Instructor: Prof. Ananda S. Chowdhury, Professor, Jadavpur University (https://sites.google.com/
Room No: 102 (Seminar Hall), CDS
Contents of the course:
1. Lecture 1: Tuesday, November 5 (5:00 PM to 7-00 PM)
Will start with basics of graphs, talk about sparse/dense graphs, connectivity in graphs, then discuss labeling problems in a weakly supervised setup and focus on Random Walks, mention how we can improvise on such a setup with and without deep learning, show some use cases, and will (try to) include a demo
2. Lecture 2: Wednesday, November 6 (5:00 PM to 7-00 PM)
The focus will be on Graph Cuts, will talk about basic formulation including graph construction and energy optimization, then discuss typical problems, like segmentation, registration, where you can apply graph cuts, mention how we can improvise on such a setup with and without deep learning, show some use cases, and will (try to) include a demo
3. Lecture 3: Thursday, November 7 (5-00 PM to 7-00 PM)
The focus will be on Graph Convolution Networks, will mention both the forward and the backward pass, will discuss typical problems in GCN like node labeling, edge labeling, and graph labeling mention how we can improvise on such a setup, show some use cases, and will (try to) include a demo
About the Instructor:
Prof. Ananda S. Chowdhury is a seasoned researcher in the field of Computer Vision and Pattern Recognition. He currently leads the Imaging, Vision, and Pattern Recognition (IVPR) group at Jadavpur University. He is a senior member of IEEE, an IAPR TC-member of Graph-based Representations in Pattern Recognition (GbR), and a life member of the Indian Unit for Pattern Recognition and Artificial Intelligence (IUPRAI). He serves as an Associate Editor for IEEE Transactions on Image Processing and an Area Editor for Pattern Recognition Letters. His previous editorial roles include positions with Pattern Recognition Letters, and IEEE Signal Processing Letters. He completed his post-doctoral fellowship at the National Institutes of Health, USA, and earned his Ph.D. in Computer Science from the University of Georgia, USA. His research interests span a wide range of theoretical and application problems in Computer Vision and Pattern Recognition, with a focus on Biomedical, Multimedia, and Surveillance applications. His work explores graph-theoretic models, level sets, probabilistic methods, and deep learning algorithms. He is the author of two books, first one being Graph Based Multimedia Analysis (https://www.amazon.in/Graph-
COURSE REGISTRATION LINK: https://forms.gle/
For questions and clarifications, contact: Phaneendra Yalavarthy, e-mail: yalavarthy@iisc.ac.in
