Deep Representations, Adversarial Learning and Domain Adaptation for Face Analytics and Action Detection in the Wild
Abstract: Recent developments in deep representation-based methods for many computer vision problems have knocked down many research themes pursued over the last four decades. In this talk, I will discuss methods based on deep representations, adversarial learning and domain adaptation for designing robust computer vision systems with applications in unconstrained face verification, search, clustering, expression recognition, attribute extraction, subject clustering, attribute extraction and action detection. The face analytics and action recognition systems being built at UMD are based on fusing multiple deep convolutional neural networks (DCNN) trained using publicly available still and video face data sets. Concepts such as multi-task learning, deep dictionaries, alignment-free methods and optimal sampling of training data have contributed to the design of a robust face analytics system. I will then discuss some new results on generative adversarial learning and domain adaptation for improving the robustness of the face recognition system. I will conclude the talk by discussing issues such as incorporating geometry and invariances in deep learning methods.
BIO: Prof. Rama Chellappa is a Distinguished University Professor and a Minta Martin Professor of Engineering and the Chair of the ECE department at the University of Maryland. He is a recipient of the K.S. Fu Prize from IAPR, the Society, Technical Achievement and Meritorious Service Awards from the IEEE Signal Processing Society (SPS) and the Technical Achievement and Meritorious Service Awards from the IEEE Computer Society. At UMD, he has received college and university level recognitions for research, teaching, innovation and mentoring of undergraduate students. He has been recognized with an Outstanding ECE Award and a Distinguished Alumni Award from Purdue University and Indian Institute of Science, respectively. He is a Fellow of IEEE, IAPR, OSA, AAAS, ACM, and AAAI and holds five patents