This paper proposes the use of feature tracks for the detection of concepts in video, particularly dynamic concepts. Feature tracks are defined as sets of local interest points fo...
Vasileios Mezaris, Anastasios Dimou, Ioannis Kompa...
Feature selection, as a preprocessing step to machine learning, has been very effective in reducing dimensionality, removing irrelevant data, increasing learning accuracy, and imp...
Though AdaBoost has been widely used for feature selection and classifier learning, many of the selected features, or weak classifiers, are redundant. By incorporating mutual infor...
LinLin Shen, Li Bai, Daniel Bardsley, Yangsheng Wa...
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...
Motion segmentation using feature correspondences can be regarded as a combinatorial problem. A motion segmentation algorithm using feature selection and subspace method is propos...