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...
We propose a compressed domain video object segmentation method for MPEG or MPEG-like encoded videos. Computational superiority is the main advantage of the compressed domain proc...
Fatih Murat Porikli, Faisal I. Bashir, Huifang Sun
Large-scale, ground-level urban imagery has recently developed as an important element of online mapping tools such as Google’s Street View. Such imagery is extremely valuable i...