Amin Sadeghi


Image understanding, history, present and future

  Computer Engineering Department, Floor 1, Class 102
  Thursday, 31 December 2015
  10:00 - 11:00


During the past 50 years, image understanding has continuously changed from lower level pattern recognition to deeper and deeper perceptual understanding. This change in paradigm is primarily due to improved data availability, increased capacity for computation and improved techniques. This trend will continue for the at least the next decade and has important implications for research. Large companies – that often have better access to data and computation – have a competitive advantage in high-performance competitions comparing to universities. Therefore, universities need to be more creative in research.

In this talk, I will first present the history and the state-of-the-art of computer vision. Then, I will portray a probable scenario for the next few years. Finally, I will discuss strategies that universities need to take in their research.


Mohammad Amin Sadeghi completed his PhD at the University of Illinois at Urbana-Champaign. His research in Computer Vision and Machine Learning has been cited over 600 times. He has received the best student paper award at CVPR, which is the highest ranking conference in computer vision. He has recently started as a faculty member at the university of Tehran.