检索结果-内蒙古大学图书馆

Conference on Empirical Methods in Natural Language processing, EMNLP 2011

作者： Xiao, Xinyan Liu, Yang Liu, Qun Lin, Shouxun Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China

ISBN: (纸本)1937284115

Although discriminative training guarantees to improve statistical machine translation by incorporating a large amount of overlapping features, it is hard to scale up to large data due to decoding complexity. We propose a new algorithm to generate translation forest of training data in linear time with the help of word alignment. Our algorithm also alleviates the oracle selection problem by ensuring that a forest always contains derivations that exactly yield the reference translation. With millions of features trained on 519K sentences in 0.03 second per sentence, our system achieves significant improvement by 0.84 BLEU over the baseline system on the NIST Chinese-English test sets. © 2011 Association for Computational Linguistics.

关键词： Forestry

来源：评论

学校读者我要写书评

暂无评论

Relaxed cross-lingual projection of constituent syntax

Relaxed cross-lingual projection of constituent syntax

引用

Conference on Empirical Methods in Natural Language processing, EMNLP 2011

作者： Jiang, Wenbin Liu, Qun Lü, Yajuan Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China

ISBN: (纸本)1937284115

We propose a relaxed correspondence assumption for cross-lingual projection of constituent syntax, which allows a supposed constituent of the target sentence to correspond to an unrestricted treelet in the source parse. Such a relaxed assumption fundamentally tolerates the syntactic non-isomorphism between languages, and enables us to learn the target-language-specific syntactic idiosyncrasy rather than a strained grammar directly projected from the source language syntax. Based on this assumption, a novel constituency projection method is also proposed in order to induce a projected constituent tree-bank from the source-parsed bilingual corpus. Experiments show that, the parser trained on the projected treebank dramatically outperforms previous projected and unsupervised parsers. © 2011 Association for Computational Linguistics.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Artificial Bee Colony Algorithm based Auto-Disturbance Rejection Control for Rehabilitation Robotic Arm Driven by PM-TS Actuator

Artificial Bee Colony Algorithm based Auto-Disturbance Rejec...

引用

2012 International Conference on Modelling,Identification and Control(建模、辨别与控制国际会议 ICMIC 2012)

作者： Jun Wu Yongji Wang Jian Huang Kexin Xing Key Laboratory of Image Processing and Intelligent Control Department of Control Science and Enginee Key Laboratory of Image Processing andIntelligent Control Department of Control Science and Engineer College of Information Engineering ZhejiangUniversity of TechnologyHangzhouZhejiang 310032China

ISBN: (纸本)9781467315241

Pneumatic Muscle (PM) has the advantages of cheapness, light weight, compliance, safe and high power/*** is suitable for rehabilitation *** minimize the number of PM for driving a single joint of rehabilitation, a new PM-TS actuator comprising a PM and a Torsion Spring (TS) is *** the traditional agonist/antagonist PM actuator, the PM is arranged in appropriate place as agonist and the torsion spring provides opposing torque as antagonist in the proposed *** dynamic model of a 1-DOF (Degree of Freedom) rehabilitation robotic arm is derived considering the PM-TS *** realize high accurate trajectory tracking control of the robotic arm, an Artificial Bee Colony (ABC) algorithm based Auto-Disturbance Rejection Control (ADRC) is proposed, where ABC is employed to optimize the control parameters of *** results demonstrate the validity of PM-TS actuator, and verify that the ABC based ADRC has satisfactory performance.

关键词： Pneumatic Muscle Artificial Bee Colony Auto-Disturbance Rejection Control Rehabilitation Robotic Arm

来源：评论

学校读者我要写书评

暂无评论

Effectively Discriminating Fighting Shots in Action Movies

引用

Journal of Computer Science & technology 2011年第1期26卷 187-194页

作者：马述高王伟强 School of Information Science and Engineering Graduate University of Chinese Academy of Sciences Computer Science Department Boston UniversityBoston MA 02215U.S.A. Key Laboratory of Intelligent Information Processing Institute of Computing TechnologyChinese Academy of Sciences

Fighting shots are the highlights of action movies and an effective approach to discriminating fighting shots is very useful for many applications, such as movie trailer construction, movie content filtering, and movie content retrieval. In this paper, we present a novel method for this task. Our approach first extracts the reliable motion information of local invariant features through a robust keypoint tracking computation; then foreground keypoints are distinguished from background keypoints by a sophisticated voting process; further, the parameters of the camera motion model is computed based on the motion information of background keypoints, and this model is then used as a reference to compute the actual motion of foreground keypoints; finally, the corresponding feature vectors are extracted to characterizing the motions of foreground keypoints, and a support vector machine （SVM） classifier is trained based on the extracted feature vectors to discriminate fighting shots. Experimental results on representative action movies show our approach is very effective.

关键词： video analysis motion concept learning

来源：评论

学校读者我要写书评

暂无评论

An orientation model for hierarchical phrase-based translation

An orientation model for hierarchical phrase-based translati...

引用

2011 International Conference on Asian Language processing, IALP 2011

作者： Xiao, Xinyan Su, Jinsong Liu, Yang Liu, Qun Lin, Shouxun Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9780769545547

The hierarchical phrase-based (HPB) translation exploits the power of grammar to perform long distance reorderings, without specifying nonterminal orientations against adjacent blocks or considering the lexical information covered by nonterminals. In this paper, we borrow from phrase-based system the idea of orientation model to enhance the reordering ability of HPB translation. We distinguish three orientations (monotone, swap, discontinuous) of a nonterminal based on the alignment of grammar, and select the appropriate orientation of nonterminal using lexical information covered by it. By incorporating the orientation model, our approach significantly outperforms a standard HPB system up to 1.02 Bleu on large scale NIST Chinese-English translation task, and 0.51 Bleu on WMT German-English translation task. © 2011 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Salient region detection and segmentation for general object recognition and image understanding

引用

Science China(information Sciences) 2011年第12期54卷 2481-2490页

作者： HUANG TieJun 1 , TIAN YongHong 1 , LI Jia 2 & YU HaoNan 11 National Engineering laboratory for Video technology, School of Electrical Engineering and Computer Science, Peking University, Beijing 100871, China 2 key laboratory of intelligent information processing, Institute of Computing technology, Chinese Academy of Sciences, Beijing 100190, China National Engineering Laboratory for Video Technology School of Electrical Engineering and Computer Science Peking University Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

General object recognition and image understanding is recognized as a dramatic goal for computer vision and multimedia retrieval. In spite of the great efforts devoted in the last two decades, it still remains an open problem. In this paper, we propose a selective attention-driven model for general image understanding, named GORIUM (general object recognition and image understanding model). The key idea of our model is to discover recurring visual objects by selective attention modeling and pairwise local invariant features matching on a large image set in an unsupervised manner. Towards this end, it can be formulated as a four-layer bottom-up model, i.e., salient region detection, object segmentation, automatic object discovering and visual dictionary construction. By exploiting multi-task learning methods to model visual saliency simultaneously with the bottom-up and top-down factors, the lowest layer can effectively detect salient objects in an image. The second layer exploits a simple yet effective learning approach to generate two complementary maps from several raw saliency maps, which then can be utilized to segment the salient objects precisely from a complex scene. For the third layer, we have also implemented an unsupervised approach to automatically discover general objects from large image set by pairwise matching with local invariant features. Afterwards, visual dictionary construction can be implemented by using many state-of-the-art algorithms and tools available nowadays.

关键词： object recognition image understanding visual saliency salient object segmentation visual dictionary

来源：评论

学校读者我要写书评

暂无评论

RETRACTED ARTICLE: The eqviualence of fuzzy logical dynamics and the neural circuits' dynamics

RETRACTED ARTICLE: The eqviualence of fuzzy logical dynamics...

引用

2011 7th International Conference on Natural Computation, ICNC 2011

作者： Hu, Hong Shi, Zhongzhi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Science Beijing 100190 China

ISBN: (纸本)9781424499533

In order to probe the secret of our brain, it is necessary to design large scale dynamical neural circuits( more than 106 neurons) to simulate complex process of our brain. But such kind task is not easy to achieve only based on the analysis of partial equations especially for complex neural models, e.g. Rose-Hindmarsh (RH) model. So we should develop a novel approach which combines logic and machine learning in the designation or analysis of large scale neural circuits, and this new approach should be able to greatly simplify the designation of large scale dynamical neural circuits which is really very important both for cognition science and neural science. For this purpose, we introduce the concept of fuzzy logical framework of a neural circuit, and we proved that if the behave of a neural circuit can be described by first order partial differential equations, then such kind neural circuit can be simulated with arbitrary small errors by a Hopfield neural circuit which has a uniform structure or a fuzzy logical dynamical system; for more, a novel learning approach for large scale layered neural circuits based on PSVM and back propagation is developed for training Hopfield neural circuits. © 2011 IEEE.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Dual form back propagation on the EM algorithm

Dual form back propagation on the EM algorithm

引用

2011 IEEE International Conference on Granular Computing, GrC 2011

作者： Hu, Hong Shi, Zhongzhi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Science Beijing 100190 China

ISBN: (纸本)9781457703713

Vladimir N. Vapnik. (1998) pointed out that maxlikelihood functions in EM algorithms are just a special risk function. Based on this opinion, a novel EM algorithm uses a risk function differ with maxlikelihood functions, in stead, a risk formula based on the least square method is used. The gradient descending approach should be used in such kind approaches. Such kind EM algorithms can estimate the parameters of a random model from both labeled and unlabeled samples, and are suitable for semi-supervised learning. © 2011 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Answering contextual questions based on ontologies and question templates

引用

Frontiers of Computer Science 2011年第4期5卷 405-418页

作者： Dongsheng WANG Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China Graduate University of the Chinese Academy of Sciences Beijing 100049 China Department of Computer Science Jiangsu University of Science and Technology Zhenjiang 212003 China

Contextual question answering （CQA）, in which user information needs are satisfied through an interactive question answering （QA） dialog, has recently attracted more research attention. One challenge is to fuse contextual information into the understanding process of relevant questions. In this paper, a discourse structure is proposed to maintain semantic information, and approaches for recognition of relevancy type and fusion of contextual information according to relevancy type are proposed. The system is evaluated on real contextual QA data. The results show that better performance is achieved than a baseline system and almost the same performance as when these contextual phenomena are resolved manually. A detailed evaluation analysis is presented.

关键词： Contextual question answering （CQA）,ontology question templates

来源：评论

学校读者我要写书评

暂无评论

A unified framework for locating and recognizing human actions

A unified framework for locating and recognizing human actio...

引用

作者： Xie, Yuelei Chang, Hong Li, Zhe Liang, Luhong Chen, Xilin Zhao, Debin China Key Laboratory of Intelligent Information Processing CAS China School of Computer Science and Technology Harbin Institute of Technology China

ISBN: (纸本)9781457703942

In this paper, we present a pose based approach for locating and recognizing human actions in videos. In our method, human poses are detected and represented based on deformable part model. To our knowledge, this is the first work on exploring the effectiveness of deformable part models in combining human detection and pose estimation into action recognition. Comparing with previous methods, ours have three main advantages. First, our method does not rely on any assumption on video preprocessing quality, such as satisfactory foreground segmentation or reliable tracking;Second, we propose a novel compact representation for human pose which works together with human detection and can well represent the spatial and temporal structures inside an action;Third, with human detection taken into consideration in our framework, our method has the ability to locate and recognize multiple actions in the same scene. Experiments on benchmark datasets and recorded cluttered videos verified the efficacy of our method. © 2011 IEEE.

关键词： Deformation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：