Yogesh Rawat

Assistant Professor, University of Central Florida

Dr. Yogesh S Rawat is an Assistant Professor at the Center for Research in Computer Vision at the University of Central Florida. His research interests lie in the intersection of Computer Vision, Deep Learning, and Multimedia Computing. Real-world is inherently sequential in nature and therefore most of the real-world application domains, such as security, personal assistance, autonomous vehicles, and robotics, involve videos and require temporal understanding. Visual perception in video domain is one of his main research directions. He has been actively involved in several Government research projects on video understating as PI/co-PI, such as IARPA (BRIAR, DIVA, WRIVA) and DARPA (KAIROS, RED). Although there has been significant advancements in visual perception in videos, but most of it relies on large-scale training on huge amounts of annotated datasets. Such a requirement is very critical for performance and is not suitable for real-world applications. With this motivation, Dr. Rawat is currently exploring data and label efficient techniques for robust video understanding. He is very passionate about involvement of undergraduate and minority students in research. He is co-PI in NSF REU program for training undergraduate students for research and is also involved in several other programs such as STRONG, STEM, and EXCEL sponsored by NSF focused on minority groups.


  • Visual Perception
  • Video Understanding
  • Limited Label Learning
  • Data-Efficient Learning
  • Dense Video Understanding