Prateek Keserwani, Ph.D.
Chief Engineer (Machine Learning),
Samsung R&D Institute India - Bangalore,
India
Research Area: Deep Learning, Computer Vision, Generative AI, Neural Architecture Search, Brain Computer Interface
I completed Ph.D. from Indian Institute of Technology Roorkee, India, under the supervision of Dr. Partha Pratim Roy on "Detection and Concealment of Text in Natural Images." I completed B.Sc., M.Sc (CS). and M.Tech (Computer Technology) from the University of Allahabad, India in 2008, 2010 and 2015 respectively. Currently, I am working in the area of neural architecture search. The neural architecture search is a step toward Learn2Learn. The current deep learning method can learn automatic features but needs the handcrafted design of the architectures. But, the neural architecture search obtains the optimal neural network from the search space and eliminates the need to design the architectures manually. Additionally, I am also interested in Generative AI.
Reviewer
Journals
IEEE Transactions on Circuits and Systems for Video Technology
ACM Transactions on Asian and Low-Resource Language Information Processing
IEICE Transactions on Information and Systems
IEEE Access
International Journal of Machine Learning and Cybernetics (Springer)
Multimedia Tools and Applications (Springer)
International Journal on Document Analysis and Recognition (Springer)
The Visual Computer (Springer)
SN Computer Science (Springer)
IET Image Processing
IET Biometrics
Conferences
ICASSP 2024
CVIP 2023
ICPR 2022
ECCV 2022 (Workshop)
CVIP 2021
ICFHR 2020