Title: Artistic Style Transfer With Generative Adversarial Networks

Speaker:  Dr. Kaustuv Nag, IIIT Guwahati

ABSTRACT:

This talk will present a new method for artistic style transfer using generative adversarial networks (GANs). The proposed method combines content from an input image with style from an artistic image to produce a new stylized image. This talk will present some essential concepts related to GANs and explain how these concepts contribute to the proposed scheme. It will also showcase the proposed scheme's results, highlighting the effectiveness of the GAN-based approach.

BIO:

Kaustuv Nag received the BTech degree in computer science and engineering from the West Bengal University of Technology, Kolkata, India, in 2010, the MTech degree in computer science and engineering from the National Institute of Technology, Durgapur, India, in 2012, and the PhD degree in engineering from Jadavpur University, Kolkata, in 2019. He is an Assistant Professor at the Department of Computer Science and Engineering, Indian Institute of Information Technology Guwahati, Guwahati, India. He was also a Visiting Researcher and a Visiting Scientist at the Indian Statistical Institute in Kolkata. His research interests include machine learning, transfer learning, neural networks, and evolutionary computation.