Automatic generation of taxonomies can be useful for a wide area of applications. In our application scenario a topical hierarchy should be constructed reasonably fast from a large...
Labeling objects in images is an essential prerequisite for many visual learning and recognition applications that depend on training data, such as image retrieval, object detecti...
Document image segmentation algorithms primarily aim at separating text and graphics in presence of complex layouts. However, for many non-Latin scripts, segmentation becomes a ch...
In this paper we propose an edge-directed error concealment (EDEC) algorithm, to recover lost slices in video sequences encoded by flexible macroblock ordering. First, the strong e...
Mengyao Ma, Oscar C. Au, Shueng-Han Gary Chan, Min...
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...