As common weather, rain streaks adversely degrade the image quality and tend to negatively affect the performance of outdoor computer vision systems. Hence, removing rains from an image has become an ...important issue in the field. To handle such an ill-posed single image deraining task, in this article, we specifically build a novel deep architecture, called rain convolutional dictionary network (RCDNet), which embeds the intrinsic priors of rain streaks and has clear interpretability. In specific, we first establish a rain convolutional dictionary (RCD) model for representing rain streaks and utilize the proximal gradient descent technique to design an iterative algorithm only containing simple operators for solving the model. By unfolding it, we then build the RCDNet in which every network module has clear physical meanings and corresponds to each operation involved in the algorithm. This good interpretability greatly facilitates an easy visualization and analysis of what happens inside the network and why it works well in the inference process. Moreover, taking into account the domain gap issue in real scenarios, we further design a novel dynamic RCDNet, where the rain kernels can be dynamically inferred corresponding to input rainy images and then help shrink the space for rain layer estimation with few rain maps, so as to ensure a fine generalization performance in the inconsistent scenarios of rain types between training and testing data. By end-to-end training such an interpretable network, all involved rain kernels and proximal operators can be automatically extracted, faithfully characterizing the features of both rain and clean background layers and, thus, naturally leading to better deraining performance. Comprehensive experiments implemented on a series of representative synthetic and real datasets substantiate the superiority of our method, especially on its well generality to diverse testing scenarios and good interpretability for all its modules, compared with state-of-the-art single image derainers both visually and quantitatively. Code is available at https://github.com/hongwang01/DRCDNet .
A family of algorithms for time series classification (TSC) involve running a sliding window across each series, discretising the window to form a word, forming a histogram of word counts over the ...dictionary, then constructing a classifier on the histograms. A recent evaluation of two of this type of algorithm, Bag of Patterns (BOP) and Bag of Symbolic Fourier Approximation Symbols (BOSS) found a significant difference in accuracy between these seemingly similar algorithms. We investigate this phenomenon by deconstructing the classifiers and measuring the relative importance of the four key components between BOP and BOSS. We find that whilst ensembling is a key component for both algorithms, the effect of the other components is mixed and more complex. We conclude that BOSS represents the state of the art for dictionary-based TSC. Both BOP and BOSS can be classed as bag of words approaches. These are particularly popular in Computer Vision for tasks such as image classification. We adapt three techniques used in Computer Vision for TSC: Scale Invariant Feature Transform; Spatial Pyramids; and Histogram Intersection. We find that using Spatial Pyramids in conjunction with BOSS (SP) produces a significantly more accurate classifier. SP is significantly more accurate than standard benchmarks and the original BOSS algorithm. It is not significantly worse than the best shapelet-based or deep learning approaches, and is only outperformed by an ensemble that includes BOSS as a constituent module.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, UILJ, UKNU, UL, UM, UPUK
Anomaly detection of a hyperspectral image without any prior information has attracted much more attention in remote sensing image understanding and interpretation, which aims at determining whether ...a sample belongs to background or anomaly. Low-rank dictionary learning plays an important role in exploiting the low-rank prior of background for hyperspectral image (HSI) anomaly detection. In this article, the low-rank dictionary learning is introduced to learn a dictionary which can reconstruct the background positively, while anomaly cannot. Considering the high correlation of data especially between the adjacent bands, we resort to spectral-difference low-rank dictionary representation learning for global background modeling which can fully exploit the low-rank prior of background. Then, the residual matrix is used to distinguish anomaly. Different from the existing anomaly detection methods based on dictionary which is constructed or learned in a separated step, our proposed model can simultaneously learn the dictionary and separate anomaly by iterative learning. The experimental results on five real data sets demonstrate the superior performance of the proposed method for hyperspectral anomaly detection compared with other state-of-the-art algorithms.
The article is devoted to a brief overview of bilingual dictionaries of Tatar language of the 21st century, in particular 2000-2017. The main objective of this study is to define the basic tendencies ...of development of Tatar bilingual lexicography of the new century, which develops mainly according to a traditional direction that was laid by the lexicographers of the 19th–20th centuries: published translation dictionaries for the general population and for highly specialized industries. The study provides the author's classification of printed translation dictionaries related to a selected segment of the history of Tatar lexicography.
El artículo está dedicado a una breve reseña de los diccionarios bilingües de la lengua tártara del siglo XXI, en particular 2000-2017. El objetivo principal de este estudio es definir las tendencias básicas de desarrollo de la lexicografía bilingüe tártara del nuevo siglo, que se desarrolla principalmente de acuerdo con una dirección tradicional que trazaron los lexicógrafos de los siglos XIX-XX: diccionarios de traducción publicados para la población en general y para industrias altamente especializadas. El estudio proporciona la clasificación del autor de los diccionarios de traducción impresos que están relacionados con un segmento seleccionado de la historia de la lexicografía tártara.
In histopathological image analysis, feature extraction for classification is a challenging task due to the diversity of histology features suitable for each problem as well as presence of rich ...geometrical structures. In this paper, we propose an automatic feature discovery framework via learning class-specific dictionaries and present a low-complexity method for classification and disease grading in histopathology. Essentially, our Discriminative Feature-oriented Dictionary Learning (DFDL) method learns class-specific dictionaries such that under a sparsity constraint, the learned dictionaries allow representing a new image sample parsimoniously via the dictionary corresponding to the class identity of the sample. At the same time, the dictionary is designed to be poorly capable of representing samples from other classes. Experiments on three challenging real-world image databases: 1) histopathological images of intraductal breast lesions, 2) mammalian kidney, lung and spleen images provided by the Animal Diagnostics Lab (ADL) at Pennsylvania State University, and 3) brain tumor images from The Cancer Genome Atlas (TCGA) database, reveal the merits of our proposal over state-of-the-art alternatives. Moreover, we demonstrate that DFDL exhibits a more graceful decay in classification accuracy against the number of training images which is highly desirable in practice where generous training is often not available.
Zero-shot learning (ZSL) aims to recognize images of novel classes, but does not use any images belonging to the novel classes during model training, which is realized by exploiting the auxiliary ...semantic information. Recently, most ZSL methods focus on learning visual-semantic embeddings to transfer knowledge from the seen classes to the novel classes. Visual-semantic embedding is usually established based on the visual features of images and the semantic information of classes, i.e., class attributes. However, image features are extracted at the individual level, while class attributes are obtained at the group level, so the granularity of these features is different, which makes it difficult to match the two kinds of features. To tackle such problem, we propose hierarchical coupled discriminative dictionary learning (HCDDL) method to hierarchically establish visual-semantic embedding at class-level and image-level with a coarse-to-fine way. Firstly, a class-level coupled dictionary is trained to build basic and coarse-grained connection between visual space and semantic space. Using the class-level coupled dictionary, image attributes are generated. Based on the fine-grained image attributes and images features, an image-level coupled dictionary is learned. In addition, during the learning of hierarchical coupled dictionaries, the discriminative losses are adopted to ensure dictionaries learn more accurate representation, which is beneficial to the recognition task. Recognition of unseen images is performed through searching the class nearest to the unseen image in multiple spaces. Experiments on four widely used benchmark datasets show the effectiveness of the proposed method, and sufficient ablation experiments demonstrate that the coarse-to-fine way leads to good performances.
Limburgish is a regional language in the Limburg region consisting mostly of the Belgian and Dutch provinces of Limburg. The discussion will be on the Dutch province of Limburg where Limburgish has ...received some legal recognition as a language. It is desirable to have a Dutch–Limburgish legal dictionary to communicate Dutch law, although Limburgish legal termi-nology is not a working legal language in any legal system. Special structures and data are needed to collect accessible contents for a Dutch–Limburgish legal dictionary. However, there is no blueprint to create a bilingual legal dictionary for a single jurisdiction. Therefore, this paper first considers some options for the design of the intended dic-tionary before going into possible sources for Dutch and Limburgish data. The concluding remarks deal with the immediate challenges to be overcome before reaching the production stage of a useful and fully-fledged Dutch–Limburgish legal dictionary.
Abstract
Linguistic resources available in the form of open data are an essential source of information for creating e-dictionaries, but access to these linguistic resources is still limited. This ...paper presents a method for maximising use of open access linguistic resources and integrating them into specialised e-dictionaries. The method combines automatic compilation of terminology data with the creation of specialised linguistic corpora to produce a Catalan version of the IATE (InterActive Terminology for Europe) database. The paper presents new methodological advances applied here to the production of terminological e-dictionaries, using open access linguistic resources. We observe that, as a result of this new methodology, the Catalan version of the IATE will be able to include specialised economics, law and health dictionaries. In conclusion, the new methodology presented here permits the creation of new models of specialised e-dictionaries, facilitates the compilation of terminology in any language and unifies the access format for terminology data.
The overriding theme of this work is that women’s struggles, human rights, myths, and literary expression are indispensable to an understanding of the modern culture and socio-political development ...of the Middle East region. The work demonstrates that no aspect of Middle Eastern history and modern evolution was shaped in isolation of women’s lives and contributions to society. The dictionary covers the biographies and written work of prominent historical female figures in the Middle East and North Africa, as well as 20th-century feminists, both male and female, who advanced women’s rights over many years. The Historical Dictionary of Women in the Middle East and North Africa includes a chronology, an introductory essay, an extensive bibliography, and a dictionary section that has over 400 cross-referenced entries on various aspects of Middle Eastern feminism and culture, touching upon religious themes such as Sharia laws, Islamic marriage, divorce, and inheritance practices. This book is an excellent access point for students, researchers, and anyone wanting to know more about the culture and history of women in the Middle East and North Africa.