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.
Recently, convolutional networks have achieved great successes in the field of computer vision. In order to improve the efficiency of convolutional networks, large amount of solutions focusing on training algorithms and parallelism strategies have been proposed. In this paper, a novel algorithm based on look-up table is proposed to speed up convolutional networks with small filters by applying GPU...
Subspace selection is widely adopted in many areas of pattern recognition. A recent result, named maximizing the geometric mean of Kullback-Leibler (KL) divergences of class pairs (MGMD), is a successful method for subspace selection, which can significantly reduce the class separation problem. However, in many applications, labeled data are very limited while unlabeled data can be easily obtained...
Fisher's linear discriminant analysis (FLDA) is one of the most well-known linear subspace selection methods. However, FLDA suffers from the class separation problem. The projection to a subspace tends to merge close class pairs. Recent results show that maximizing the geometric mean or harmonic mean of Kullback-Leibler (KL) divergences of class pairs can significantly reduce this problem. In this...
Training a large number of qualified software engineers is a great challenge for universities, and curriculum design is an important issue. Based on IEEE-CS/ACM SE2004, Nanjing University in China designs the software engineering undergraduate curriculum NJU-SEC2006. There are three main concerns about the curriculum design. Firstly, the knowledge delivering sequence is designed to match the different...
It is important to integrate contextual information in order to improve the performance of automatic image annotation. Graph based representations allow incorporation of such information. In this paper, we propose a graph-based approach to automatic image annotation which models both feature similarities and semantic relations in a single graph. The annotation quality is enhanced by introducing graph...
In engineering applications, Gaussian process (GP) regression method is a new statistical optimization approach, to which more and more attention is paid. It does not need pre-assuming a specified model and just requires a small amount of initial training samples. Based on the design of experiment (DOE), determining a reasonable statistical sample space is an important part for training the GP surrogate...
In order to improve the accuracy of the image annotation, an automatic image annotation method based on mutual K-nearest neighbor graph (MKNN) is proposed. The proposed algorithm describes the relationship between low-level features, annotation words and image by a mutual K-nearest neighbor graph. Semantic information is extracted by exploiting the mutual relationship of two nodes in the mutual K-nearest...
In order to improve the computing speed of automatic image annotation. We propose a fast solution for this problem in this paper. First, the proposed approach describes the relationship between the low-level features, annotated words and image by a multi-modal graph which is linear correlation, block-wise and community-like structure. Second, we, to achieve fast solution of the problem, exploit the...
In many areas of pattern recognition and machine learning, subspace selection is an essential step. Fisher's linear discriminant analysis (LDA) is one of the most well-known linear subspace selection methods. However, LDA suffers from the class separation problem. The projection to a subspace tends to merge close class pairs. A recent result, named maximizing the geometric mean of Kullback-Leibler...
Semi-tied covariance (STC) is applied widely in speech recognition due to its feature de-correlation ability. Solving the transform matrices of STC is a nonlinear optimization problem. Gales proposed an efficient method by iteratively updating a row of transform matrices. However, it needs to solve cofactors of elements of a matrix row in two layers of loops. Directly solving them is very time-consuming...
To improve codebook quality in the process of vector quantization, the paper proposes a novel codebook generation algorithm which is based on image segmentation using t-mixture models and greedy EM algorithm. Additionally, in the initial codebook generating procedure, the PNN algorithm is used to reduce LBG algorithmpsilas sensitivity to initial codebook. Experimental results show that the proposed...
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.