检索结果-内蒙古大学图书馆

8th International Conference on Intelligent Computing technology, ICIC 2012

作者： Wang, Xiao-Feng Min, Hai Key Lab. of Network and Intelligent Information Processing Department of Computer Science and Technology Hefei University Hefei Anhui 230022 China Intelligent Computing Lab. Hefei Institute of Intelligent Machines Chinese Academy of Sciences P.O.Box 1130 Hefei Anhui 230031 China Department of Automation University of Science and Technology of China Hefei Anhui 230027 China

ISBN: (纸本)9783642315879

In this paper, an efficient two-stage segmentation framework was proposed to address the plant leaf image with overlapping phenomenon, which is built based on the leaf approximate symmetry and level set evolution theory. In the pre-segmentation stage, a straight line was manually set on the target leaf to approximate the principal leaf vein and the Local Chan-Vese (LCV) model was used on the global image region to help searching the so-called un-overlapping contour in target leaf. In the formal segmentation stage, the symmetry detection was performed based on the pre-defined approximated principal vein to obtain the narrow-band evolution region and the second initial contour. Next, the LCV model was once again used to find the complete target leaf contour in the narrow-band evolution region. Finally, experiments on some real leaf images with overlapping phenomenon have demonstrated the efficiency and robustness of the proposed segmentation framework. © 2012 Springer-Verlag.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Forest-based translation rule extraction

Forest-based translation rule extraction

引用

2008 Conference on Empirical Methods in Natural Language processing, EMNLP 2008, Co-located with AMTA 2008 and the International Workshop on Spoken Language Translation

作者： Mi, Haitao Huang, Liang Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences P.O. Box 2704 Beijing 100190 China Dept. of Computer and Information Science University of Pennsylvania Levine Hall 3330 Walnut St. Philadelphia PA 19104 United States

Translation rule extraction is a fundamental problem in machine translation, especially for linguistically syntax-based systems that need parse trees from either or both sides of the bitext. The current dominant practice only uses 1-best trees, which adversely affects the rule set quality due to parsing errors. So we propose a novel approach which extracts rules from a packed forest that compactly encodes exponentially many parses. Experiments show that this method improves translation quality by over 1 BLEU point on a state-of-the-art tree-to-string system, and is 0.5 points better than (and twice as fast as) extracting on 30- best parses. When combined with our previous work on forest-based decoding, it achieves a 2.5 BLEU points improvement over the baseline, and even outperforms the hierarchical system of Hiero by 0.7 points. © 2008 Association for Computational Linguistics.

关键词： Hierarchical systems

来源：评论

学校读者我要写书评

暂无评论

Texture image segmentation using Brushlet-domain hidden Markov models

Texture image segmentation using Brushlet-domain hidden Mark...

引用

MIPPR 2009 - Remote Sensing and GIS Data processing and Other Applications: 6th International Symposium on Multispectral Image processing and Pattern Recognition

作者： Liu, Fang Yang, Kai Hao, Hongxia Hou, Biao Zhong, Hua School of Computer Science and Technology Xidian University Xi'an Shanxi 710071 China Intelligent Perception and Image Understanding Key Lab. of Ministry of Education of China Xi'an Shanxi 710071 China Intelligent Information Processing Laboratory Xidian University Xi'an Shanxi 710071 China

ISBN: (纸本)9780819478092

By researching the Brushlet domain coefficients of texture images, we found that the distribution of the magnitudes of Brushlet domain coefficients roughly meet rayleigh distribution. And there are correlations between Brushlet coefficients in adjacent scales. Therefore, Rayleigh Mixture Model (RMM) is used to characterize the statistics of the magnitudes of Brushlet coefficients. To capture the inter-scale persistence of Brushlet coefficients, a "four to four" models with markov property is adopted in this paper. On the basis, by combining with the multi-scale Bayesian segmentation method, we propose a multiscale Bayesian texture segmentation algorithm that is based on a Brushlet domain hidden Markov tree (BruHMT) model. The experiment results indicate that our method is feasible and effective. Especially for coarse texture, our method is superior than texture segmentation method using Wavelet domain hidden Markov tree (WHMT) model. © 2009 Copyright SPIE - The International Society for Optical Engineering.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Reduced memory zerotree envelop coding for wavelet image

Reduced memory zerotree envelop coding for wavelet image

引用

MIPPR 2007: Automatic Target Recognition and Image Analysis;and Multispectral Image Acquisition

作者： Wentao, Wang Guoyou, Wang Jianguo, Liu State Key Lab. for Multi-spectral Information Processing Technologies Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China College of Computer Science South-Central University for Nationalities 708 Minyuan Road Wuhan 430074 China

ISBN: (纸本)9780819469502

In this paper, we propose a new image codec, which called embedded zerotree wavelet coefficients envelop coding (EZWCEC). The coefficients envelop is characterized by describing the global tendency of the significant wavelet coefficients. Based on the empirical analysis and experimental results, our EZWCEC algorithm restores the trend of the significant wavelet coefficients and estimates the magnitude of some insignificant coefficients on the decoder. Unlike other zerotree coding algorithms such as Said and Pearlman's SPIHT using three lists, EZWCEC only uses two lists during encoding and decoding. So the memory requirement for the hardware implementation is reduced significantly. Although PSNR values for EZWCEC are lower than SPIHT's and JPEG2000's, our experiment results have shown that EZWCEC can dramatically improve the visual quality of reconstructed at low bit rates (e.g., below 0.1bpp).

关键词： Image coding

来源：评论

学校读者我要写书评

暂无评论

Fast template matching with partial skipping using sub-template

Fast template matching with partial skipping using sub-templ...

引用

2012 3rd IEEE/IET International Conference on Audio, Language and Image processing, ICALIP 2012

作者： Zhang, Qiao Gao, Huijie Kang, Zhen State Key Lab. of Multi-spectral Information Processing Technology Institute for Pattern Recognition and Artificial Intelligence Huazhong Univ. of Sci. and Tech. Wuhan 430074 China School of Mathematic and Computer Science Wuhan Polytechnic University Wuhan 430023 China

ISBN: (纸本)9781467301718

This paper presents a new fast template matching method with partial skipping using sub-template. In this method, we use sub-template to search point by point in the current searched window, and compare every SAD with threshold, if some SAD exceeds the threshold, set the new threshold equal to this SAD value and this point is one potential optimization location, when all points in the current window are compared, we will get a minimum value and a optimization location, then skip the other points whose SAD is not the minimum value. In other words, the searching step is that template size subtracts the subtemplate size, and we set the next threshold equal to the current optimization SAD value, we update the threshold and the optimal point until the end of the searched image like this, then will find the global minimum points and its SAD value. Experimental results show that the proposed method is near one hundred times faster than the conventional template match method. © 2012 IEEE.

关键词： Global optimization

来源：评论

学校读者我要写书评

暂无评论

Exploring Syntactic Features for Pronoun Resolution Using Context-Sensitive Convolution Tree Kernel

Exploring Syntactic Features for Pronoun Resolution Using Co...

引用

International Conference on Asian Language processing (IALP)

作者： Kong Fang Yancui Li Guodong Zhou Qiaoming Zhu Jiangsu Provincial Key Lab for Computer Information Processing Technology School of Computer Science and Technology Soochow Univ. Suzhou China College of Information Technology Henan Institute of Science and Technology Xinxiang Henan China Jiangsu Provincial Key Lab. for Comput. Inf. Process. Technol. Soochow Univ. Suzhou Suzhou China

This paper proposes to use a convolution kernel over parse tree to model syntactic structure information for pronoun resolution. Our study reveals that the syntactic structure features embedded in a parse tree are very effective for pronoun resolution and these features can be well captured by the context-sensitive convolution tree kernel. Evaluation on the ACE 2003 corpus shows that among all structured syntactic feature space, shortest path tree achieves the best performance. Then we incorporate more features into SPT, result shows that SPT can use successfully with normal features. Finally, we compare our system with other pronoun resolution systems, our results are outstanding in success rate than normal features and tree kernel-based method of Yang.

关键词： Convolution Kernel information processing computer science Educational institutions information technology Paper technology Electronic mail Data mining lab.ling

来源：评论

学校读者我要写书评

暂无评论

Generalized geometry-based optimal power control in wireless networks

Generalized geometry-based optimal power control in wireless...

引用

2012 9th Annual IEEE Communications Society Conference on Sensor, Mesh and Ad Hoc Communications and Networks, SECON 2012

作者： Wang, Wei Shin, Kang G. Zhang, Zhaoyang Wang, Wenbo Peng, Tao Department of Information Science and Electronic Engineering Zhejiang Provincial Key Laboratory of Information Network Technology Zhejiang University Hangzhou 310027 China Department of Electrical Engineering and Computer Science University of Michigan Ann Arbor MI 48109-2121 United States Wireless Signal Processing and Networking Lab Beijing University of Posts and Telecommunications Beijing 100876 China

ISBN: (纸本)9781467319058

Geometry-based optimal power control was proposed in [14] to transform the power-control problem to a new geometrical problem on the position relationship between a line and some points. This scheme provides a novel visual perspective and lowers the complexity of optimization. We generalize this scheme to a larger class of power-control optimization problems so as to maximize the network utility with multiple average and peak power constraints in wireless networks. To facilitate the handling of the geometrical model, we define a subset of geometrical models with specified characteristics, called a regular geometrical model, and derive the type of power-control problems eligible for the regular geometrical model. For such a type of problems, two strategies are proposed for the construction of the regular geometrical model. Utilizing geometrical properties, we propose a novel geometry-based optimization scheme for the general power-control problem. Its computational complexity is significantly lower than the conventional algorithms. We also provide a further discussion on irregular geometrical model cases. Finally, we provide two examples of deploying the proposed geometry-based power-control scheme. © 2012 IEEE.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Fusion of the dimensionless parameters and filtering methods in rotating machinery fault diagnosis

引用

Journal of Networks 2014年第5期9卷 1201-1207页

作者： Xiong, Jianbin Zhang, Qinhua Sun, Guoxi Peng, Zhiping Liang, Qiong Guangdong Provincial Key Lab. of Petrochemical Equipment Fault Diagnosis Maoming China School of Computer and Electronic Information Guangdong University of Petrochemical Technology Maoming China

For the problem of large dimensionless index fluctuations in rotating machinery complex fault and that the corresponding scope is difficult to determine. In this paper proposes a rotating machinery complex fault method that combined dimensionless and the least squares method filtering. This method implementation filtering and determine the scope of the dimensionless index. By doing experiments with 8 kinds of bearing failure data of petrochemical rotary sets, comparing four filtering methods, the scope of the dimensionless index was established, and the text combined dimensionless index respectively with Kalman (EKF), the weighted average, moving average, the least squares method filtering. © 2014 ACADEMY PUBLISHER.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Exploring Prompt-based Multi-task Learning for Multimodal Dialog State Tracking and Immersive Multimodal Conversation 11

Exploring Prompt-based Multi-task Learning for Multimodal Di...

引用

11th Dialog System technology Challenge, DSTC 2023

作者： Chen, Yirong Li, Ya Wang, Tao Xing, Xiaofen Xu, Xiangmin Liu, Quan Liu, Cong Hu, Guoping Guangdong Provincial Key Laboratory of Human Digital Twin School of EE South China University of Technology Guangzhou China iFLYTEK Research Hefei China Pazhou Lab. Guangzhou China School of Future Technology South China University of Technology Guangzhou China State Key Laboratory of Cognitive Intelligence Hefei China National Engineering Research Center of Speech and Language Information Processing Hefei China

With the rise of the metaverse, immersive multimodal conversation has attracted more and more researchers’ attention. Multimodal contexts will become more important for human-computer interaction in the metaverse, especially in shopping domain. Unlike traditional conversation tasks, immersive multimodal conversation has challenges such as multimodal ambiguous candidate identification and multimodal coreference resolution, which makes it more difficult to dialog state tracking and response generation, as described in SIMMC 2.1 challenge, a part of DSTC11. In particular, as the number of objects in the scene increases, the difficulty will increase dramatically. We proposed PMTLED (Prompt-based Multi-Task Learning Encoder-Decoder), in which different subtasks use different prompts to make the model tend to focus on the current subtask. We achieve the winner in ambiguous candidates indentification and runner-up in multimodal coreference resolution (MM-Coref), multimodal dialog state tracking (MM-DST) and assistant response generation. Our code and model are made publicly availab.e at https://***/scutcyr/dstc11-simmc2.1-scut-bds-lab. © 2023 Association for Computational Linguistics.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Parallel implementation of apriori algorithm based on MapReduce

Parallel implementation of apriori algorithm based on MapRed...

引用

13th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing, SNPD 2012

作者： Li, Ning Zeng, Li He, Qing Shi, Zhongzhi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China Graduate University Chinese Academy of Sciences Beijing 100139 China Key Lab. of Machine Learning and Computational Intelligence College of Mathematics and Computer Science Hebei University Baoding 071002 Hebei China

ISBN: (纸本)9780769547619

Searching frequent patterns in transactional databases is considered as one of the most important data mining problems and Apriori is one of the typical algorithms for this task. Developing fast and efficient algorithms that can handle large volumes of data becomes a challenging task due to the large databases. In this paper, we implement a parallel Apriori algorithm based on MapReduce, which is a framework for processing huge datasets on certain kinds of distributable problems using a large number of computers (nodes). The experimental results demonstrate that the proposed algorithm can scale well and efficiently process large datasets on commodity hardware. © 2012 IEEE.

关键词： MapReduce

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：