We propose a new technique for edge-suppressing operations on images. We introduce cross projection tensors to achieve affine transformations of gradient fields. We use these tens...
We present an algorithm for jointly learning a consistent bidirectional generative-recognition model that combines top-down and bottom-up processing for monocular 3d human motion ...
Cristian Sminchisescu, Atul Kanaujia, Dimitris N. ...
Structured light systems use projected light to augment a scene with extra information. The goal of such systems is often the recovery of depth information based on 2D image(s) fr...
Abstract. Multi-sampled imaging is a general framework for using pixels on an image detector to simultaneously sample multiple dimensions of imaging (space, time, spectrum, brightn...
Characteristics of surveillance video generally include low resolution and poor quality due to environmental, storage and processing limitations. It is extremely difficult for comp...
Frank Lin, Clinton Fookes, Vinod Chandran, Sridha ...