Large-scale, ground-level urban imagery has recently developed as an important element of online mapping tools such as Google’s Street View. Such imagery is extremely valuable i...
The paper introduces a new framework for feature learning in classification motivated by information theory. We first systematically study the information structure and present a n...
The detection of people is one of the foremost problems for indexing, browsing and retrieval of video. The main difficulty is the large appearance variations caused by action, clot...
We introduce a new approach to image reconstruction from highly incomplete data. The available data are assumed to be a small collection of spectral coef?cients of an arbitrary li...
Karen O. Egiazarian, Alessandro Foi, Vladimir Katk...
With the explosive growth of Web and the recent development in digital media technology, the number of images on the Web has grown tremendously. Consequently, Web image clustering...