleration phases. Such movements are called "Ballistic" due to their impulsive nature, and include reaches and strikes. These movements are most commonly used for interacting with objects and the environment. We describe a Bayesian approach for visual analysis of ballistic hand movements. One of the key challenges to recognizing them is the variability of the target-location of the hand~- people can reach above their heads, for something on the floor, etc. Our approach recognizes them independent of the movement's target-location and direction by modeling the ballistic dynamics. A video sequence is automatically segmented into ballistic subsequences without tracking the hands. The segments are then classified into strike and reach movements based on low-level motion features. Each ballistic segment is further analyzed to compute qualitative labels for the movement's target-location and direction. Tests are presented with a set of reach and strike movement sequences.
Visibility in architectural layouts
affects human navigation, so a suitable representation of visibility
context is useful in understanding human activity. Motivated by studies
of spatial behavior, we use a set of features from visibility analysis
to represent spatial context in the interpretation of human activity. An
agent’s goal, belief about the world, trajectory and visible layout are
considered to be random variables that evolve with time during the
agent’s movement, and are modeled in a Bayesian framework. We design a
search-based task in a sprite-world, and compare the results of our
framework to those of human subject experiments. Our findings confirm
that knowledge of spatial layout improves human interpretations of the
trajectories (implying that visibility context is useful in this task).
Since our framework demonstrates performance close to that of human
subjects with knowledge of spatial layout, our findings confirm that our
model makes adequate use of visibility context. In addition, the
representation we use for visibility context allows our model to
generalize well when presented with new scenes.
Speaker Bio
Larry S. Davis received
his B.A. from Colgate University in 1970 and his M. S. and Ph. D. in
Computer Science from the University of Maryland in 1974 and 1976
respectively. From 1977-1981 he was an Assistant Professor in the
Department of Computer Science at the University of Texas, Austin. He
returned to the University of Maryland as an Associate Professor in
1981. From 1985-1994 he was the Director of the University of Maryland
Institute for Advanced Computer Studies. He is currently a Professor in
the Institute and the Computer Science Department, as well as Chair of
the Computer Science Department. He was named a Fellow of the IEEE in
1997.
Prof. Davis is known for his research in computer vision and high
performance computing. He has published over 100 papers in journals and
has supervised over 20 Ph. D. students. He is an Associate Editor of the
International Journal of Computer Vision and an area editor for Computer
Models for Image Processing: Image Understanding. He has served as
program or general chair for most of the field's major conferences and
workshops, including the 5’th International Conference on Computer
Vision, the 2004 Computer Vision and Pattern Recognition Conference, and
the 11’th International Conference on Computer Vision.
