-
Human Motion Analysis in the Interplay of Multimodality, Representation and Learning
Thu, Apr 18, 2013 @ 01:30 PM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Ferda Ofli, University of California - Berkeley
Talk Title: Human Motion Analysis in the Interplay of Multimodality, Representation and Learning
Abstract: Human motion analysis is one of the most challenging research areas in computer vision in which one can seek to perform better by fusing information from multi-sensory data, by proposing richer feature representations, and by developing more efficient learning algorithms. In this talk, I will first describe the Berkeley MHAD, recently released comprehensive multimodal human action database, and present action recognition results for individual modalities as well as combinations of different modalities using state-of-the-art feature representations together with kernel-based methods. Then, I will introduce a new skeletal representation of human actions based on orderings of the most informative joints and demonstrate on multiple datasets that the new representation is discriminative for human action recognition and performs better than state-of-the-art feature representations. Finally, I will talk about a multimodal analysis framework for learning and synthesis of human body motions in the context of dance performances.
Biography: Ferda Ofli received B.Sc. degrees both in Electrical and Electronics Engineering and Computer Engineering, and the Ph.D. degree in Electrical Engineering from Koc University, Istanbul, Turkey, in 2005 and 2010, respectively. He is currently a postdoctoral researcher in the Teleimmersion Lab at the University of California at Berkeley, Berkeley, CA. His research interests span the areas of multimedia signal processing, computer vision, pattern recognition and machine learning. He received Graduate Studies Excellence award in 2010 for outstanding academic achievement at Koc University. http://www.eecs.berkeley.edu/~fofli/
Host: Prof. Shrikanth Narayanan
Location: Ronald Tutor Hall of Engineering (RTH) - 320
Audiences: Everyone Is Invited
Contact: Mary Francis