Prof. Rama Chellappa, Minta Martin Professor of Engineering and Chair, Department of Electrical and Computer Engineering, University of Maryland, College Park, USA  spoke about The Upending of 5 decades of Computer Vision Research – Deep Representations, Big Data & GPUs on 6 March. He discussed new methods based on deep representations for designing robust computer vision systems with applications in unconstrained face and action verification and recognition, expression recognition, subject clustering and attribute extraction. He also discussed the recent advances such as generative adversarial networks and domain adaptation.