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.
In this paper we propose a task-driven progressive part localization (TPPL) approach for fine-grained object recognition. Most existing methods follow a two-step approach which first detects salient object parts to suppress the interference from background scenes and then classifies objects based on features extracted from these regions. The part detector and object classifier are often independently...
The increasing numbers of textual documents from diverse sources such as different websites (e.g. social networks, news, magazines, blogs and medical recommendation websites), publications and articles and medical prescriptions leads to massive amounts of daily complex data. This phenomenon has caused many researchers to focus on analysing the content and measuring the similarities among the documents...
In this paper, we introduce a distance-based approach for measuring the semantic dissimilarity between two concepts in a knowledge graph. The proposed Normalized Semantic Web Distance (NSWD) extends the idea of the Normalized Web Distance, which is utilized to determine the dissimilarity between two textural terms, and utilizes additional semantic properties of nodes in a knowledge graph. We evaluate...
The increased level of heterogeneity among the network components of current mobile Radio Access Networks (RANs), has meant that conventional network troubleshooting techniques are no longer sustainable; impacting negatively on customer experience and Quality of Service (QoS). Intelligent Fault Management (IFM) is a promising approach that utilizes the power of data mining in addressing emerging and...
With massive amounts of data producing each day in almost every field, traditional data processing techniques have become more and more inadequate. However, the research of effectively managing and retrieving these big data is still under development. Multimedia high-level semantic concept mining and retrieval in big data is one of the most challenging research topics, which requires joint efforts...
This paper presents a method to validate the insertion of a new concept in an ontology. This method is based on our previous works which add new concepts in a basic ontology using a general ontology (genaral ontology contains all the concepts of the basic ontology). To verify the semantic relevance of an ontology, we have proposed a method with three steps. First, we have found the neighborhood of...
This paper describes performance of an interpreter uncovering meanings of prepositions in "master" — preposition — "slave" constructions. The basis of the semantic interpreter is a set of "if A, than B" rules, with the left parts containing lexical and semantic markers of the "masters" and the "slaves" and morphological markers of the "slaves"...
With the explosive growth of online multi-media data, methodologies of retrieving documents from heterogeneous modalities are indispensable to facilitate information acquisition in real applications. Most of existing research efforts are focused on building correlation learning models on hand-crafted features for visual and textual modalities. However, they lack the ability to capture the meaningful...
Image annotation is a fundamental and challenging task in the field of semantic image retrieval. In this paper, we deal with image annotation via matrix completion. Concretely, we formulate the problem of annotating the tags of an image into a constrained optimization problem, in which the constraint is to keep the consistency with the given initial labels and the objective is to minimize the discrepancy...
This paper investigates the problem of modeling Internet images and associated text for cross-modal retrieval tasks such as text-to-image search, and image-to-text search. Canonical correlation analysis (CCA), a classic two view approach for mapping text and image into a common latent space, does not make use of the semantic information of text and image pairs. We use CCA to map text, image and semantic...
It has analysed the related technology of promoting Instructional Micro Video correlation in the paper, and proposed the semantic representation of Instructional micro video. Based on the characteristics of Instructional micro video, it has put forward the semantic representation of instructional micro video from the perspective of ontology metadata. At last, a case has been designed to state how...
Multi-document summarization addressing the problem of information overload has been widely utilized in the various real-world applications. Most of existing approaches adopt term-based representation for documents which limit the performance of multi-document summarization systems. In this paper, we proposed a novel pattern-based topic model (PBTMSum) for the task of the multi-document summarization...
With the popularization of network technology and higher level educational information, education in the field of knowledge management has become a research hotspot. The knowledge point is an essential cell which transferred information in teaching. Automatically extracted from the network a lot of teaching resources in knowledge and information, and then translates the information into the corresponding...
With the popularity of Internet video, video retrieval applications become more and more widespread. The effect of the traditional retrieval optimization algorithms cannot meet the needs of users. To improve rearrangement semantic rationality of video search results, this paper introduces the video annotation to mark based on the video content objectively. At the same time, the use of words semantic...
Monitoring the massive volume of data streaming from managed nodes in Telecommunication networks reacting in a timely manner is increasingly critical for modern Telecommunications Operations Support Systems (OSS). Given the large number and the varieties of the nodes in a telecoms network, the streaming monitoring data is naturally diverse and the volume is often at scales of multiple millions data...
One of the most popular techniques used in recommender systems is collaborating filtering. In this technique it is usual that Pearson's correlation is used to find the similarity between users. It is a known fact that Pearson's correlation is not suitable for measuring the strength of nonlinear relations. Since Spearman's correlation is in fact Pearson's correlation applied to ranks and does not work...
Cross-Modal mapping plays an essential role in multimedia information retrieval systems. However, most of existing work paid much attention on learning mapping functions but neglected the exploration of high-level semantic representation of modalities. Inspired by recent success of deep learning, in this paper, deep CNN (convolutional neural networks) features and topic features are utilized as visual...
Appropriately defining and then efficiently calculating similarities from large data sets are often essential in data mining, both for building tractable representations and for gaining understanding of data and generating processes. Here we rely on the premise that given a set of objects and their correlations, each object is characterized by its context, i.e. its correlations to the other objects,...
The massively growing of literature resource makes it a challenge for researchers to find useful papers. To solve the information overload problem, some researches on personalized paper recommendation have been conducted. However, the knowledge gap between a researcher's background knowledge and research target is seldom concerned. In this paper, we propose a knowledge-gap based literature recommendation...
Aspect extraction is one of most challenging tasks in opinion mining. Many researches have attempted to solve this problem for English text. For less popular languages such as Vietnamese, their complex structure causes difficulties in management or semantic analysis tasks. In this paper, we propose an approach to extracting and classifying aspect-terms for Vietnamese language. The semi-supervised...
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.