In this paper, a novel Sparsely Encoded Local Descriptor (SELD) is proposed for face recognition. Compared with K-means or Random-projection tree based previous methods, sparsity constraint is introduced in our dictio...
详细信息
In this paper, a novel Sparsely Encoded Local Descriptor (SELD) is proposed for face recognition. Compared with K-means or Random-projection tree based previous methods, sparsity constraint is introduced in our dictionary learning and sequent image encoding, which implies more stable and discriminative face representation. Sparse coding also leads to an image descriptor of summation of sparse coefficient vectors, which is quite different from existing code-words appearance frequency(/histogram)-based descriptors. Extensive experiments on both FERET and challenging LFW database show the effectiveness of the proposed SELD method. Especially on the LFW dataset, recognition accuracy comparable to the best known results is achieved.
The degree of similarity between fuzzy numbers plays an important role in fuzzy information fusion. In this paper, improved ROG-based similarity measure developed from the current ROG method is presented. It is shown ...
详细信息
MicroRNAs can regulate hundreds of target genes and play a pivotal role in a broad range of biological process. However, relatively little is known about how these highly connected miRNAs-target networks are remodelle...
详细信息
MicroRNAs can regulate hundreds of target genes and play a pivotal role in a broad range of biological process. However, relatively little is known about how these highly connected miRNAs-target networks are remodelled in the context of various diseases. Here we examine the dynamic alteration of context-specific miRNA regulation to determine whether modified microRNAs regulation on specific biological processes is a useful information source for predicting cancer prognosis. A new concept, Context-specific miRNA activity (CoMi activity) is introduced to describe the statistical difference between the expression level of a miRNA's target genes and non-targets genes within a given gene set (context).
A group of decision-makers may differ in their choice of alternatives while taking a decision. So, in any decision-making problem concerning decisions made by a group, the question arises how best we can aggregate ind...
详细信息
The Dempster-Shafer (D-S) evidence theory is widely used in many fields of information fusion. However, counter-intuitive results may be obtained by the classical Dempster combination rule when collected evidences are...
详细信息
In this paper, we propose a novel dependency-based bracketing transduction grammar for statistical machine translation, which converts a source sentence into a target dependency tree. Different from conventional brack...
详细信息
In this paper, we propose a novel dependency-based bracketing transduction grammar for statistical machine translation, which converts a source sentence into a target dependency tree. Different from conventional bracketing transduction grammar models, we encode target dependency information into our lexical rules directly, and then we employ two different maximum entropy models to determine the reordering and combination of partial dependency structures, when we merge two neighboring blocks. By incorporating dependency language model further, large-scale experiments on Chinese-English task show that our system achieves significant improvements over the baseline system on various test sets even with fewer phrases.
Tree-based translation models, which exploit the linguistic syntax of source language, usually separate decoding into two steps: parsing and translation. Although this separation makes tree-based decoding simple and e...
详细信息
Tree-based translation models, which exploit the linguistic syntax of source language, usually separate decoding into two steps: parsing and translation. Although this separation makes tree-based decoding simple and efficient, its translation performance is usually limited by the number of parse trees offered by parser. Alternatively, we propose to parse and translate jointly by casting tree-based translation as parsing. Given a source-language sentence, our joint decoder produces a parse tree on the source side and a translation on the target side simultaneously. By combining translation and parsing models in a discriminative framework, our approach significantly outperforms a forest based tree-to-string system by 1.1 absolute BLEU points on the NIST 2005 Chinese-English test set. As a parser, our joint decoder achieves an F1 score of 80.6% on the Penn Chinese Treebank.
Chiaroscuro in art is characterized by strong contrasts between light and dark. An object in a certain light condition has a certain chiaroscuro pattern in appearance;and this pattern is invariant to the changes of il...
详细信息
In this paper we introduce a compactness based clustering algorithm. The compactness of a data class is measured by comparing the inter-subset and intra-subset distances. The class compactness of a subset is defined a...
详细信息
In statistical machine translation, decoding without any reordering constraint is an NP-hard problem. Inversion Transduction Grammars (ITGs) exploit linguistic structure and can well balance the needed flexibility aga...
详细信息
In statistical machine translation, decoding without any reordering constraint is an NP-hard problem. Inversion Transduction Grammars (ITGs) exploit linguistic structure and can well balance the needed flexibility against complexity constraints. Currently, translation models with ITG constraints usually employs the cube-time CYK algorithm. In this paper, we present a shift-reduce decoding algorithm that can generate ITG-legal translation from left to right in linear time. This algorithm runs in a reduce-eager style and is suited to phrase-based models. Using the state-ofthe- art decoder Moses as the baseline, experiment results show that the shift-reduce algorithm can significantly improve both the accuracy and the speed on different test sets.
暂无评论