We present a region based active contour model which does not require any initialisation and is capable of modelling multi-modal image regions. Its external force is based on stat...
In this paper, we present a fast approach to obtain semantic scene segmentation with high precision. We employ a two-stage classifier to label all image pixels. First, we use the ...
Wen Yang, Dengxin Dai, Bill Triggs, Gui-Song Xia, ...
Suppose a set of arbitrary (unlabeled) images contains frequent occurrences of 2D objects from an unknown category. This paper is aimed at simultaneously solving the following rel...
A new color segmentation method is presented in this paper. The method is specified for color images that have both large and small objects, and objects with both step and ramp ed...
Complex human activities occurring in videos can be defined in terms of temporal configurations of primitive actions. Prior work typically hand-picks the primitives, their total...