In this paper, a novel algorithm is proposed for intra-frame coding, named as rate-distortion optimized transform (RDOT). Unlike existing intra-frame coding schemes where the transform matrices are either fixed or mod...
详细信息
In this paper, a novel algorithm is proposed for intra-frame coding, named as rate-distortion optimized transform (RDOT). Unlike existing intra-frame coding schemes where the transform matrices are either fixed or mode dependent, in the proposed algorithm, transform is implemented with multiple candidate transform matrices. With this flexibility, for coding each residual block, the encoder is endowed with the power to select the optimal transform matrix in terms of rate-distortion tradeoff. The proposed algorithm has been implemented in the latest ITU-T VCEG-KTA software. Experimental results show that, over a wide range of test set, the proposed method achieves average 0.43dB coding gain compared with the recent Mode-Dependent Directional Transform (MDDT). The improvement is more significant at high bit-rates, and up to 1dB coding gain can be achieved.
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. Howe...
详细信息
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 (KL) divergences of class pairs (MGMD), can significantly reduce the class separation problem. Furthermore, maximizing the harmonic mean of Kullback-Leibler (KL) divergences of class pairs (MHMD) emphasizes smaller divergences more than MGMD, and deals with the class separation problem more effectively. However, in many applications, labeled data are very limited while unlabeled data can be easily obtained. The estimation of divergences of class pairs is unstable using inadequate labeled data. To take advantage of unlabeled data for subspace selection, semi-supervised MHMD (SSMHMD) is proposed using graph Laplacian as normalization. Quasi-Newton method is adopted to solve the optimization problem. Experiments on synthetic data and real image data show the validity of SSMHMD.
Risk evaluation is very important to the design and improvement of physical protection systems. In this paper, an evaluation method of multi-source information fusion is proposed based on the D-S evidence theory. In t...
详细信息
With the expansion of the Web, automatically organizing large scale text resources, e.g. Web pages, becomes very important. Many Web sites, like Google and Yahoo, use hierarchical classification trees to organize text...
详细信息
A mathematical framework based on probability theory is presented that enables us to analyze one important aspect of SI algorithms: the population diversity. Firstly the population density degree is defined for the po...
详细信息
We describe for dependency parsing an annotation adaptation strategy, which can automatically transfer the knowledge from a source corpus with a different annotation standard to the desired target parser, with the sup...
详细信息
Thinning algorithms can be classified into two general types: serial and parallel algorithms. Several algorithms have been proposed, but they have limitations. A new thinning algorithm based on the centroid of the blo...
详细信息
In this paper we present a feature extraction approach by using ICA filters bank, which consists of the ICA basis images learned from the training images. On the basis of its ability to capture the inherent properties...
详细信息
In our daily life, more and more commercial activities that have traditionally been conducted via physical mechanisms are being conducted virtually by means of information technologies (ITs). With the tendency of incr...
详细信息
Tree-based statistical machine translation models have made significant progress in recent years, especially when replacing 1-best trees with packed forests. However, as the parsing accuracy usually goes down dramatic...
详细信息
暂无评论