Follow us on Facebook     RFMI 2016    

Invited Speakers

A. Srivastava

Anuj Srivastava (Professor, Florida State University, USA)

Title - On Advances in the Role of Differential Geometry in Computer Vision and Pattern Recognition

Abstract - The problem area of computer vision and pattern recognition (CVPR) involves modeling low-dimensional structures of interest, using high-dimensional data. It is thus natural to use geometry and statistics as basic tools for analysis in CVPR. Geometry is the language for studying structures while statistical is the science of modeling variability. The recent decade have seen substantial advances in use of geometry in vision algorithms. Examples include shape analysis, action recognition, covariance tracking, medical image analysis, and so on. In this talk, I will introduce some basic elements of differential geometry and....

read more

X. Pennec

X. Pennec (Senior Research Scientist, INRIA, France)

Title - Riemannian and Affine Structures for Statistics on Shapes and Deformations in Computational Anatomy

Abstract - Computational anatomy is an emerging discipline at the interface of geometry, statistics, image analysis and medicine that aims at analyzing and modeling the biological variability of the organs shapes and their dynamics at the population level. The goal is to model the mean anatomy, its normal variation, its motion/evolution and to discover morphological differences between normal and pathological groups. Since shapes and deformations live in non-linear spaces, this requires a consistent statistical framework on manifolds and Lie groups. The geometric structure...

read more

S. Zafeirou

S. Zafeirou (Senior Lecturer, Associate Professor, Imperial College London, UK)

Title - Building the first large scale 3D morphable model of faces.

Abstract - 3D Morphable Models (3DMMs) are powerful 3D statistical models of human face shape and texture. 3DMMs have been widely applied in numerous areas, such as computer vision, human behavioral analysis, and computer graphics etc. In particular, a 3DMM used in an analysis-by-synthesis framework is still among the state-of-the-art methods for performing reconstruction of the 3D facial surface from single images captured under unconstrained conditions. Until now, the most widely known 3DMM was the so-called Basel Model, which is built from 200 people. In this presentation, I will talk about the first large scale 3DMM...

read more

M. Shah

Mubarak Shah (Center for Research in Computer Vision, University of Central Florida, USA)

Title - Spatiotemporal graphs for object segmentation and human pose estimation in videos

Abstract - Images and videos can be naturally represented by graphs, with spatial graphs for images and spatiotemporal graphs for videos. However, for different applications, there are usually different formulations of the graphs, and algorithms for each formulation have different complexities. Therefore, wisely formulating the problem to ensure an accurate and efficient solution is one of the core issues in Computer Vision research. In this talk, I will explore three problems in this domain to demonstrate how to formulate all of these problems in terms of spatiotemporal graphs and ...

read more