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.
With the purpose of automatic detection of crowd patterns including abrupt and abnormal changes, a novel approach for extracting motion “textures” from dynamic Spatio-Temporal Volume (STV) blocks formulated by live video streams has been proposed. This paper starts from introducing the common approach for STV construction and corresponding Spatio-Temporal Texture (STT) extraction techniques. Next...
Realizing the automated and online detection of crowd anomalies from surveillance CCTVs is a research-intensive and application-demanding task. This research proposes a novel technique for detecting crowd abnormalities through analyzing the spatial and temporal features of the input video signals. This integrated solution defines an image descriptor that reflects the global motion information over...
The traditional relation extraction methods require the pre-defined relation types and a corpus with human tags. The information extracted by the current open relation extraction (ORE) methods is incomplete, and the relation types are finite. To solve the above problems, we propose ClausORE, which is an n-ary ORE method for Chinese text and extracts the entities and relations between entities from...
Clustering of entity pairs is the core content of the unsupervised relation extraction method. However, most of the clustering algorithm in the previous unsupervised relation extraction does not take into account the influence of the duality between entity pairs and the relationship characteristics on clustering results. In order to overcome this defect, this paper proposed a novel clustering algorithm...
Feature extraction is of great importance in condition monitoring and fault diagnosis of rolling machinery. Nonlinear dimensionality reduction (NDR) theories brought a new idea for recognizing and predicting the underlying nonlinear behavior. In this paper, we propose a NDR based feature extraction method for fault classification of rolling element bearing. Original feature spaces are constructed...
For facilitating the end-users can utilize available software services to construct the business applications on demand and independently, early works have proposed an end-user oriented and reusable service model-business service. However, the business service needs to be able to be instantiated to support the end-users to express specialized usage manners of business functionality. Utilizing the...
Video processing for surveillance and security applications has become a research hotspot in the last decade. This paper reports a research into volume-based segmentation techniques for video event detection. It starts with an introduction of the structure in 3D video volumes denoted by spatio-temporal features extracted from video footages. The focus of the work is on devising an effective and efficient...
Due to the difference between Web page and plain text document, the concept of Web object is introduced in this paper. Besides, the supposed state transition and the emission symbol conditions are improved based on Pseudo two dimension hidden Markov model (P2D-HMM), and a novel web objects information extraction method is proposed. Finally, through an example, it shows that the proposed method has...
Although it has been studied for years by the computer vision and machine learning communities, image annotation is still far from practical. In this paper, we propose a novel attempt at model-free image annotation, which is a data-driven approach that annotates images by mining their search results. Some 2.4 million images with their surrounding text are collected from a few photo forums to support...
Text classification has been considered as a hot research area in data mining. This paper presents a new approach combining hidden Markov model (HMM) with support vector machine (SVM) for text classification. HMMs are used to as a feature extractor and then a new feature vector is normalized as the input of SVMs, so the trained SVMs can classify unknown texts successfully. The experimental results...
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.