Example-based learning of codes that statistically encode general image classes is of vital importance for computational vision. Recently, non-negative matrix factorization (NMF) ...
This work is about scene interpretation in the sense of detecting and localizing instances from multiple object classes. We concentrate on object indexing: generate an over-comple...
Statistical methods, such as independent component analysis, have been successful in learning local low-level features from natural image data. Here we extend these methods for le...
This paper discusses theoretical and experimental aspects of gradient-based approaches to the direct optimization of policy performance in controlled ??? ?s. We introduce ??? ?, a...
In this paper we propose a novel image contrast enhancement method using collaborative learning. Block-based histogram equalization methods such as contrast limited adaptive histo...
Yuchou Chang, Dah-Jye Lee, James K. Archibald, Yi ...