We describe a solution to the challenging problem of estimating human body shape from a single photograph or painting. Our approach computes shape and pose parameters of a 3D huma...
Peng Guan, Alexander Weiss, Alexandru O. Balan, Mi...
We present an approach to low-level vision that combines two main ideas: the use of convolutional networks as an image processing architecture and an unsupervised learning procedu...
Abstract. We describe progress in the automatic detection and identification of humans in video, given a minimal number of labelled faces as training data. This is an extremely cha...
Image classification is a well-studied and hard problem in computer vision. We extend a proven solution for classifying web spam to handle images. We exploit the link structure of...
Scalable image retrieval systems usually involve hierarchical quantization of local image descriptors, which produces a visual vocabulary for inverted indexing of images. Although ...
Rongrong Ji (Harbin Institute of Technology), Xing...