One of the most challenging issues in visual information retrieval is retrieval by shape, due to a lack of mathematically rigorous definition of shape similarity. This paper presents a bipolar model for computing shap...
详细信息
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 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.
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.
This paper presents a robust and real time method of license plate localization based on level sets. The proposed algorithm consists of three steps: (1) medial axis transformation of selected level sets, (2) identific...
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
We describe an effective constituent projection strategy, where constituent projection is performed on the basis of dependency projection. Especially, a novel measurement is proposed to evaluate the candidate projecte...
详细信息
We describe an effective constituent projection strategy, where constituent projection is performed on the basis of dependency projection. Especially, a novel measurement is proposed to evaluate the candidate projected constituents for a target language sentence, and a PCFG-style parsing procedure is then used to search for the most probable projected constituent tree. Experiments show that, the parser trained on the projected treebank can significantly boost a state-of-the-art supervised parser. When integrated into a tree-based machine translation system, the projected parser leads to translation performance comparable with using a supervised parser trained on thousands of annotated trees.
This paper proposes a method of face recognition using the support vector machine (SVM) based on the fuzzy rough set theory (FRST). Firstly, features from human face images are extracted by combining the 2-D wavelet d...
详细信息
This paper presents an improved neural architecture for gaze movement control in target searching. Compared with the four-layer neural structure proposed in [14], a new movement coding neuron layer is inserted between...
详细信息
This paper presents an improved neural architecture for gaze movement control in target searching. Compared with the four-layer neural structure proposed in [14], a new movement coding neuron layer is inserted between the third layer and the fourth layer in previous structure for finer gaze motion estimation and control. The disadvantage of the previous structure is that all the large responding neurons in the third layer were involved in gaze motion synthesis by transmitting weighted responses to the movement control neurons in the fourth layer. However, these large responding neurons may produce different groups of movement estimation. To discriminate and group these neurons' movement estimation in terms of grouped connection weights form them to the movement control neurons in the fourth layer is necessary. Adding a new neuron layer between the third layer and the fourth lay is the measure that we solve this problem. Comparing experiments on target locating showed that the new architecture made the significant improvement.
Strategies for network immunization have been drawing wide interest in the area of complex networks during the past decade. The target strategy, in which degree values are used to determine vaccinating priority, has b...
详细信息
暂无评论