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.
Object part segmentation is a challenging and fundamental problem in computer vision. Its difficulties may be caused by the varying viewpoints, poses, and topological structures, which can be attributed to an essential reason, i.e., a specific object is a 3D model rather than a 2D figure. Therefore, we conjecture that not only 2D appearance features but also 3D geometric features could be helpful...
Recently, CNN-based models have achieved remarkable success in image-based salient object detection (SOD). In these models, a key issue is to find a proper network architecture that best fits for the task of SOD. Toward this end, this paper proposes two-stream fixation-semantic CNNs, whose architecture is inspired by the fact that salient objects in complex images can be unambiguously annotated by...
Dense captioning is a newly emerging computer vision topic for understanding images with dense language descriptions. The goal is to densely detect visual concepts (e.g., objects, object parts, and interactions between them) from images, labeling each with a short descriptive phrase. We identify two key challenges of dense captioning that need to be properly addressed when tackling the problem. First,...
Answer selection is a very important task in domain question answering. However, because of the word variety between questions and answers, there exists the lexical gap between questions and answers, which is the major challenge in question answer matching. In this work, in order to overcome the lexical gap, we propose an attention based bidirectional gated convolution with neural tensor network (ABiRCNN+NTN),...
The hash symbol, called a hashtag, is used to mark the keyword or topic in a tweet. It was created organically by users as a way to categorize messages. Hashtags also provide valuable information for many research applications such as sentiment classification and topic analysis. However, only a small number of tweets are manually annotated. Therefore, an automatic hashtag recommendation method is...
In this paper, we propose an adaptive template for semantic labeling of indoor scene objects and estimating their oriented bounding facets (OBFs). The proposed adaptive template encodes prior geometric information of objects based on statistics of the training images. Given an input image, we utilize the adaptive template on the detected bounding boxes to initialize the raw labeling and OBF estimation...
We propose a new approach for constructing mid-level visual features for image classification. We represent an image using the outputs of a collection of binary classifiers. These binary classifiers are trained to differentiate pairs of object classes in an object hierarchy. Our feature representation implicitly captures the hierarchical structure in object classes. We show that our proposed approach...
In this tutorial, we define and discuss key aspects of the problem of computational inference of aesthetics and emotion from images. We begin with a background discussion on philosophy, photography, paintings, visual arts, and psychology. This is followed by introduction of a set of key computational problems that the research community has been striving to solve and the computational framework required...
With the rapid development of educational technologies, machine learning (ML) based second language learning (SLL) attracts the attention of many scholars from computational linguistics. Garden path (GP) sentence is a special sentence structure in which processing breakdown and backtracking are involved in the machine decoding. Faced with GP sentence, learners have to make original misinterpretation...
As computers have become more affordable and accessible, the theories and techniques of natural language processing (NLP) are increasingly used as a means for automatically decoding natural language. Well-formed substring table (WFST) is an efficient parsing algorithm used to decode natural language. The form of (START, FINISH, LABEL→FOUND. TO FIND) is accepted by system as its basic model, and its...
The inter-language studies on the textual semantic accessibility scale (SAS) are a new branch of the computational linguistics and the present paper tries to statistically probe into the SASes in English, French and Japanese literature works sampled from the corresponding corpora. Firstly, six control groups are formed by the equidistant texts extracted every 10 pages, 5 pages, 4 pages, 3 pages, 2...
The study on the degree of the textual comprehensibility based on French corpus comes under the umbrella of corpus-involved text research. A systematic random sampling is employed in the present paper to compare the six different groups extracted from one and the same sampled French text. The formula, viz. A+BX≤C, is provided here to equidistantly extract linguistic fragments from the famous French...
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.