Home > Seminars > Richa Singh & Mayank Vatsa - Deep Learning for Face Analysis: Looking Beyond CNNs

Richa Singh & Mayank Vatsa - Deep Learning for Face Analysis: Looking Beyond CNNs

Start:

4/6/2017 at 3:30PM

End:

4/6/2017 at 5:00PM

Location:

129 DeBartolo

Host:

College of Engineering close button
headerbottom

Kevin Bowyer

Kevin Bowyer

VIEW FULL PROFILE Email: kwb@nd.edu
Phone: 574-631-9978
Website: http://www.nd.edu/~kwb
Office: 321 Stinson-Remick Hall

Affiliations

Biometrics, data mining, computer vision, pattern recognition, applications to medical imaging, ethics and computing, computer science education.
Click for more information about Kevin
574-631-9978
Add to calendar:
iCal vCal

In the last couple of years, deep learning algorithms have pushed the boundaries for numerous problems in computer vision. The performance of advanced machine (deep) learning algorithms has attained the numbers which were unexpected a decade back. There are three paradigms in deep learning: autoencoder, restricted Boltzmann machine, and convolutional neural network. Majority of deep learning research is currently driven using Convolutional Neural Networks and making the network deeper. In our research, we have shown that newer deep learning formulations in other paradigms can be designed to achieve similar or better performance compared to CNNs. The presentation will be divided into two parts: in the first part of the presentation, we will see how autoencoder can be used to solve face recognition problems with small training data. In the second part of the presentation, we will discuss how newer formulations of deep learning can be designed for challenging face recognition and anti-spoofing problems.

Seminar Speaker:

Richa Singh & Mayank Vatsa

Richa Singh & Mayank Vatsa

Richa Singh received the Ph.D. degree in Computer Science from West Virginia University, Morgantown, USA, in 2008. She is currently an Associate Professor with the IIIT Delhi, India and an Adjunct Associate Professor at West Virginia University, USA. Her areas of interest are biometrics, pattern recognition, and machine learning. She is a recipient of the Kusum and Mohandas Pai Faculty Research Fellowship at the IIIT Delhi, the FAST Award by Department of Science and Technology, India, and several best paper and best poster awards in international conferences. She is an Editorial Board Member of Information Fusion (Elsevier), and Associate Editor of IEEE Access and the EURASIP Journal on Image and Video Processing (Springer). She served as the Program Co-Chair of IEEE BTAS 2016 and General Co-Chair of ISBA 2017. She also served in e-Governance Standards Committee, Government of India, as well as UIDAI Biometric Standards Committee to design biometric standards for Aadhaar.

Mayank Vatsa received the Ph.D. degree in Computer Science from West Virginia University, Morgantown, USA, in 2008. He is currently Head of Infosys Center for Artificial Intelligence, an Associate Professor with the IIIT Delhi, India and Visiting Professor at West Virginia University, USA. His areas of interest are biometrics, image processing, computer vision, machine learning and information fusion. He is a recipient of the AR Krishnaswamy Faculty Research Fellowship, the FAST Award by DST, India, and several best paper and best poster awards in international conferences. He has published more than 200 peer reviewed papers in journals and conferences. He  is  also  the  Vice  President  (Publications)  of  IEEE  Biometrics Council, an Associate Editor of the IEEE Access, and an Area Editor of Information Fusion (Elsevier). He served as the PC Co-Chair of ICB 2013, IJCB 2014, and ISBA 2017. He also served in e-Governance Standards Committee, Government of India, as well as UIDAI Standards Committee to design biometric standards for nation-wide projects in India.