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.
Networks are models representing relationships between entities. Often these relationships are explicitly given, or we must learn a representation which generalizes and predicts observed behavior in underlying individual data (e.g. attributes or labels). Whether given or inferred, choosing the best representation affects subsequent tasks and questions on the network. This work focuses on model selection...
Big data analysis has been pervasively adopted as a method to analyze the tremendous amount of daily generated high throughput data in an efficient and accurate manner. Among the series of tools available in the field of big biomedical data, correlation networks are one of the most powerful tools for modelling gene expression, which is important in the study of disease and ageing. With the help of...
Visual tracking is a very challenging problem in computer vision as the performance of a tracking algorithm may be degraded due to many challenging issues in the scenes, such as illumination change, deformation, and background clutter. So far no algorithms can handle all these challenging issues. Recently, it has been shown that correlation filters can be implemented efficiently and, with suitable...
Visual tracking is a challenging task due to a number of factors, such as occlusions, deformations, illumination variations and abrupt motion changes present in a video sequence. Generally, trackers are robust to some of these factors, but do not achieve satisfactory results when dealing with multiple factors at the same time. More robust results when multiple factors are present can be obtained by...
In this paper, the problem of single-channel blind source separation (SCBSS) of a mixture of two co-frequency phase-shift keying (PSK) signals with unknown carrier frequency offsets (CFOs) is investigated. Two SCBSS algorithms which are robust to CFOs are proposed to perform separation of the mixture signals. In the first algorithm, the phase changes of the received signals caused by CFOs are tracked...
Part-based trackers are effective in exploiting local details of the target object for robust tracking. In contrast to most existing part-based methods that divide all kinds of target objects into a number of fixed rectangular patches, in this paper, we propose a novel framework in which a set of deformable patches dynamically collaborate on tracking of non-rigid objects. In particular, we proposed...
Learning similarity functions between image pairs with deep neural networks yields highly correlated activations of large embeddings. In this work, we show how to improve the robustness of embeddings by exploiting independence in ensembles. We divide the last embedding layer of a deep network into an embedding ensemble and formulate training this ensemble as an online gradient boosting problem. Each...
Non-linear methods are usually used to analyze and process random sequences with outliers or in presence of impulsive noise. One of these methods is based on order statistics, which includes rank information by increasing the problem size. In this article we use a rank one quadratic measurement model based on sketches and apply it to order statistics. We introduce a method to estimate the correlation...
Bearings have been widely used with the broad application of rotating machines. Hence, in order to increase the efficiency, reliability and safety of rotating machinery, condition monitoring of bearings is significant during the operation. However, due to the influence of high background noise and components slippage, incipient faults are difficult to detect. With the continuous research on the bearing...
In this paper, we introduce a novel message hiding scheme for the purpose of authentication inside images. The hiding process is performed by means of insertion in the frequency domain of Discrete Cosine Transform. By employing a type of sequences with well-defined, low cross-correlation values to encode information, we were able to embed messages inside images. Furthermore, it is also possible to...
Visual object tracking is one of the basic units in the construction of smart cities, which focuses on establishing a dynamic appearance model to represent and recognize the target in complex scenarios. In this paper, we consider visual object tracking as multiple local patches matching problem and design an online tracker based on correlation filter and binary descriptors. We integrate binary descriptors...
In this paper, a target detection procedure with global error control is proposed. The novelty of this approach consists in taking into account spatial structures of the target while ensuring proper error control over pixelwise errors. A generic framework is discussed and a method based on this framework is implemented. Results on simulated data show conclusive gains in detection power for a nominal...
This paper considers a multi-user multiple-input multiple-output (MU-MIMO) visible light communication (VLC) interference channel. The multi-user interference (MUI) can be successfully eliminated with the perfect knowledge of channel state information (CSI). However, the perfect information may not be available at transmitter, which will lead to severe interference and consequently degrade the system...
In object tracking, a novel tracking framework which is called “Tracking-Leaning-Detection” was proposed by Zdenka Kalal. This framework decomposes the object tracking task into tracking, learning and detection. In every frame that follows, the tracker and the detector work simultaneously to obtain the location of the object independently, and the learning acts as an information exchanging center...
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...
Learning robust regression model from high-dimensional corrupted data is an essential and difficult problem in many practical applications. The state-of-the-art methods have studied low-rank regression models that are robust against typical noises (like Gaussian noise and out-sample sparse noise) or outliers, such that a regression model can be learned from clean data lying on underlying subspaces...
We propose a new tracking framework with an attentional mechanism that chooses a subset of the associated correlation filters for increased robustness and computational efficiency. The subset of filters is adaptively selected by a deep attentional network according to the dynamic properties of the tracking target. Our contributions are manifold, and are summarised as follows: (i) Introducing the Attentional...
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...
In recent years, Deep Learning has been successfully applied to multimodal learning problems, with the aim of learning useful joint representations in data fusion applications. When the available modalities consist of time series data such as video, audio and sensor signals, it becomes imperative to consider their temporal structure during the fusion process. In this paper, we propose the Correlational...
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...
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.