We present a new approach to iteratively estimate both
high-quality depth map and alpha matte from a single image
or a video sequence. Scene depth, which is invariant
to illumin...
Jiejie Zhu (University of Kentucky), Miao Liao (Un...
Density of moles is a strong predictor of malignant
melanoma. Some dermatologists advocate periodic fullbody
scan for high-risk patients. In current practice, physicians
compare...
Image auto-annotation is an important open problem in
computer vision. For this task we propose TagProp, a discriminatively
trained nearest neighbor model. Tags of test
images a...
Matthieu Guillaumin, Thomas Mensink, Jakob Verbeek...
Scene content understanding facilitates a large number of applications, ranging from content-based image retrieval to other multimedia applications. Material detection refers to t...
We propose a statistical formulation for 2-D human pose estimation from single images. The human body configuration is modeled by a Markov network and the estimation problem is to...