We describe an unsupervised learning algorithm for extracting sparse and locally shift-invariant features. We also devise a principled procedure for learning hierarchies of invari...
Graph cut image segmentation with intensity information alone is prone to fail for objects with weak edges, in clutter, or under occlusion. Existing methods to incorporate shape a...
This paper introduces a flexible learning approach for image retrieval with relevance feedback. A semantic repository is constructed offline by applying the k-nearest-neighborbase...
Digital audio and video have recently taken a center stage in the communication world, which highlights the importance of digital media information management and indexing. It is ...
Lin Lin, Guy Ravitz, Mei-Ling Shyu, Shu-Ching Chen
Camera phones present new opportunities and challenges for mobile informationassociation and retrieval. The visual input in the real environment is a new and rich interaction moda...