This paper presents a novel approach for recognizing and interpreting dimensions in engineering drawings. It starts by detecting potential dimension frames, each comprising only t...
This paper proposes a unified framework for spatiotemporal segmentation of video sequences. A Bayesian network is presented to model the interactions among the motion vector field...
This paper presents a dynamic conditional random field (DCRF) model to integrate contextual constraints for object segmentation in image sequences. Spatial and temporal dependenci...
One of the key problems of restoring a degraded image from motion blur is the estimation of the unknown shiftinvariant linear blur filter. Several algorithms have been proposed ut...
Kernel machines (e.g. SVM, KLDA) have shown state-ofthe-art performance in several visual classification tasks. The classification performance of kernel machines greatly depends o...