We propose an unsupervised, probabilistic method for learning visual feature hierarchies. Starting from local, low-level features computed at interest point locations, the method c...
In feature models’ construction, one basic task is to ensure the consistency of feature models, which often involves detecting and fixing of inconsistencies in feature models. S...
Bo Wang, Yingfei Xiong, Zhenjiang Hu, Haiyan Zhao,...
In this paper we present a method for learning classspecific
features for recognition. Recently a greedy layerwise
procedure was proposed to initialize weights of deep
belief ne...
Mohammad Norouzi (Simon Fraser University), Mani R...
Abstract. We address the problem of estimating human body pose from a single image with cluttered background. We train multiple local linear regressors for estimating the 3D pose f...
We present a new technique for extracting local features from images of architectural scenes, based on detecting and representing local symmetries. These new features are motivate...