Anastasis Stathopoulos
Ph.D. student @ Rutgers | anas.stathop@gmail.com

I am a Ph.D. student in the Department of Computer Science at Rutgers University, conducting research in Computer Vision and Deep Learning advised by Dimitris Metaxas. Prior to this, I did my bachelors in ECE at NTUA in Athens, Greece.

My current research interests lie in deep representation learning, transfer learning and structured prediction with their applications in pose estimation and recovery of 3D structure from images.

  |     |  


Education

Sept. 2018 - Present
Rutgers Univeristy
Ph.D. Student in Computer Science
Oct. 2012 - June 2018
National Technical University of Athens (NTUA)
Integrated Masters in Electical & Computer Engineering (ECE)
  • Major: Computer Science | GPA: 8.12/10.00
  • Diploma Thesis: Real-time Joint Semantic Reasoning for Autonomous Driving

Experience

May 2020 - Aug. 2020
Amazon Prime Video, Video Compliance & Classification - Seattle, WA, USA
Applied Science Intern (Computer Vision & Deep Learning)
  • Topic: Video Understanding for Content Moderation
Sept. 2018 - Present
Rutgers Univeristy, Computer Science Department - Piscataway, NJ, USA
Research Assistant | Advisor: Dimitris Metaxas
Teaching Assistant
  • CS:112 - Data Structures (Spring 2019, 2020)
  • CS:596 - Topics in the Foundation of Computer and Data Science (Fall 2019)
  • CS:112 - Principles of Programming Languages (Fall 2018)
Sept. 2017 - June 2018
National Technical University of Athens (NTUA) - Athens, Greece
Research Assistant | Thesis Preparation
  • Topic: Real-time Joint Semantic Reasoning for Autonomous Driving
June 2016 - Aug. 2016
Rutgers Univeristy, ECE Department - Piscatawy, NJ, USA
Visiting Researcher | Host: Shantenu Jha
  • Topic: Benchmarking Image Segmentation Algorithms on Parallel and Distributed Environments

Publications

Unbiased Auxiliary Classifier GANs with MINE
Ligong Han, Anastasis Stathopoulos, Tao Xue, Dimitris Metaxas
CVPR Workshop on Adversarial ML in Computer Vision, 2020 (Oral Presentation)
DeepMind Travel Award
PDF | Bibtex

Credits to Jon Barron