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.
Normal adult becomes memory decline when increasing age. Memory decline can change from normal aging to mild cognitive impairment (MCI) and then Alzheimer's disease dementia. In order to reduce the risk of dementia, the cognitive training or brain training is needed. Cognitive training can stimulate the ability of normal person's memory for keeping ability of memory prompt when increasing age. Virtual...
Background noise reduction has been studied for many years. However, unwanted human speech noise suppression is not well discussed due to sparsity of the speech signal. Traditional blind source separation (BSS) methods such as independent component analysis (ICA) assume the prior knowledge of the number of sources and require that the number of sources must equal the number of sensors. Above limitations...
Aiming at the problem of fault detection for satellite communication system, a prediction method based on Gaussian mixture model is proposed. Firstly, the observation sequence is collected by modem as well as frequency conversion equipment. Then feature parameters are extracted after pre-processing. The expectation maximum algorithm is applied to train the Gaussian mixture model. The posterior probabilities...
This paper proposes an anomaly-based Intrusion Detection System (IDS), which flags anomalous network traffic with a distance-based classifier. A polynomial approach was designed and applied in this work to extract hidden correlations from traffic related statistics in order to provide distinguishing features for detection. The proposed IDS was evaluated using the well-known KDD Cup 99 data set. Evaluation...
Recently, kernelized correlation Filter-based trackers have aroused the interest of many researchers and achieved good results in the field of tracking. However, the current tracking model based on kernelized correlation filters can not deal with the changes of the target appearance and scale effectively. Therefore, in this paper, we intend to solve these two problems and improve the robustness of...
To reduce data-storage costs and enhance high accuracy of industrial process fault detection, a data driven fault diagnosis method is proposed based on diffusion maps and hidden Markov model. Firstly, the correlation dimension of sample data is calculated. Secondly, the high-dimensional eigenvectors are extracted into low-dimensional manifold space by diffusion maps. Finally, the low-dimensional eigenvectors...
In software and IT systems engineering, personal characteristics are expected to impact performance and attitude. To clarify the optimal composition in a team of students in academic education, we researched the relationship between student personality characteristics and learning effectiveness of teams using the Five Factor and Stress theory (FFS). The results taken from a Project-based Learning...
End-to-end training from scratch of current deep architectures for new computer vision problems would require Imagenet-scale datasets, and this is not always possible. In this paper we present a method that is able to take advantage of freely available multi-modal content to train computer vision algorithms without human supervision. We put forward the idea of performing self-supervised learning of...
The Correlation Filter is an algorithm that trains a linear template to discriminate between images and their translations. It is well suited to object tracking because its formulation in the Fourier domain provides a fast solution, enabling the detector to be re-trained once per frame. Previous works that use the Correlation Filter, however, have adopted features that were either manually designed...
Most existing weakly supervised localization (WSL) approaches learn detectors by finding positive bounding boxes based on features learned with image-level supervision. However, those features do not contain spatial location related information and usually provide poor-quality positive samples for training a detector. To overcome this issue, we propose a deep self-taught learning approach, which makes...
In linear representation-based image classification, an unlabeled sample is represented by the entire training set. To obtain a stable and discriminative solution, regularization on the vector of representation coefficients is necessary. For example, the representation in sparse representation-based classification (SRC) uses L1 norm penalty as regularization, which is equal to lasso. However, lasso...
We propose a novel and principled hybrid CNN+CRF model for stereo estimation. Our model allows to exploit the advantages of both, convolutional neural networks (CNNs) and conditional random fields (CRFs) in an unified approach. The CNNs compute expressive features for matching and distinctive color edges, which in turn are used to compute the unary and binary costs of the CRF. For inference, we apply...
Given a state-of-the-art deep neural network classifier, we show the existence of a universal (image-agnostic) and very small perturbation vector that causes natural images to be misclassified with high probability. We propose a systematic algorithm for computing universal perturbations, and show that state-of-the-art deep neural networks are highly vulnerable to such perturbations, albeit being quasi-imperceptible...
Multi-label classification is a vital problem, as it has numerous applications in computer vision, such as automatic image annotation. The label set for each instance is always assumed to be in the original whole form. However, missing labels often occur because manual labelling is a time-consuming and label-intensive work in the case of large amount of data. The incompleteness of labels can certainly...
In this paper, we propose an approach to the domain adaptation, dubbed Second-or Higher-order Transfer of Knowledge (So-HoT), based on the mixture of alignments of second-or higher-order scatter statistics between the source and target domains. The human ability to learn from few labeled samples is a recurring motivation in the literature for domain adaptation. Towards this end, we investigate the...
Multi-instance multi-label (MIML) learning has many interesting applications in computer visions, including multi-object recognition and automatic image tagging. In these applications, additional information such as bounding-boxes, image captions and descriptions is often available during training phrase, which is referred as privileged information (PI). However, as existing works on learning using...
The CNN-RNN design pattern is increasingly widely applied in a variety of image annotation tasks including multi-label classification and captioning. Existing models use the weakly semantic CNN hidden layer or its transform as the image embedding that provides the interface between the CNN and RNN. This leaves the RNN overstretched with two jobs: predicting the visual concepts and modelling their...
Linking two data sources is a basic building block in numerous computer vision problems. Canonical Correlation Analysis (CCA) achieves this by utilizing a linear optimizer in order to maximize the correlation between the two views. Recent work makes use of non-linear models, including deep learning techniques, that optimize the CCA loss in some feature space. In this paper, we introduce a novel, bi-directional...
This paper proposes a novel tracker which is controlled by sequentially pursuing actions learned by deep reinforcement learning. In contrast to the existing trackers using deep networks, the proposed tracker is designed to achieve a light computation as well as satisfactory tracking accuracy in both location and scale. The deep network to control actions is pre-trained using various training sequences...
We propose an extremely simple but effective regularization technique of convolutional neural networks (CNNs), referred to as BranchOut, for online ensemble tracking. Our algorithm employs a CNN for target representation, which has a common convolutional layers but has multiple branches of fully connected layers. For better regularization, a subset of branches in the CNN are selected randomly for...
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.