The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Recently, deep learning has enjoyed a great deal of success for computer vision problems due to its capability to model highly complex tasks, such as image classification, object detection, face recognition, among many others. Although these neural networks are nowadays very powerful, there is a huge amount of parameters (i.e. the model) that need to be learned and require considerable storage space...
Video summarization is an important multimedia task for applications such as video indexing and retrieval, video surveillance, human-computer interaction and video "storyboarding". In this paper, we present a new approach for automatic summarization of video collections that leverages a structured minimum-risk classifier and efficient submodular inference. To test the accuracy of the predicted...
This paper presents a novel local posture orientation-context descriptor, and proposes a FDDL(Fisher discriminant dictionary learning) method based on local orientation-preserving(LOP-FDDL) for sparse coding in action recognition task. To take full use of the information about the position of the local body-part related to the center of the torso, ant the spatial-temporal shape changes of the human...
Many rare and common genetic variants, including SNPs and CNVs, are reported to be associated with mental disorders, yet more remain to be discovered. However, despite the large amount of high-throughput genomics data, there is a lack of integrative methods to systematically prioritize variants that confer susceptibility to mental disorders in personal genomes. Here, we developed a computational tool:...
Thanks to recent advances in the field of genomics, it is now possible to create a comprehensive atlas of the basic units of life—cells. In this paper, we present a frame work for single cell genomics research which employs several new machine learning models such as convolutional neural networks, deep auto-encoder, recurrent neural networks etc. With these effective learning models on multi-source...
In biomedical research, events revealing complex relations between entities play an important role. Event trigger identification is a crucial and prerequisite step in the pipeline process of biomedical event extraction. There exist two main problems in the previous work: (1) Traditional feature-based methods often rely on human ingenuity, which is a time-consuming process. Though most representation-based...
In this paper, we propose a new discriminative dictionary learning framework, called robust Label Embedding Projective Dictionary Learning (LE-PDL), for data classification. LE-PDL can learn a discriminative dictionary and the blockdiagonal representations without using the l0-norm or l1-norm sparsity regularization, since the l0 or l1-norm constraint on the coding coefficients used in the existing...
Given an undirected network where some of the nodes are labeled, how can we classify the unlabeled nodes with high accuracy? Loopy Belief Propagation (LBP) is an inference algorithm widely used for this purpose with various applications including fraud detection, malware detection, web classification, and recommendation. However, previous methods based on LBP have problems in modeling complex structures...
Modern patient data tends to be large-scale and multi-dimensional, containing both spatial and temporal features. Learning good spatio-temporal features from large patient data is a challenging task, especially when there are missing observations. In this paper, we propose a spatio-temporal autoencoder (STAE), an unsupervised deep learning scheme, to learn features from large-scale and high-dimensional...
In conventional dictionary learning, the class label of the atoms is not retained. As a result of that, the location of non-zeros elements in the sparse vector (s-vector) does not infer about the true class of the test vector unlike the sparse representation classification (SRC) over the exemplar dictionary. Thus, in our earlier works employing the learned dictionary for language recognition (LR),...
Cross-modal hashing is usually regarded as an effective technique for large-scale textual-visual cross retrieval, where data from different modalities are mapped into a shared Hamming space for matching. Most of the traditional textual-visual binary encoding methods only consider holistic image representations and fail to model descriptive sentences. This renders existing methods inappropriate to...
The deep convolutional neural network (CNN) is the state-of-the-art solution for large-scale visual recognition. Following some basic principles such as increasing network depth and constructing highway connections, researchers have manually designed a lot of fixed network architectures and verified their effectiveness.,,In this paper, we discuss the possibility of learning deep network structures...
We propose the Anchored Regression Network (ARN), a nonlinear regression network which can be seamlessly integrated into various networks or can be used stand-alone when the features have already been fixed. Our ARN is a smoothed relaxation of a piecewise linear regressor through the combination of multiple linear regressors over soft assignments to anchor points. When the anchor points are fixed...
The deep learning neural network is a recent development that has become the subject of research in the computer vision and remote sensing disciplines. Super resolution (SR) images can be obtained using deep neural network methods that achieve a higher performance than all previous traditional methods. Here, in this study, the objective is to describe existing deep learning methods for SR satellite...
Deep neural networks (DNNs) usually demand a large amount of operations for real-time inference. Especially, fully-connected layers contain a large number of weights, thus they usually need many off-chip memory accesses for inference. We propose a weight compression method for deep neural networks, which allows values of +1 or −1 only at predetermined positions of the weights so that decoding using...
Encryption is often not sufficient to secure communication, since it does not hide that communication takes place or who is communicating with whom. Covert channels hide the very existence of communication enabling individuals to communicate secretly. Previous work proposed a covert channel hidden inside multi-player first person shooter online game traffic (FPSCC). FPSCC has a low bit rate, but it...
Learning to hash has been widely applied to approximate nearest neighbor search for large-scale multimedia retrieval, due to its computation efficiency and retrieval quality. Deep learning to hash, which improves retrieval quality by end-to-end representation learning and hash encoding, has received increasing attention recently. Subject to the ill-posed gradient difficulty in the optimization with...
For large-scale visual search, highly compressed yet meaningful representations of images are essential. Structured vector quantizers based on product quantization and its variants are usually employed to achieve such compression while minimizing the loss of accuracy. Yet, unlike binary hashing schemes, these unsupervised methods have not yet benefited from the supervision, end-to-end learning and...
We propose a gray coding method for deep neural network (DNN) based decoder. With multiple resources considered together, DNN can be used to decode corrupted signals. In deep learning training, stochastic gradient descent (SGD) algorithm is used, which means that the cost function must be differentiable. Then, allocating the discrete bits for each symbol is difficult. To solve this problem, the basic...
Sparse Modeling Representative Selection (SMRS) has been recently proposed for finding the most relevant instances in datasets. This method deploys a data self-representativeness coding in order to infer a coding matrix that is regularized with a row sparsity constraint. The method assumes that the score of any sample is set to the L2 norm of the corresponding row in the coding matrix. Since the SMRS...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.