Jorge Gomes da Silva
Research Scientist, Sr., Duke University, USA
This work addresses the problem of simultaneous signal recovery and dictionary learning based on compressive measurements. Multiple signals are analyzed jointly, with multiple sensing matrices, under the assumption that the unknown signals come from a union of a small number of disjoint subspaces. This problem is important, for instance, in image inpainting applications, in which the multiple signals are constituted by (incomplete) image patches taken from the overall image. This work extends standard dictionary learning and block-sparse dictionary optimization, by considering compressive measurements (e.g., incomplete data). Previous work on blind compressed sensing is also generalized by using multiple sensing matrices and relaxing some of the restrictions on the learned dictionary. Drawing on results developed in the context of matrix completion, it is proven that both the dictionary and signals can be recovered with high probability from compressed measurements. The solution is unique up to block permutations and invertible linear transformations of the dictionary atoms. The recovery is contingent on the number of measurements per signal and the number of signals being sufficiently large; bounds are derived for these quantities. In addition, a computationally practical algorithm that performs dictionary learning and signal recovery is derived, and conditions for convergence to a local optimum are established. Experimental results for image inpainting demonstrate the capabilities of the method.
Date and time: June 2, 15:00 – 16:00.
Place: IST (Alameda), Torre Norte, 5th floor, room 5.9 (DEEC meeting room). More Information..
The presentation will be May 27th, at 10h00
Location: DCC - FCUP, sala 1
Rua Campo Alegre 1021.
Human Motion: Tracking and recognition of actions, emotions and interactions
J. K. Aggarwal
Department of Electrical and Computer Engineering
The University of Texas, Austin, Texas 78712
Humans have always been interested in motion: Mobiles hung over the crib fascinate young children. Zeno studied moving arrows to pose a paradox. Zeke is investigating the human brain devoted to the understanding of motion. Prof. Aggarwal’s interest in motion started with the study of motion of rigid planar objects and gradually progressed to the study of human motion. Understanding human motion is a diverse and complex subject that includes recognizing and tracking individual actions, interactions between people, and interactions between people and objects, from the actions and emotions of an isolated person to the actions and interactions of a crowd. Prof. Aggarwal’s talk will present an overview of the ongoing research in human motion recognition at The University of Texas at Austin. The issues considered in these problems will illustrate the richness and the difficulty associated with understanding human motion. The application of the above research to monitoring will also be discussed.
J. K. Aggarwal has served on the faculty of The University of Texas at Austin College of Engineering since 1964. His research interests include computer vision, pattern recognition and image processing focusing on human motion. He is a Fellow of IEEE, IAPR and AAAS. More recently, he is the recipient of the 2004 K S FU prize of the International Association for Pattern Recognition, the 2005 Kirchmayer Graduate Teaching Award of the IEEE and the 2007 Okawa Prize of the Okawa Foundation of Japan. He is also a Life Fellow of IEEE and Golden Core member of IEEE Computer Society. He has authored or edited several books, chapters, conferences proceedings, and papers. More Information..