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.
Salient object detection has been greatly boosted thanks to the deep convolutional neural networks (CNN), especially fully convolutional neural networks (FCN). Nowadays, it is possible to train an end-to-end deep model for salient object detection. However, the diverse scales of salient objects still pose major challenges for these state-of-the-art methods. In this paper, we investigate how different...
Opinion target extraction aims to find the object to which an opinion is expressed. It is helpful in getting a comprehensive understanding about public opinions on hot spot social events. In Chinese microblog posts analysis, due to the absence of words with emotional tendency (opinion words), traditional approaches relying on opinion words are not suitable. In this paper, we propose an unsupervised...
A key problem in salient object detection is how to effectively exploit the multi-level saliency cues in a unified and data-driven manner. In this paper, building upon the recent success of deep neural networks, we propose a fully convolutional neural network based approach empowered with multi-level fusion to salient object detection. By integrating saliency cues at different levels through fully...
Taking the construction of STKOS (Science and Technology Knowledge Organization System) Service System in Intelligence 3.0 as the mainline, this paper first analyzes various functions that the system shall have, and designs the overall architecture of the system. Second, it introduces the implementation of the system from the perspectives of STKOS registration, triple retrieval, visual presentation...
Classification of microarray data has always been a challenging task due to the enormous number of genes. Finding a small, closely related gene set to accurately classify disease cells is an important research problem. Integrating biological knowledge into genomic analysis to help to improve the interpretation of the results is an effective approach. In this paper, affinity propagation (AP) clustering...
Sentiment lexicon is the core of many academic and commercial sentiment analysis system. But compared with the plentiful English sentiment resources, Chinese sentiment lexicon is scarce which limits the application of lexicon-based method in Chinese sentiment analysis.
In Web2.0, users become the adaptive agents of knowledge architecture. As a result, knowledge architectu??re and services get restored to their original state of human-oriented and furthermore, personal knowledge architecture becomes a process of self-organization. This provides a favorable condition under which we can expect to develop a self-adaptive personalized knowledge service system based on...
In this paper, we study the methods of constructing place-name ontology of Beijing based on attribute properties and spatial relation properties of place-name entities from the perspective of spatial cognition. Firstly, we locate place-name entities in the coordinate frame of Beijing city qualitatively and define the concept of place-name entities combining with the types of them. And then select...
For more serious network security threat, security tools, also developed rapidly, but a fundamental limitation of traditional host-based anti-malware systems is that they run inside the very hosts they are protecting, making them vulnerable to counter-detection and subversion by malware, so VMM-based anti-malware systems have recently become a hot research field. Based on the analysis of existing...
Web is becoming a programmable platform, with countless services blooming everyday in various forms like Feeds, REST APIs and Widgets, etc. Although the existing technologies, such as Mashups, have reduced the challenges to build new applications by composing these services, it's still far from enabling the non-technical users to solve their situational problems by correlating and consuming these...
From the perspective of semantic network model, this paper does research on the urban road extraction from high-resolution remote sensing images. First, we analyze spatial features and contextual information of road in high resolution remote sensing images. By using the method of regional segmentation edge detection, area filter and Hough transform methods respectively, we obtain the candidate nodes...
Timed event is an essential part of concurrent actor interaction. This paper presents predictable time-centric semantic framework for designing actor-oriented embedded control software on the distributed platform, which reduces complexity by separating actor's data-centric computational parts from timed interaction among actors. Actors are concurrent components. Signal, timed metric distance and causality...
Concurrent real-time component is the basic unit of time-critical software on the distributed platform and trustworthy design is a continuing challenge to designers. This paper presents a reliable actor-oriented design for concurrent real-time component by separating data-related functionality and time-related interaction among components. Actor-oriented component is an encapsulation of parameterized...
This paper presents an extensible software framework for embedded system modeling on a distributed platform. Actors are concurrent components to specify time-triggered sensor readings, task invocations, actuator updates, and pattern switches independent of any given platform. Composite actor can be arbitrarily nested and framework consists of a formal semantics by separating platform-independent concerns...
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.