This paper addresses the problem of similar image retrieval, especially in the setting of large-scale datasets with millions to billions of images. The core novel contribution is ...
One current direction to enhance the search accuracy in visual object retrieval is to reformulate the original query through (pseudo-)relevance feedback, which augments a query wi...
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...
Many traditional relevance feedback approaches for CBIR can only achieve limited short-term performance improvement without benefiting long-term performance. To remedy this limita...
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...