Recent years, the Cloud computing technologies have become more and more important for many existing database applications. The Cloud platform provides an ease to use interface between providers and users, allow providers to develop and provide software and databases for users over locations. Currently, there are many Cloud platform providers support large-scale database services. However, most...

We present a structured inference approach in deep neural networks for multiple attribute prediction. In attribute prediction, a common approach is to learn independent classifiers on top of a good feature representation. However, such classifiers assume conditional independence on features and do not explicitly consider the dependency between attributes in the inference process. We propose to ...

Attribute Grammars are the specification language of many tools that automatically generate programming language implementations. We consider the problem of verifying properties of attribute grammar specifications, particularly properties that are not well supported by existing tools. Rather than propose methods for extending existing tool implementation techniques, we propose the use of off-th...

The existing digital rights management (DRM) schemes in cloud computing introduce a heavy computation overhead on the content provider for key distribution. In this paper, we propose an attribute-based DRM scheme in cloud computing by combining the techniques of ciphertextpolicy attribute-based encryption (CP-ABE) and proxy reencryption (PRE). We first divide the content encryption key into two...

The k-Nearest Neighbour (k-NN) method is a typical lazy learning paradigm for solving classification problems. Although this method was originally proposed as a non-parameterised method, attribute weight setting has been commonly adopted to deal with irrelevant attributes. In this paper, we propose a new attribute weight setting method for k-NN based classifiers using quadratic programming, whi...

and foreword: People like to assign the attribute speed (i. e. performance) not only to hardware but also to software. But software does not have an attribute speed. Software defines for each user initiated task a sequence of information processing steps (machine instructions) to be performed. A suitable term for the aspect under construction can only be found when having a second imlementation...

Integrating phonetic knowledge into a speech recognizer is a possible way to further improve the performance of conventional HMM-based speech recognition methods. This paper presents a cascaded architecture which consists of attribute detection and conditional random field to make use of phonetic knowledge within the phone decoding process. The attribute detection can be implemented by using an...

Humans focus attention on different face regions when recognizing face attributes. Most existing face attribute classification methods use the whole image as input. Moreover, some of these methods rely on fiducial landmarks to provide defined face parts. In this paper, we propose a cascade network that simultaneously learns to localize face regions specific to attributes and performs attribute ...