Serwis Infona wykorzystuje pliki cookies (ciasteczka). Są to wartości tekstowe, zapamiętywane przez przeglądarkę na urządzeniu użytkownika. Nasz serwis ma dostęp do tych wartości oraz wykorzystuje je do zapamiętania danych dotyczących użytkownika, takich jak np. ustawienia (typu widok ekranu, wybór języka interfejsu), zapamiętanie zalogowania. Korzystanie z serwisu Infona oznacza zgodę na zapis informacji i ich wykorzystanie dla celów korzytania z serwisu. Więcej informacji można znaleźć w Polityce prywatności oraz Regulaminie serwisu. Zamknięcie tego okienka potwierdza zapoznanie się z informacją o plikach cookies, akceptację polityki prywatności i regulaminu oraz sposobu wykorzystywania plików cookies w serwisie. Możesz zmienić ustawienia obsługi cookies w swojej przeglądarce.
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...
Recent low-rank based matrix/tensor recovery methods have been widely explored in multispectral images (MSI) denoising. These methods, however, ignore the difference of the intrinsic structure correlation along spatial sparsity, spectral correlation and non-local self-similarity mode. In this paper, we go further by giving a detailed analysis about the rank properties both in matrix and tensor cases,...
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...
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...
Recently, zero-shot action recognition (ZSAR) has emerged with the explosive growth of action categories. In this paper, we explore ZSAR from a novel perspective by adopting the Error-Correcting Output Codes (dubbed ZSECOC). Our ZSECOC equips the conventional ECOC with the additional capability of ZSAR, by addressing the domain shift problem. In particular, we learn discriminative ZSECOC for seen...
Short-term tracking is an open and challenging problem for which discriminative correlation filters (DCF) have shown excellent performance. We introduce the channel and spatial reliability concepts to DCF tracking and provide a novel learning algorithm for its efficient and seamless integration in the filter update and the tracking process. The spatial reliability map adjusts the filter support to...
Testability optimization is an important part of testability design. In the past, testability optimization design often neglects the correlation between testability and reliability and does not pay much attention to the influence of system reliability. Considering such circumstance, this paper studies the impact of the basic reliability of the system and the Built-In Test (BIT) working mode. Different...
In this paper, we propose a joint analog-digital (AD) beamforming scheme that exploits the mutual coupling effect to further improve the performance of multi-user multiple-input single-output (MU-MISO) systems. We firstly propose a joint AD scheme by iteratively optimizing the beamforming vectors in the digital domain and the load impedances of each antenna element in the analog domain. We further...
Sparse unmixing of hyperspectral data is an important technique which aims at estimating the fractional abundances of endmembers (pure spectral components). It is well known that enforcing sparseness becomes a necessary process in sparse unmixing methods. To better exploit the sparsity in hyperspectral imagery, a double reweighted sparse unmixing algorithm has been proposed. However, it focusses on...
The Euclid distance based K-means clustering is among the hard classification algorithms. When dealing with deterministic remote sensing data, it is difficult to gain satisfactory classification results using K-means algorithm. The traditional K-means clustering algorithm is faced with several shortcomings such as locally converged optimization, being sensitive to initial clustering centers, etc....
Variables in chemical process are mutually affected and chemical process failures are often caused by the chain effect of a number of variables, so some minor changes in variables can often lead to an unknown fault. In this paper, the multivariable correlations are studied from the perspective of the whole process, and PCC (Pearson Correlation Coefficient) is used to calculate the correlation coefficient...
Cross-media retrieval, which uses a text query to search for images and vice-versa, has attracted a wide attention in recent years. The mostly existing cross-media retrieval methods aim at finding a common subspace and maximizing different modalities correlations. But these approaches do not directly capture the underlying semantic information of different modalities. This paper proposes a novel cross-media...
Contour detection is a fundamental problem in computer vision. However, there is still a considerable disparity between detection results and actual contours. To detect object-level contours on the basis of comprehensive analysis of potential edges, we present a deep-learning-based approach with a conditional random fields (CRF) model. We obtain the initial edgemap with a VGGNet-based model, and establish...
This paper addresses the problem of joint detection and estimation fusion when sensor quantized data are correlated in the distributed system. The traditional methods to handle this joint problem tend to treat the detection and estimation tasks separately, which put more emphasis on the detection part but treat the estimation part sub-optimally. In this work, the joint detection and estimation fusion...
Multiple view data with different feature representations have widely arisen in various practical applications. Due to the information diversity, fusing multiview features is very valuable for classification purpose. In this paper, we propose a new multifeature fusion method called fractional-order discriminative multiview correlation projection (FDMCP), which is based on fractional-order scatter...
Feature fusion plays an important role in target recognition, especially when single sensor's recognition capability is limited under severe situations. In view of shortcomings of Multi-set Canonical Correlation Analysis (MCCA) and its supervised modified methods in using category information in fusion projection rule learning, a generalized discriminative learning version of MCCA, termed as GDMCCA,...
This paper addresses the problem of joint source and channel coding for 3-D video coding and transmission. Firstly, we formulate a packet-level joint texture and depth coding mode selection framework for error-resilient source coding using Lagrange multiplier. Then, we evolve to the more general formulation that jointly optimizes error-resilient source coding and channel coding for texture and depth...
There are two ways to improve the D-S evidence theory, the methods based on modification for Dempster rule, and the methods based on modification for original evidence sources. For modification of evidence sources, there are mainly two methods: discounting factor method and weighted average method. Although the weighted average method has better focusing degree, it ignores conflicting degree of combination...
A novel scheme with deep cross-modal correlation learning is developed in this paper to facilitate more effective Sketch-based Image Retrieval (SBIR) for large-scale annotated images. It integrates the deep multimodal feature generation, deep cross-modal correlation learning and similarity search optimization through mining all the beneficial multimodal information sources in sketches and images,...
Due to the simplicity of its implementation and the impressive performance, Extreme Learning Machine (ELM) has been widely used in applications of machine learning. However, there are two potential problems in ELM: 1) lack of an efficient method for minimizing error; 2) consideration of little inherent structural information about correlations among output components. To overcome those problems, this...
Podaj zakres dat dla filtrowania wyświetlonych wyników. Możesz podać datę początkową, końcową lub obie daty. Daty możesz wpisać ręcznie lub wybrać za pomocą kalendarza.