Saliency Estimation

When multiple cameras view the same scene often a single good view suffices to visualize what’s going on. Within a single view keeping only the “important” pixels suffices to convey the story the image or video tells. Our team develops algorithms for finding the “important”, or salient, parts of visual data.


R. Margolin, L. Zelnik-Manor, and A. Tal, How to Evaluate Foreground Maps?, CVPR’ 2014. (pdf, Project page)

Follow the link for more details.