2013 Behavior Imaging Seminars

Fall 2013 Schedule

October 9, 2013
Linda Smith, University of Indiana, Psychology
TSRB 132 2:00-3:00pm

Title: Holding, seeing, and object learning by infants

Abstract: A developmental pathway may be defined as the route, or chain of events, through which a new structure or function forms. Research into these pathways often reveal complex, multi-causal and unexpected dependencies. For example, in behavioral development, the evidence indicates that motor achievements –sitting, crawling, walking – are important components of in the development of seemingly unrelated cognitive achievements. This talk will present evidence concerning developmental dependences between motor development, action on objects, visual object recognition and object name learning in 12 to 24 month old infants, a period in which children appear to build view-independent object representations and in which they learn the names for many object categories. The talk will specifically present data from a series of experiments, including those using head-mounted cameras/eye-trackers to capture that changing visual experiences that result as a consequence of toddlers rapidly changing motor skills.

October 23, 2013
Warren Jones, Emory University, Pediatric Research
TSRB 132 4:00-5:00pm

Click Here to view Dr. Jones' talk.

Title: Quantifying Social Engagement in Infants and Toddlers with ASD 

Abstract: Autism is a neurodevelopmental disorder of genetic origins, although the way in which genetic vulnerabilities are converted into symptoms remains unknown.  One hypothesis is that symptomatology results from the disruption of very basic mechanisms of normative socialization.  In typical development, the processes of normative social interaction are present from the first hours and weeks of life: preferential attention to familiar voices, faces, face-like stimuli, and biological motion guides typical infants from birth. These processes are highly-conserved phylogenetically and lay the foundation for iterative specialization of mind and brain, entraining babies to the social signals of their caregivers.  This presentation will focus on a series of studies quantifying social engagement in infants and toddlers, and the use of these quantifications as assays of social development and risk for social disability in infants and toddlers with autism spectrum disorders (ASD).

Speaker Bio: Warren Jones is Director of Research at the Marcus Autism Center and faculty in the Department of Pediatrics at the Emory University School of Medicine.  He completed his Ph.D. in Neuroscience at Yale University.  He currently directs the Social Neuroscience Laboratory at the Marcus Autism Center.  Research in the laboratory focuses on mapping and quantifying the developmental course of social disability in autism spectrum disorders, from birth through young adulthood.  The goal of this research is to understand the origins and development of autism, and to inform better treatment practices, by developing tools for objective early diagnosis and prediction of outcome for individuals with autism spectrum disorders.

Background Papers:

Klin A, Lin DJ, Gorrindo P, Ramsay G, & Jones W. (2009). Two-year-olds with autism fail to orient towards human biological motion but attend instead to non-social, physical contingencies. Nature, 459, 257-261. PMID: 19329996

Shultz S, Klin A, & Jones W. (2011) Inhibition of Eye Blinking Reveals Subjective Perceptions of Stimulus Salience. Proceedings of the National Academy of Sciences USA. 108(52):21270-5. PMID: 22160686

November 6, 2013
Fernando De la Torre, Carnegie Mellon University, Robotics
MIRC 102a 12:00-1:00pm

Title: Component Analysis for Human Sensing

Abstract: Enabling computers to understand human behavior has the potential to revolutionize many areas that benefit society such as clinical diagnosis, human computer interaction, and social robotics. A critical element in the design of any behavioral sensing system is to find a good representation of the data for encoding, segmenting, classifying and predicting subtle human behavior. In this talk I will propose several extensions of Component Analysis (CA) techniques (e.g., kernel principal component analysis, support vector machines, spectral clustering) that are able to learn spatio-temporal representations or components useful in many human sensing tasks. In particular, I will show how several extensions of CA methods outperform state-of-the-art algorithms in problems such as facial feature detection and tracking, temporal clustering of human behavior, early detection of activities, non-rigid feature matching, weakly-supervised visual labeling, and robust classification. The talk will be adaptive, and I will discuss the topics of major interest to the audience.

Biography: Fernando De la Torre received his B.Sc. degree in Telecommunications (1994), M.Sc. (1996), and Ph. D. (2002) degrees in Electronic Engineering from La Salle School of Engineering in Ramon Llull University, Barcelona, Spain. In 2003 he joined the Robotics Institute at Carnegie Mellon University , and since 2010 he has been a Research Associate Professor. Dr. De la Torre's research interests include computer vision and machine learning, in particular face analysis, optimization and component analysis methods, and its applications to human sensing. He is Associate Editor at IEEE PAMI and leads the Component Analysis Laboratory (http://ca.cs.cmu.edu) and the Human Sensing Laboratory (http://humansensing.cs.cmu.edu).

November 20, 2013
Roland Goecke, University of Canbera, Audio-Video Speech Processing
TSRB 132 12:00-1:00pm

Title: From Affective Computing to Computational Behaviour Analysis

Abstract: In this talk, I will give an overview of our research into developing technology that analyses the affective state and more broadly behaviour of humans. Such technology is useful for a number of applications, with applications in healthcare, e.g. mental health disorders, being a particular focus for us. Depression and other mood disorders are common and disabling disorders. Their impact on individuals and families is profound. The WHO Global Burden of Disease reports quantify depression as the leading cause of disability world-wide. Despite the high prevalence, current clinical practice depends almost exclusively on self-report and clinical opinion, risking a range of subjective biases. There currently exist no laboratory-based measures of illness expression, course and recovery, and no objective markers of end-points for interventions in both clinical and research settings. Using a multimodal analysis of facial expressions and movements, body posture, head movements as well as vocal expressions, we are developing affective sensing technology that supports clinicians in the diagnosis and monitoring of treatment progress. Encouraging results from a recently completed pilot study demonstrate that this approach can achieve over 90% agreement with clinical assessment. We are currently extending this line of research to other disorders such as anxiety, post-traumatic stress disorder, dementia and autism spectrum disorders. In particular for the latter, a natural progression is to analyse dyadic and group social interactions. At the core of our research is a focus on robust approaches that can work in real-world environments.

Biography: Dr Roland Goecke is an Associate Professor in Information Technology & Engineering at the Faculty of Education, Science, Technology and Engineering, University of Canberra, Australia. He is the Head of the Vision and Sensing Group and the Deputy Director of the Human-Centred Computing Research Laboratory. He received his Masters degree in Computer Science from the University of Rostock, Germany, in 1998 and his PhD in Computer Science from the Australian National University, Canberra, Australia, in 2004. Before joining UC in December 2008, Dr Goecke worked as a Senior Research Scientist with Seeing Machines, as a Researcher at the NICTA Canberra Research Labs, and as a Research Fellow at the Fraunhofer Institutes for Computer Graphics, Germany. His research interests are in affective computing, pattern recognition, computer vision, human-computer interaction, multimodal signal processing and e-research. Dr Goecke has been an author and co-author of more than 100 peer-reviewed publications. His research has been funded by grants from the Australian Research Council (ARC), the National Health and Medical Research Council (NHMRC), the National Science Foundation (NSF, USA), the Australian National Data Service (ANDS) and the National eResearch Collaboration Tools and Resources project (NeCTAR).