Keynote Speakers
Giving Interaction a Hand – Deep Models of Co-speech Gesture in Multimodal Systems
Prof. Stefan Kopp
Sociable Agents Group, Bielefeld University, Germany
Humans frequently join words and gestures in multimodal communication. Such natural co-speech gesturing goes far beyond what currently can be processed by gesture-based interfaces, and especially its coordination with speech still poses open challenges for basic research and multimodal interfaces alike. How can we develop computational models for processing and generating natural speech-gesture behavior, in a flexible, fast and adaptive manner similar to humans? In this talk I will review approaches and methods applied to this problem. I will argue that those models need to (and can) be based on a deeper understanding of what shapes co-speech gesturing in a particular situation. In particular, I will present work that connects empirical analyses with computational modeling and evaluation to unravel the cognitive, embodied and socio-interactional mechanisms underlying the use of speech-accompanying gestural behavior, and to develop deeper models of these mechanisms for interactive systems such as virtual characters, humanoid robots, or multimodal interfaces.
Stefan Kopp is professor of Computer Science at
Bielefeld University, head of the "Sociable Agents" research group
at the DFG Center of Excellence "Cognitive Interaction Technology"
(CITEC) and deputy coordinator of a DFG collaborative research
center on "Alignment in Communication". His research centers around
the question how artificial systems can turn into intuitive,
socially adept interaction partners (either virtual or robotic). For
this, his groups develops empirically grounded, cognitively
plausible models of verbal and nonverbal socio-communicative
behavior. Current projects focus on versatile multimodality using
speech and gesture, the dynamics of interpersonal coordination and
adaptation in dialogue, and embodied architectures that ground the
learning of behavior perception and production in sensorimotor and
social cognitive processing. Stefan is the current president of the
German Cognitive Science Society.
Hands and Speech in Space: Multimodal Interaction with Augmented
Reality interfaces
Prof. Mark Billinghurst
HIT Lab, University of Canterbury, New Zealand
Augmented Reality (AR) is technology that allows
virtual imagery to be seamlessly integrated into the real
world. Although first developed in the 1960's it has only been
recently that AR has become widely available, through platforms such
as the web and mobile phones. However most AR interfaces have very
simple interaction, such as using touch on phone screens or camera
tracking from real images. In this presentation I will talk about
the opportunities for multimodal input in AR applications. New depth
sensing and gesture tracking technologies such as Microsoft Kinect
or Leap Motion have made is easier than ever before to track hands
in space. Combined with speech recognition and AR tracking and
viewing software it is possible to create interfaces that allow
users to manipulate 3D graphics in space through a natural
combination of speech and gesture. I will review research in
multimodal AR interfaces from the HIT Lab NZ and other leading
research groups to show the state of the art in multimodal AR
interfaces. The talk will also give an overview of the significant
research questions that need to be addressed before speech and
gesture interaction with AR applications can become commonplace.
Professor Mark Billinghurst is a researcher developing
innovative computer interfaces that explore how virtual and real
worlds can be merged. Director of the HIT Lab New Zealand (HIT Lab
NZ) at the University of Canterbury in New Zealand, he has produced
over 250 technical publications and presented demonstrations and
courses at a wide variety of conferences. He has a PhD from the
University of Washington and conducts research in Augmented and
Virtual Reality, multimodal interaction and mobile interfaces. He
has previously worked at ATR Research Labs, British Telecom, Nokia
and the MIT Media Laboratory. One of his research projects, the
MagicBook, was winner of the 2001 Discover award for best
Entertainment application, and his AR Tennis project won the 2005
IMG award for best independent mobile game. In 2001 he co-founded of
ARToolworks, one of the oldest commercial AR companies.
Behavior Imaging and the Study of Autism
Prof. Jim Rehg
School of Interactive Computing, Georgia Institute of Technology, USA
Beginning in infancy, individuals acquire the
social and communication skills that are vital for a healthy and
productive life. Children with developmental delays face great
challenges in acquiring these skills, resulting in substantial
lifetime risks. Children with an Autism Spectrum Disorder (ASD)
represent a particularly significant risk category, due both to the
increasing rate of diagnosis of ASD and its consequences. Since the
genetic basis for ASD is unclear, the diagnosis, treatment, and
study of the disorder depends fundamentally on the observation of
behavior. Unfortunately, current methods for acquiring and analyzing
behavioral data are so labor-intensive as to preclude their large
scale application. In this talk, I will describe our research agenda
in Behavior Imaging, which targets the capture, modeling, and
analysis of social and communicative behaviors between children and
their caregivers and peers. We are developing computational methods
and statistical models for the analysis of vision, audio, and
wearable sensor data. Our goal is to develop a new set of
capabilities for the large-scale collection and interpretation of
behavioral data. I will describe several research challenges in
multi-modal sensor fusion and statistical modeling which arise in
this area, and present illustrative results from the analysis of
social interactions with children.
James M. Rehg (pronounced "ray") is a Professor in the
School of Interactive Computing at the Georgia Institute of
Technology, where he is the Director of the Center for Behavior
Imaging, co-Director of the Computational Perception Lab, and
Associate Director of Research in the Center for Robotics and
Intelligent Machines. He received his Ph.D. from CMU in 1995 and
worked at the Cambridge Research Lab of DEC (and then Compaq) from
1995-2001, where he managed the computer vision research group. He
received the National Science Foundation (NSF) CAREER award in 2001,
and the Raytheon Faculty Fellowship from Georgia Tech in 2005. He
and his students have received a number of best paper awards,
including best student paper awards at ICML 2005 and BMVC 2010, and
a method of the year award from Nature Methods in 2012. Dr. Rehg is
active in the organizing committees of the major conferences in
computer vision, most-recently serving as the Program co-Chair for
ACCV 2012. He has authored more than 100 peer-reviewed scientific
papers and holds 23 issued US patents. Dr. Rehg is currently leading
a multi-institution effort to develop the science and technology of
Behavior Imaging, funded by an NSF Expedition award (see
www.cbs.gatech.edu for
details).
|