My research is focused on machine learning problems with geometric flavor. The symbiosis between data-driven and model-driven methods opens up new and exciting possibilities to overcome limitations in the new era of machine learning. The data we consume have a unique structure which we can further exploit in learning paradigm used, for example, in computer vision, medical imaging and robotics.
Dr. Dan Raviv
Post-doctoral– Massachusetts Institute of Technology (MIT)
Doctorate – Technion, Israel Institute of Technology. Computer Science department.
Master – Technion, Israel Institute of Technology. Computer Science department.
Bachelor – Technion, Israel Institute of Technology. Mathematics department.
- Affine invariant geometry for non-rigid shapes. D. Raviv and R. Kimmel. International journal of computer vision (IJCV), 111 (1), 2014.
- Scale invariant metrics of volumetric datasets. D. Raviv, and R. Raskar. SIAM Journal on Imaging Sciences, 8(1) (SIIMS), 2015.
- Locally Rigid Averaging (LRA): Expected geometrical mean from stretchable non-rigid observations. D. Raviv, E. Bayro-Corrochano and R. Raskar. International Journal of Computer Vision (IJCV), 2017
- Deep video gesture recognition using illumination invariants. O. Gupta, D. Raviv and R. Raskar. Pattern Recognition, 2018.