SeSaMe Special Seminar by Professor Ananda S. Chowdhury
Title: Graph Theoretic Multimedia Computing
Speaker: Prof Ananda S. Chowdhury
Date & Time: 17th July 2014 (Thu), 2.30pm
Venue: SeSaMe meeting room
Abstract: In this talk, it will be shown how some problems in multimedia can be efficiently solved using graph theoretic techniques. Graph based clustering, representations, and, matching will be explored in this connection. Primary focus will be on video summarization. Basic mono-view video summarization problem will be first solved using constrained Delaunay graph based clustering. The proposed solution will then be modified according to user customization. An alternative solution for the mono-view video summarization problem using multiple feature fusion with canonical correlation analysis and graph modularity based clustering will be discussed next. Then, scalable mono-view summarization will be briefly dealt with using skeleton graphs and random walks. Multi-view video summarization will be concisely addressed thereafter with bipartite matching constrained optimal path forest algorithm. The talk will end with a small discussion on how spectral graph clustering can be applied for detecting scenes in a movie.
Bio: Ananda S. Chowdhury is currently working as an Associate Professor in the department of Electronics and Telecommunication Engineering at Jadavpur University, Kolkata, India where he leads the Imaging, Vision and Pattern Recognition group. He earned his Ph.D. in Computer Science from the University of Georgia, USA in July 2007 and worked as a post-doctoral fellow in the department of Radiology and Imaging Sciences at the National Institutes of Health, USA during the period August 2007 to December 2008. In summer 2013, he visited Institut Für Informatik in University of Munster, Germany. His research interests span Computer Vision, Pattern Recognition, and, Biomedical Image Processing. He has co-authored more than thirty-five papers in leading international journals and conferences in addition to a monograph from the coveted Advances in Computer Vision and Pattern Recognition series of Springer. He is a member of the IEEE, the IEEE Computer Society, the IEEE Signal Processing Society and the IAPR. His Erdӧs number is 2.