Mode-seeking has been widely used as a powerful data analysis technique for clustering and filtering in a metric feature space. We introduce a versatile and efficient modeseekin...
We present a new, block-based image codec based on sparse representations using a learned, structured dictionary called the IterationTuned and Aligned Dictionary (ITAD). The quest...
It is important to integrate contextual information in order to improve the inaccurate results of current approaches for automatic image annotation. Graph based representations all...
Vassilios Stathopoulos, Jana Urban, Joemon M. Jose
Although many interactive segmentation methods exists, none can be considered a silver bullet for all clinical tasks. Moreover, incompatible data representations prevent multiple a...
Due to the lack of explicit spatial consideration, existing
epitome model may fail for image recognition and target detection,
which directly motivates us to propose the so-calle...
Xinqi Chu, Shuicheng Yan, Liyuan Li, Kap Luk Chan,...