Philippos Mordohai is an Assistant Professor in the Department of Computer Science since 2008. Before joining Stevens, he held post-doctoral research associate positions at the University of North Carolina, Chapel Hill, and the University of Pennsylvania. Dr. Mordohai holds Ph.D. and M.S. degrees in Electrical Engineering from the University of Southern California and the Diploma of Electrical and Computer Engineering from the Aristotle University of Thessaloniki, Greece.
His research interests include perceptual organization, 3D reconstruction, 3D shape representation and manifold learning. Dr.
Mordohai has worked on fundamental perceptual organization problems, such as figure completion and the integrated inference of perceptual structures of different types including their boundaries. As an extension of this research, he proposed an approach for manifold learning and function approximation in high-dimensional spaces. He has also extensively investigated 3D reconstruction in various forms:
binocular, multiple-view and video-based. The real-time, large-scale, video-based reconstruction system developed by the University of North Carolina and the University of Kentucky is considered the state of the art for real-time reconstruction and received the Best Demo Award at the IEEE Conference on Computer Vision and Pattern Recognition in 2007.
Besides the reconstruction of static environments, a direction of high priority on Dr. Mordohai's research agenda is the 3D reconstruction of dynamic scenes. Moreover, Dr. Mordohai is investigating methods for analyzing range data in order to segment and recognize a broad range of object categories.
Dr. Mordohai has authored or co-authored approximately peer-reviewed and invited 30 papers in international journals, conferences and collections. He has also co-authored a book entitled "Tensor Voting: A Perceptual Organization Approach to Computer Vision And Machine Learning" with Gérard Medioni, which was published by Morgan & Claypool in 2006. He served as local chair for the Third International Symposium on 3D Data Processing, Visualization and Transmission in 2006.
He also served as program or arrangements chair for three international workshops held in conjunction with major computer vision conferences.
Dr. Mordohai is a reviewer or program committee member for over 40 international journals and conferences. He is listed Marquis Who's Who in Science and Engineering 2008 and 2010 and has received the National Scholarship Foundation of Greece scholarship in 1997 and 1998 and the award of excellence in the Greek Mathematical Society Annual Student Contest, in 1990, 1992 and 1993.
M. Pollefeys, D. Nistér, J.-M. Frahm, A. Akbarzadeh, P. Mordohai, B. Clipp, C. Engels, D. Gallup, S.-J. Kim, P. Merrell, C. Salmi, S. Sinha, B. Talton, L. Wang, Q. Yang, H. Stewénius, R. Yang, G. Welch, H. Towles,. (2008). "Detailed Real-Time Urban 3D Reconstruction From Video", International Journal of Computer Vision, vol. 78 (2-3), 143-167
P. Mordohai and G. Medioni. "Dimensionality Estimation, Manifold Learning and Function Approximation using Tensor Voting", Journal of Machine Learning Research, vol. 11 411-450
X. Hu and P. Mordohai. (2010). Evaluation of Stereo Confidence Indoors and Outdoors", International Conference on Computer Vision and Pattern Recognition
A. Toshev, P. Mordohai and B. Taskar. (2010). Detecting and Parsing Architecture at City Scale from Range Data", International Conference on Computer Vision and Pattern Recognition
P. Mordohai. (2009). The Self-Aware Matching Measure for Stereo", International Conference on Computer Vision
A. Patterson, P. Mordohai and K. Daniilidis. (2008). Object Detection from Large-Scale 3D Datasets using Bottom-up and Top-down Descriptors", European Conference on Computer Vision
P. Mordohai and G. Medioni. (2006). Tensor Voting: A Perceptual Organization Approach to Computer Vision And Machine Learning