Rivera, PaulGould, Stephen2015-12-10December 69780769545882http://hdl.handle.net/1885/39504Multi-class pixel labeling is an important problem in computer vision that has many diverse applications, including interactive image segmentation, semantic and geometric scene understanding, and stereo reconstruction. Current state-of-the-art approachesKeywords: Baseline models; Coherent images; Contextual information; Data sets; Diverse applications; Interactive image segmentation; markov random field; Multi-class; Scene understanding; Semi-supervised; State-of-the-art approach; Stereo reconstruction; Test sets; image segmentation; markov random field; pixel labeling201110.1109/DICTA.2011.242016-02-24