We propose a new technique for quad-dominant remeshing which separates the local regularity requirements from the global alignment requirements by working in two steps. In the fir...
Video temporal segmentation is normally the first and important step for content-based video applications. Many features including the pixel difference, colour histogram, motion, ...
In recent work we have presented a formal framework for linguistic annotation based on labeled acyclic digraphs. These `annotation graphs' oer a simple yet powerful method fo...
ased Video Abstraction for Video Surveillance Systems Changick Kim, Member, IEEE, and Jenq-Neng Hwang, Fellow, IEEE Key frames are the subset of still images which best t the conte...