Learn More
A significant weakness of most current deep Convolutional Neural Networks is the need to train them using vast amounts of manually labelled data. In this work we propose a unsupervised framework to learn a deep convolutional neural network for single view depth prediction , without requiring a pre-training stage or annotated ground truth depths. We achieve(More)
Recent innovations in training deep convolutional neu-ral network (ConvNet) models have motivated the design of new methods to automatically learn local image descrip-tors. The latest deep ConvNets proposed for this task consist of a siamese network that is trained by penalising misclas-sification of pairs of local image patches. Current results from(More)
Generally face images may be visualized as points drawn on a low-dimensional manifold embedded in high-dimensional ambient space. Many dimensionality reduction techniques have been used to learn this manifold. Orthogonal locality preserving projection (OLPP) is one among them which aims to discover the local structure of the manifold and produces orthogonal(More)
As Sensor networks are being used in remote environment monitoring, healthcare, machine automation, security of these networks is becoming a central concern. Till now main concern was to make sensor networks useful and deployable and little emphasis was placed on security. This paper analyses security issues and vulnerabilities in wireless sensor networks.(More)
In this paper we introduce a supervised, maximum margin framework for linear and non-linear Non-negative Matrix Factorization. By contrast to existing methods in which the matrix factorization phase (i.e. the feature extraction phase) and the classification phase are separated, we incorporate the maximum margin classification constraints within the NMF(More)
Due to increasing crime rate identification using biometrics has become an important field of research. When it is not possible to take snapshot, to read iris, to take finger prints etc then identification using gait may be proved an effective tool to identify a person. This paper presents a method which distinguishs between normal and abnormal gait. A(More)
In this paper, we propose a maximum-margin framework for classification using Non-negative Matrix Factorization. In contrast to previous approaches where the classification and matrix factorization stages are separated, we incorporate the maximum margin constraints within the NMF formulation, i.e we solve for a base matrix that maximizes the margin of the(More)