The question how to integrate information from different sources in speech decoding is still only partially solved (layered architecture versus integrated search). We investigate t...
This paper proposes a new multi-exposure fusion algorithm for HDR imaging. The advantage of the fusion based method is that it does not actually generate HDR images so that the co...
Jaehyun An, Sang Heon Lee, Jung Gap Kuk, Nam Ik Ch...
We explore automated discovery of topicallycoherent segments in speech or text sequences. We give two new discriminative topic segmentation algorithms which employ a new measure o...
— We present theory, design and measurement results for an on-line histogram equalization algorithm implemented on a 750MS/s 6b flash analog to digital converter in standard 0.3...
This paper proposes novel hierarchical self-organizing associative memory architecture for machine learning. This memory architecture is characterized with sparse and local interco...