In recent years, the deluge of visual data explosively aggregates at online information sites in a variety of diverse forms, such as image, video, multiple view, multiple modality, etc. which brings great challenges to the retrieval, analysis and understanding. In practice, many tasks upon such data (e.g., content-based image retrieval, object recognition, etc.) heavily rely on the modeling and representation of the big visual data. In the literature, there exist a large number of studies that have attempted to pursue the efficient model or representation, by introducing techniques like compact feature learning, content analysis, scene understanding, and so on. However, questions and challenges brought by the emerging large-scale visual applications still remain to be answered in this area, and require the intensive and multidisciplinary research. The aim of this special issue is to provide a forum for related researchers to share the most state-of-the-art development in modeling and representation for big visual data, with emphasis on their applications to addressing diverse large-scale visual problems.
Edited by Leida Li, Cheng Deng, Xianglong Liu, Yan Wang and Hantao Liu