Computer vision: semantic and instance segmentation in images; action segmentation in videos; few-shot, weakly-supervised, cross-domain settings of these vision problems
Sinisa Todorovic obtained his M.S. and Ph.D. degrees in electrical and computer engineering from the University of Florida. He earned his B.S./M.S. in electrical engineering from the University of Belgrade in Serbia. Before coming to Oregon State University, Todorovic was a postdoc in the Beckman Institute at University of Illinois at Urbana-Champaign where he worked on multiscale image segmentation, structural pattern recognition, object / scene recognition and texture classification and synthesis. He was also a software engineer at Siemens from 1998-2001. Computer vision, machine learning, and artificial intelligence — specifically, recognition and modeling of objects, human activities, and texture occurring in images and video.