Title of talk: Perception and cognition of non-verbal behavior: Three quite different applications
"Apart from the verbal communication, humans also display very rich information through non-verbal channels, about their state of mind, attitudes and intentions. This information is mostly transfered unconsciously though head, arm and body motion, facial expression, gaze patterns, pupil dilation, muscle tension, etc. Today I will talk about three quite different projects where such signals is analyzed and recognized in a computerized manner. The methods in all these projects are heavily machine learning-based and data driven. A central aspect is that we, through our collaborations with domain experts in gerontology, veterinary science, and music, record rich data under realistic circumstanses in the actual environment where the non-verbal communication takes place, and use our domain specialists to achieve expert labeling of the data. I will for each application describe how this is done, and also describe how we make use of this data using different kinds of machine learning methods."
Hedvig Kjellström is a Professor in the Division of Robotics, Perception, and Learning, and the Head of the Department of Intelligent Systems, at KTH in Stockholm, Sweden. She received an MSc in Engineering Physics and a PhD in Computer Science from KTH in 1997 and 2001, respectively. Between 2002 and 2006 she worked as a scientist at the Swedish Defence Research Agency, where she focused on Information Fusion and Sensor Fusion. In 2007 she returned to KTH, pursuing research in activity analysis in video. Her present research focuses on methods for enabling artificial agents to interpret human behavior and reasoning, and also to behave and reason in ways interpretable to humans. These ideas are applied in human-robot interaction, performing arts, healthcare, and smart society. In 2010, she was awarded the Koenderink Prize for fundamental contributions in Computer Vision for her ECCV 2000 article on human motion reconstruction, written together with Michael Black and David Fleet. She has written around 100 papers in the fields of Computer Vision, Machine Learning, Robotics, Information Fusion, Cognitive Science, Speech, and Human-Computer Interaction. She is mostly active within Computer Vision, where she is an Associate Editor for IEEE TPAMI and regularly serves as Area Chair for the major conferences.
During the seminar, we offer lunch to participants who register before 16:00 on 15 November. Don´t forget to cancel your registration if you can't attend.
The seminar is open to anyone with an interest in female role models within academia - especially from Chalmers, Sahlgrenska University Hospital, Sahlgrenska Academy, Gothenburg University, Borås University, and MedTech West.