The past recent years have witnessed the explosive growth of image and video data on the Internet, which brings significant challenges and profound impacts to search and related technologies. It is challenging for many existing algorithms to effectively and efficiently handle very large collections of image and video contents, especially when the scale rises from tens of thousands to tens of millions or even billions. Fortunately, along with the growth of imagery contents, more and more resources on the Internet become available, such as the associated metadata, context and social information. In addition, the power of grassroots has been fully demonstrated in the Web 2.0 era. For example, they can easily tag and comment on millions of images and videos, as well as label millions of images via a simple game.
展开▼