Conventional vision systems and algorithms assume the imaging system to have a single viewpoint. However, these imaging systems need not always maintain a single viewpoint. For ins...
Rahul Swaminathan, Michael D. Grossberg, Shree K. ...
In this paper, we propose to focus on the segmentation of vectorial features (e.g. vector fields or color intensity) using region-based active contours. We search for a domain that...
Consider a scenario where Jane is at an airport. She wants to find a restaurant with healthy food and short waiting time on the way to her terminal. The airport can provide such s...
We describe a learning based method for recovering 3D human body pose from single images and monocular image sequences. Our approach requires neither an explicit body model nor pri...
Abstract--The H.264 standard achieves much higher coding efficiency than the MPEG-2 standard, due to its improved inter-and intra-prediction modes at the expense of higher computat...