Avinab Saha
Scholar

Avinab Saha

Google Scholar ID: tlp7uQEAAAAJ
Research Scientist, Google Research
Machine LearningVisual PerceptionGenerative AIRLHFSelf-Supervised Learning
Citations & Impact
All-time
Citations
267
 
H-index
7
 
i10-index
6
 
Publications
14
 
Co-authors
31
list available
Resume (English only)
Academic Achievements
  • - Published Papers:
  • - IEEE Transactions on Image Processing (TIP) 2024
  • - 3rd Explainable AI for Computer Vision (XAI4CV) Workshop, CVPR 2024
  • - 3rd Workshop on Image/Video/Audio Quality in CV and Gen AI, WACV 2024
  • - IEEE/CVF Computer Vision and Pattern Recognition (CVPR) 2023
  • - IEEE Transactions on Image Processing (TIP) 2023
  • - Other Achievements:
  • - Passed PhD Progress Review (November 2024)
  • - Google Research Internship (May 2024)
  • - Guest Lecturer for ECE 371Q (September 2023)
  • - Invited Talk at VQEG Spring Meeting (June 2023)
Research Experience
  • - 05/2024 - Present: Research Intern, Google Research, Mountain View in Athena Team.
  • - 05/2022 - 08/2022: PhD Research Intern, Apple, Cupertino in Display & Color Technologies Team.
  • - 06/2019 - 01/2021: Research Engineer, Samsung Research in AI Visual Processing Lab.
  • - 05/2018 - 08/2018: Research Intern, Samsung Research in AI Visual Processing Lab.
Education
  • - Degree: Bachelor's degree
  • - School: IIT Kharagpur
  • - Advisor: Prof. Jayanta Mukhopadhyay
  • - Time: 2019
  • - Major: Electronics and Electrical Communications Engineering
  • - Degree: Ph.D. (in progress)
  • - School: The University of Texas at Austin
  • - Advisor: Prof. Al Bovik
  • - Time: Fourth year
Background
  • - Research Interests: Perceptual Image & Video Quality Assessment, with a focus on Cloud Gaming & Virtual Reality applications
  • - Professional Field: Electronics and Electrical Communications Engineering
  • - Brief Introduction: Currently a fourth-year Ph.D. student at The University of Texas at Austin, focusing on perceptual image and video quality assessment.
Miscellany
  • - Personal Interests: Not provided