About Me

I am a 5th year Ph.D. student advised by Prof. Amit Roy-Chowdhury. Prior to pursuing my Ph.D. I was a Masters student with Prof. Roy-Chowdhury from 2016 to 2018 with thesis on Face Recognition in Art Portraits.

I obtained my B. Tech in Electronics and Communications from Visvesvaraya National Institute of Technology, Nagpur, India in 2014.

Research Interests

I am interested in computer vision, machine learning and video analysis. Much of my research is about understanding images and videos in the latent feature space and explioting the feature space for the task of transfer learning, video synthesis and enhancement, and future anticipation.

News

  • Jul 2020: Two papers on adversarial knowledge transfer and video enhancement accepted at ACM-MM 2020.
  • Jun 2020: Joined JD.com AI Research, Mountain View, CA as a Research Intern.
  • Apr 2020: Paper on enhanced reconstruction accepted at ISBI Workshop 2020.
  • Feb 2020: Paper on video synthesis accepted at CVPR 2020.

Selected Publications



ALANET: Adaptive Latent Attention Network for Joint Video Deblurring and Interpolation (Oral Presentation)

Akash Gupta, Abhishek Aich, Amit K. Roy-Chowdhury
ACM International Conference on Multimedia (ACM-MM), 2020

[Project Page]      [arXiv]      [Code]


Adversarial Knowledge Transfer from Unlabeled Data

Akash Gupta*, Rameswar Panda*, Sujoy Paul, Jianming Zhang, Amit K. Roy-Chowdhury (* joint first authors)
ACM International Conference on Multimedia (ACM-MM), 2020

[Project Page]      [arXiv]      [Code]


Non-Adversarial Video Synthesis with Learned Prior

Abhishek Aich*, Akash Gupta*, Rameswar Panda, Rakib Hyder, Salman Asif, Amit K. Roy-Chowdhury (* joint first authors)
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020

[Project Page]      [arXiv]      [Code]


Deep Quantized Representation for Enhanced Reconstruction

Akash Gupta, Abhishek Aich, Amit K. Roy-Chowdhury
IEEE International Symposium on Biomedical Imaging (ISBI Workshop), 2020

[Code]


Deep Learning based Identity Verification in Renaissance Portraits

Akash Gupta, Niluthpol Mithun, Conrad Rudolph, Amit K. Roy-Chowdhury
IEEE International Conference on Multimedia and Expo (ICME), 2018

[Code]




Akash Gupta
PhD Candidate

Video Computing Group (VCG)
University of California, Riverside



agupt013 [at] ucr dot edu