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.
Detecting actions in untrimmed videos is an important yet challenging task. In this paper, we present the structured segment network (SSN), a novel framework which models the temporal structure of each action instance via a structured temporal pyramid. On top of the pyramid, we further introduce a decomposed discriminative model comprising two classifiers, respectively for classifying actions and...
Semi-supervised Learning as an efficient paradigm has been applied to many research areas, it also becomes one of the research focuses in machine learning and knowledge discovery. Traditionally, most classification models are built by supervised learning procedure, which leads to high rate of misclassification when test samples are significantly more than the training samples. This paper proposed...
In order to get rid of the limit of traditional methods and provide a decision making reference for the supervision of securities organizations and the risk control of investors, A novel model based on SOM2W network (SOM with 2 winners self-organizing map) is proposed for assessment financial performance of the listed companies. In addition, a tabu-mapping method is proposed to avoid that the same...
Mastering knowledge of user profile is one of the technical cornerstones for service providers who handle a large amount of service consumption data and are well positioned to dynamically infer user interests. This paper presents a technology allowing to gather usage data from different multimedia services, create and track users profiles in real-time and monetize them by targeting content or other...
Atmospheric quality assessment is an important research subject, focusing on the evaluation of the quality of atmospheric environment, a model based on the immune algorithm (IM) is proposed in this paper. The model has the characters of pellucid principle and physical explication. Moreover, the simplification is the important advantage of the method. Experimental results show that the proposed model...
An improved model based on Kohonen neural network, called self-organizing map neural network with two winners (SOM2W), is applied to assess stock companies in this paper. In addition, in order to improve the precision of solutions, tabu-mapping method is also used to avoid that the same output node is mapped by more than one input. The clustering analysis for the stock is also done by using SOM2W...
In order to obtain a reasonable method for new share pricing, new hybrid models based on self-organizing map with 2 winners (SOM2W) and radial basis function (RBF) neural network with characteristics of intelligence are proposed and applied to new share pricing in this paper. To enhance the dynamic competition and clustering capability of SOM2W network, and improve the precision of solutions, a tabu-mapping...
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.