Megha Nawhal
mnawhal@sfu.ca

I am a PhD student in the School of Computing Science at Simon Fraser University advised by Greg Mori. My research interests lie in computer vision and machine learning with a particular focus on generative modeling techniques for images and videos. During my PhD, I have also worked with Leonid Sigal as an intern at Borealis AI. I also spent summer'19 at Adobe Research, SF.

Previously, I worked as a Research Scientist in the Cognitive Industry Solutions group at IBM Research, Bangalore. Earlier, I graduated from IIT Kanpur where I completed my Master's thesis under the supervision of K S Venkatesh on improved scene capture methods in unfavorable lighting conditions. During this, I also spent time at Sony Corporation, Japan as an intern in Summer 2013.

CV | Google Scholar

Selected Projects
sym

Activity Graph Transformer for Temporal Action Localization
Megha Nawhal, Greg Mori
arxiv | webpage

sym

MCMI: Multi-Cyle Image Translation with Mutual Information Constraints
Xiang Xu, Megha Nawhal, Greg Mori, Manolis Savva
arxiv | webpage

sym

Generating Videos of Zero-Shot Compositions of Actions and Objects
Megha Nawhal, Mengyao Zhai, Andreas Lehrmann, Leonid Sigal, Greg Mori
European Conference on Computer Vision (ECCV), 2020
paper | bibtex | slides | video | webpage

sym

Continuous Graph Flow
Zhiwei Deng*, Megha Nawhal*, Lili Meng, Greg Mori
ICML 2020 - Workshop on Graph Representation Learning and Beyond
paper | bibtex | webpage

sym

PiggybackGAN: Efficient Lifelong Learning for Image Conditioned Generation
Mengyao Zhai, Lei Chen, Jiawei He, Megha Nawhal, Fred Tung, Greg Mori
European Conference on Computer Vision (ECCV), 2020
paper | bibtex

sym

LifelongGAN: Continual Learning for Conditional Image Generation
Mengyao Zhai, Lei Chen, Fred Tung, Jiawei He, Megha Nawhal, Greg Mori
International Conference on Computer Vision (ICCV), 2019
paper | bibtex

sym

VideoWhiz: Non-Linear Interactive Overviews for Recipe Videos
Megha Nawhal, Jacqueline B Lang, Greg Mori, Parmit Chilana
Graphics Interface (GI), 2019
paper | bibtex

sym

Learning Disentangled Multimodal Representations for Fashion Domain
Amrita Saha, Megha Nawhal, Mitesh M. Khapra, Vikas C. Raykar
IEEE Winter Conference on Applications of Computer Vision (WACV), 2018
paper | bibtex

sym

Improved Scene Capture in Unfavorable Lighting Conditions
Megha Nawhal, Saumik Bhattacharya, K S Venkatesh
IEEE International Conference on Image Processing (ICIP), 2017
paper | bibtex


Template credits: Deepak, Jon, Saurabh, and Abhishek