Behzad Bozorgtabar

photo placeholder image
About Me
I am a Research Scientist at EPFL, in the Signal Processing Laboratory 5 (LTS5). I am also affiliated with the University Hospital Center (CHUV) and the Center of Biomedical Imaging (CIBM). My research interests lie in the general area of machine learning and computer vision, particularly in deep representation learning, as well as their applications in domain adaptation, self-supervised learning and in the context of 3D vision and medical imaging analysis. The ultimate goal of my research is to develop robust deep image and video representations that capture and understand the world as well as our human eye and mind do. Those representations will form the basic building block of many downstream applications. Please check my homepage at ( to view my up-to-date publications and projects.

ELD 231 (Bâtiment ELD)
Station 11
CH-1015 Lausanne


Web site: Web site:

Web site: Web site:

Administrative data

Fields of expertise

⇨ Machine Learning (generative adversarial networks, self-supervised learning, meta-learning, domain-adaptation) 
⇨ Computer Vision (object detection, object tracking, multi-target tracking, action recognition, event detection, scene geometry, depth and ego-motion estimation from video) 
⇨ Affective Computing (real-time facial expression recognition ) 
⇨ Image Processing (semantic image segmentation, medical image analysis) 

Teaching & PhD


Electrical and Electronics Engineering


Lab in signal and image processing

These lab sessions are designed as a practical companion to the course "Image Analysis and Pattern Recognition" by Prof. Thiran. The main objective is to learn how to use some important image processing libraries, namely OpenCV, for performing image analysis tasks.