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.
Multi-label classification has attracted many attentions in various fields, such as text categorization and semantic image annotation. Aiming to classify an instance into multiple labels, various multi-label classification methods have been proposed. However, the existing methods typically build models in the identical feature (sub)space for all labels, possibly inconsistent with real-world problems...
Aesthetic quality estimation of an image is a challenging task. In this paper, we introduce a deep CNN approach to tackle this problem. We adopt the sate-of-the-art object-recognition CNN as our baseline model, and adapt it for handling several high-level attributes. The networks capable of dealing with these high-level concepts are then fused by a learned logical connector for predicting the aesthetic...
Correlation tracker has made a huge success in visual object tracking. However, it is mainly because that the tracker cannot catch the occurrence of appearance changes, tracking based on correlation filters often drifts due to the unexpected appearance changes caused by occlusion, deformation and background clutter. In this paper, we propose a new method to detect the case when the tracker encountered...
Understanding ongoing topics and their evolutions in social media is of great importance. Although topic analysis is not a novel research question, social media environment has presented new challenges. First, with insufficient co-occurrence information, short text have undermined many word co-occurrence oriented topic models' applicability. Second, real time message streams make traditional discretized...
Unprecedented expansion of user generated content in recent years demands more attempts of information filtering in order to extract high quality information from the huge amount of available data. In particular, topic detection from microblog streams is the first step toward monitoring and summarizing social data. This task is challenging due to the short and noisy characteristics of microblog content...
Topic models are used in text analysis to extract domain features and to explore unknown domains. The topic models and its extensions follow traditional machine learning approach as single-shot learning. Automatic knowledge based topic models (AKBTM) filled this gap by learning from each task and carrying it to future tasks as knowledge rules. Most of the research in AKBTM focuses on rule extraction...
Collaborative Filtering (CF) is widely used in large-scale recommendation engines because of its efficiency, accuracy and scalability. However, in practice, the fact that recommendation engines based on CF require interactions between users and items before making recommendations, make it inappropriate for new items which haven't been exposed to the end users to interact with. This is known as the...
The deep transformation induced by the World Wide Web (WWW) revolution has thoroughly impacted a relevant part of the social interactions in our present global society. The huge amount of unstructured information available on blogs, forum and public institution web sites puts forward different challenges and opportunities. Starting from these considerations, in this paper we pursue a two-fold goal...
Feature selection methods have been widely used in gene expression analysis to identify differentially expressed genes and explore potential biomarkers for complex diseases. While a lot of studies have shown that incorporating feature structure information can greatly enhance the performance of feature selection algorithms, and genes naturally fall into groups with regard to common function and co-regulation,...
Semantic analysis is an important component of recommendation systems and information retrieval in computer aided detection. Previous researches have made certain breakthroughs in disease diagnosis and drugs recommended by semantic analysis. We propose a bilateral shortest paths method for computing semantic relatedness based on the human thought patterns for making sufficient use of the hyperlink...
This study investigates the relative efficacy of using n-grams extracted terms, the aggregation of such terms, and a combination of feature extraction techniques in building an automated essay-type grading (AETG) system. The paper focused on the modification of the Principal Component Analysis (PCA) by integrating n-grams terms as input into the PCA algorithm. Hardcopies of examiners' marking schemes...
Considerable research efforts have been devoted to Twitter sentiment analysis in recent years. Given the informal writing style of Twitter, there exists an endless variety of sound vocabulary, slogans, emoticons and special characters that can be used to express one's opinion in a maximum of 140-characters. This results in a sparsity problem making the training of machine learning classifiers from...
The wide spread of the world wide web, the accelerating internet technologies development and the continuous upload of documents has produced large volumes of data. As a result, a huge amount of similar information is available on the web however very difficult to retrieve the best, concise and most precise one. In addition, the continuous upload of information leads to another issue which is documents'...
Datamining is the process of extracting interesting information of patterns from large databases. One of the most important datamining task and well-researched is the association rules mining. It aims to find the interesting correlation and relations among sets of items in the transaction databases. One of the main problems related to the discovery of these associations that a decision maker faces...
The combination of standard visible RGB channels and near infrared (NIR) information has been observed to perform better than RGB-only data in the scene categorization task. However, RGB-NIR data are limited due to the collection difficulties. With limited data, it is hard for most deep networks to learn an effective solution, while humans are able to solve such kind of problem within a little of...
There are different opinions on the names and quantity of semantic roles. In order to analyze the deep meaning of human language, we did two parts of tasks based on Chinese Semantic Dependency Graph Bank, which is a corpus analyzed by semantic dependency graph (SDG). After calculating the frequency of each role, we normalized the roles' names and distinguished the differences between each other. There...
With the improvement of China's international influence, more Chinese words are borrowed into English. To find out how popular Chinese borrowings in English, a questionnaire is conducted among English speakers (Chinese natives are excluded). Swaan's Q-value model is hereby employed to analyze the data. The result shows that Chinese borrowings in English vary in Q-value and the ones related to economy...
This paper discusses word of Haodai from the perspective of language information processing. The meaning and usages of Haodai are very complex in Mandarin. Its functions and usages in simple sentence and compound sentence have been carefully examined with explanation and appropriate examples.
Psychiatry describes speech symptoms that are indicative of disorganized thought, but measuring them is not easy. With natural language processing tools, it is possible to quantify psychiatric symptoms. Graph representations of word trajectories and semantic incoherence have independently been shown to predict the Schizophrenia diagnosis. Both analyses assess thought organization through speech, but...
In this paper, we present a generic model to enrich user profiles by means of contextual and temporal information. This reflecting the current interests of these users in every period of time defined by a search session, and infers data freshness. We argue that the annotation of resources gives more transparency on users' needs. Based on this idea, we integrate social tagging in order to exploit part...
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.