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.
Crowdsourcing services make it possible to collect huge amount of annotations from less trained crowd workers in an inexpensive and efficient manner. However, unlike making binary or pairwise judgements, labeling complex structures such as ranked lists by crowd workers is subject to large variance and low efficiency, mainly due to the huge labeling space and the annotators' non-expert nature. Yet...
Very deep neural networks with hundreds or more layers have achieved significant success in a variety of vision tasks spanning from image classification, detection, to image captioning. However, simply stacking more layers in the convolution operation could suffer from the gradient vanishing problem and thus could not lower down the training loss further. The residual network [1] pushes the model's...
Image retrieval and classification are hot topics in computer vision and have attracted great attention nowadays with the emergence of large-scale data. We propose a new scheme to use both deep learning models and large-scale computing platform and jointly learn powerful feature representations in image classification and retrieval. We achieve a superior performance on the ImageNet dataset, where...
Recently, establishment and maintenance of the tax assessment indicators system is still in the stage of manual operation. The accuracy of tax assessment depends on the officials' judgment and analysis which bring them huge amount of work. Furthermore, the evaluation results are affected by manual factors and not reliable. To improve tax assessment, this paper proposes a tax assessment model based...
Tax risk management is a new business field of tax management, which has become the core task of professional revenue management. As the traditional tax payment model has shortcoming of inefficiency and high cost, it is necessary to create a stable and orderly management environment to identify tax risks for different taxpayers quickly and efficiently. In this paper, the theory of machine learning...
Almost all unbalanced classification algorithms focus on how to maximize the balance degree of the data set, which means to remove those negative samples that are useless for classifier training while keeping the positive samples and useful samples as many as possible. However, we find that the best balance degree is not necessary with the highest classification accuracy. In this paper, we propose...
Rotten and greasy coating on tongue is one of the most salient features reflecting inner health of body, which is widely used in observe diagnosis in Traditional Chinese Medicine (TCM). This paper is mainly concentrated on the classification of two tongue coating states: rotten and greasy. As it is an unbalanced classification and texture recognition problem, method of random oversampling, Gabor feature...
Good feature extraction scheme and classifiers are the key to face recognition algorithms. A general and efficient face feature extraction approach is presented which utilizes linear discriminant information and global search strategy. In order to get rid of redundant information and meanwhile reduce computational burden, we first compute the nonzero feature space of scatter matrix of the training...
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.