Over the past decade, multiple-instance learning (MIL)
has been successfully utilized to model the localized
content-based image retrieval (CBIR) problem, in which a
bag corresp...
Wu-Jun Li (Hong Kong University of Science and Tec...
In image retrieval, global features related to color or texture are commonly used to describe the image content. The use of interest points in contentbased image retrieval allows ...
Content-based image retrieval in astronomy needs methods that can deal with an image content made of noisy and diffuse structures. This motivates investigations on how information ...
In this paper, we present a novel image representation that renders it possible to access natural scenes by local semantic description. Our work is motivated by the continuing effo...