Bernard Ghanem, King Abdullah University of Science and Technology (KAUST), SA - https://www.bernardghanem.com/

Bernard Ghanem is currently an Associate Professor at King Abdullah University of Science and Technology (KAUST), in the Visual Computing Center (VCC). He leads the Image and Video Understanding Lab (IVUL) at KAUST. His research interests are broadly in computer vision and machine learning broadly, and specifically in large-scale video understanding, 3D understanding, and foundations of machine learning. He was a graduate research assistant at the Computer Vision and Robotics Lab (CVRL) at the Beckman Institute for Advanced Science and Technology at the University of Illinois at Urbana-Champaign. His advisor was Professor Narendra Ahuja, who heads CVRL. His PhD work focused on modeling dynamic textures from video for the purpose of non-trivial synthesis, recognition, compression, extraction, and activity recognition. While He was doing his PhD, I worked on other things too, including efficient optimization schemes (e.g. in normalized graph cuts), sparse representation and dictionary learning, and ways of using human perceptual information in computer vision applications.

Going Beyond Temporal Activity Localization in Video

Richard Newcombe, Meta Reality Labs, US

Richard Newcombe is director of research science at Meta Reality Labs.