Modern embedded Systems-on-a-Chip deploy multiple programmable cores to meet increasing performance requirements of video, graphics, and modem applications. However, software implementations of task scheduling and inter-task synchronization often limit performance improvements of multicores. Remarkably, several demanding video applications (e.g. H.264 video decoding) rely on task dependency gra...

State-of-the-art word embeddings, which are often trained on bag-of-words (BOW) contexts, provide a high quality representation of aspects of the semantics of nouns. However, their quality decreases substantially for the task of verb similarity prediction. In this paper we show that using symmetric pattern contexts (SPs, e.g., “X and Y”) improves word2vec verb similarity performance by up to 15...

While many pattern recognition algorithms have been developed in the last forty years, classifying images/videos in practical applications still faces the challenges of self/mutual occlusions, clustered backgrounds, illumination variations, etc. In order to improve the recognition performance, many systems are designed by fusing multiple complementary features for various classification tasks. ...

From the accumulated results, we hypothesize that neurons in the central processor systems of the brain generally exhibit a common state-dependency in slow dynamics of their spontaneous activities during sleep. In this paper, activities of relay cells in the cat's lateral geniculate nucleus (LGN) were studied to see if our hypothesis can be applied in this thalamic region. Data segments in poly...

The Composite design pattern is a well-known implementation of whole-part relationships with trees of Composite objects. This paper presents a permission-based speci cation of the Composite pattern that allows nodes in an object hierarchy to depend on invariants over their children while permitting clients to add new children to any node in the hierarchy at any time. Permissions can capture the...

Kernel learning is a popular research topic in pattern recognition and machine learning. Kernel selection is a crucial problem endured by kernel learning method in the practical applications. Many methods of finding the optimal parameters have been presented, but this kind of methods have no ability of changing the kernel structure, accordingly without changing the data distribution in kernel m...

Single sensor with Bayer pattern color filters are used to reduce size and cost of consumer digital cameras. These cameras use various demosaicing algorithms to construct the entire image with true colors from the acquired insufficient RGB (Red,Green and Blue) mosaics. In order to estimate original true colors, iterative demosaicing algorithms are being employed. These algorithms incur high cos...