检索结果-内蒙古大学图书馆

作者： Pishchulin, Leonid Gass, Tobias Dreuw, Philippe Ney, Hermann MPI for Informatics - Computer Vision and Multimodal Computing Group Campus E1 4 D-66123 Saarbrücken Germany ETH Zurich Computer Vision Lab. Sternwartstrasse 7 CH-8092 Zurich Switzerland RWTH Aachen - Department 6 Ahornstr. 55 D-52056 Aachen Germany

This paper systematically analyzes the strengths and weaknesses of existing image warping algorithms on the tasks of face recognition. Image warping is used to cope with local and global image variability and in general is an NP-complete problem. Although many approximations have recently been proposed, neither thorough comparison, nor systematic analysis of methods in a common scheme has been done so far. We follow the bottom-up approach and analyze the methods with increasing degree of image structure preserved during optimization. We evaluate the presented warping approaches on four challenging face recognition tasks in highly variable domains. Our findings indicate that preserving maximum dependencies between neighboring pixels by imposing strong geometrical constraints leads to the best recognition results while making optimization efficient. © 2011 Elsevier Ltd. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Knowledge discovery approach based on closeness relationship of FC

Knowledge discovery approach based on closeness relationship...

引用

6th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2009

作者： Zhang, Degan Li, Miao Zhang, Xiaoli Wang, Jinhui Tianjin Key Lab. of Intelligent Computing and Novel Software Technology Tianjin University of Technology Tianjin 300191 China Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin 300191 China

ISBN: (纸本)9780769537351

A fuzzy clustering is one of important and valid methods to knowledge discovery. One of problems in fuzzy clustering is to determine a certain fuzzy sample classification in given limited sample space. Another is its validity, that is to say, if the sample is resemble in sample space, its fuzzy type will be resemble too. In our research, firstly, using triangle arithmetic operator and triangle transference, we extend fuzzy equivalence relationship to fuzzy closeness relationship, and cluster. Secondly, importing fuzzy coverage based on fuzzy closeness relationship, we judge resemble type of resemble sample. Thirdly, we introduce the clustering method based on fuzzy closeness relationship and fuzzy coverage. The method can overcome information more loss in fuzzy equivalence. Finally, evaluating its validity, we test its feasibility. The method above is applied to knowledge discovery for electronic commerce on Internet, we have got good result. © 2009 IEEE.

关键词： Fuzzy clustering

来源：评论

学校读者我要写书评

暂无评论

A hybrid efficient short-term traffic flow forecast technology

A hybrid efficient short-term traffic flow forecast technolo...

引用

6th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2009

作者： Lin, Xin Wang, Xiaoye Xiao, Yingyuan Zhang, Degan Tianjin Key Lab. of Intelligent Computing and Novel Software Technology Tianjin University of Technology Tianjin 300191 China Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin 300191 China

ISBN: (纸本)9780769537351

This paper presents a hybrid short-term traffic flow forecast technology. For the uncertainty, the short-term traffic flow forecast is complicated, and the accuracy is not high. This strategy combines the RBF neural network and ant colony clustering algorithm to forecast the traffic flow. It used ant colony clustering algorithm to get the centers of hidden layer neurons. To find the best clustering result, local search is used in ant colony algorithm. The model has strong local generalization abilities and high accuracy. The simulation experiment results illuminate that the application is fairly effective. © 2009 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

An efficient web service composition approach based on improved particle swarm optimization model

An efficient web service composition approach based on impro...

引用

International Conference on Management and Service Science, MASS 2009

作者： Yi, Liang Yingyuan, Xiao Tianjin Key Lab. of Intelligent Computing and Novel Software Technology Tianjin University of Technology Tianjin 300191 China Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin 300191 China

ISBN: (纸本)9781424446391

Along with the rapid growth of the number of the availab.e web services over the internet, the quality of services (Qos) becomes an imperative concern for service consumers and providers. How to differentiate their quality based on Qos criteria at web service level is a challenging issue. Considering that evolutionary algorithm has powerful ability of searching information, a new web service composition model under improved particle swarm optimization (IPSO) algorithm is presented in this paper. According to the non-functional attributes Qos of services, the model can select web services with optimal Qos and compose them into value-added web services. Furthermore, IPSO model not only can find the service with optimal Qos immediately but also can overcome the bottleneck of the standard PSO model. It can balance the exploitation and exploration and avoid premature convergence to some extent. As a result, web services can be invocated dynamically and be composed automatically and efficiently. The preliminary experimental results indicate that the web service composition approach based on IPSO model is applicable and feasible to the optimization of general service compositions. ©2009 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

A novel two-step-deformation active contour with application to facial features extraction

A novel two-step-deformation active contour with application...

引用

2009 2nd International Congress on Image and Signal Processing, CISP'09

作者： Hua, Zhang Yuanquan, Wang Tianjin Key Lab. of Intelligent Computing and Novel Software Technology Tianjin University of Technology Tianjin 300191 China Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin 300191 China

ISBN: (纸本)9781424441310

In allusion to the boundary leaking problem of traditional active contours when used to extract facial features, two kinds of local information are introduced to enhance the weak boundary, then to build new external force for active contours. The prior knowledge of the local shape of the facial features is incorporated into the evolution of active contour. The snake contour in each evolution step just serves as prediction, and then is ruled by the prior local shape;this way, the snake contour deforms via prediction-correction two steps. This two-step-deformation (TSD) snake can utilize the a priori shape of objects effectively. The proposed strategies are evaluated on several images and the experimental results validate the high performance of this TSD snake for facial features segmentation. ©2009 IEEE.

关键词： Deformation

来源：评论

学校读者我要写书评

暂无评论

Research on multi-dimensional association rules mining in distributed environments based on advanced SQL query

Research on multi-dimensional association rules mining in di...

引用

6th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2009

作者： Zhang, Lei Qiao, Mei Zhang, Degan Tianjin Key Lab. of Intelligent Computing and Novel Software Technology Tianjin University of Technology Tianjin 300191 China Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin 300191 China

ISBN: (纸本)9780769537351

This paper proposes the MDMA (Multi-dimensional Distributed Mining Association rules) algorithm based on advanced SQL query. The algorithm works on star-style structure networks. It uses CUBE operator in new standard SQL and combines with SQL powerful query function. So there is no need for the proposed algorithm to conduct a great deal of iterations to generate frequent itemsets in the process of mining association rules. Therefore, no matter what the number of the site in the distributed environments and the scale of the local database in the local site is, the algorithm always needs only two times of scanning the database and only three times of network communications to generate all the global frequent itemsets. Consequently, this algorithm has the merits of light network traffic, low time cost, better scalab.lity and more simplicity. © 2009 IEEE.

关键词： Association rules

来源：评论

学校读者我要写书评

暂无评论

Image Captioning with Clause-Focused Metrics in a Multi-Modal Setting for Marketing

arXiv

引用

arXiv 2019年

作者： Harzig, Philipp Zecha, Dan Lienhart, Rainer Kaiser, Carolin Schallner, René Multimedia Computing and Computer Vision Lab University of Augsburg Augsburg86159 Germany GfK Verein Nuremberg90419 Germany

Automatically generating descriptive captions for images is a well-researched area in computer vision. However, existing evaluation approaches focus on measuring the similarity between two sentences disregarding fine-grained semantics of the captions. In our setting of images depicting persons interacting with branded products, the subject, predicate, object and the name of the branded product are important evaluation criteria of the generated captions. Generating image captions with these constraints is a new challenge, which we tackle in this work. By simultaneously predicting integer-valued ratings that describe attributes of the human-product interaction, we optimize a deep neural network architecture in a multi-task learning setting, which considerably improves the caption quality. Furthermore, we introduce a novel metric that allows us to assess whether the generated captions meet our requirements (i.e., subject, predicate, object, and product name) and describe a series of experiments on caption quality and how to address annotator disagreements for the image ratings with an approach called soft targets. We also show that our novel clause-focused metrics are also applicable to other image captioning datasets, such as the popular MSCOCO dataset. Copyright © 2019, The Authors. All rights reserved.

关键词： Integer programming

来源：评论

学校读者我要写书评

暂无评论

Multimodal image captioning for marketing analysis

arXiv

引用

arXiv 2018年

作者： Harzig, Philipp Brehm, Stephan Lienhart, Rainer Kaiser, Carolin Schallner, René Multimedia Computing and Computer Vision Lab University of Augsburg Augsburg86159 Germany GfK Verein Nuremberg90419 Germany

Automatically captioning images with natural language sentences is an important research topic. State of the art models are able to produce human-like sentences. These models typically describe the depicted scene as a whole and do not target specific objects of interest or emotional relationships between these objects in the image. However, marketing companies require to describe these important attributes of a given scene. In our case, objects of interest are consumer goods, which are usually identifiable by a product logo and are associated with certain brands. From a marketing point of view, it is desirable to also evaluate the emotional context of a trademarked product, i.e., whether it appears in a positive or a negative *** address the problem of finding brands in images and deriving corresponding captions by introducing a modified image captioning network. We also add a third output modality, which simultaneously produces real-valued image ratings. Our network is trained using a classificationaware loss function in order to stimulate the generation of sentences with an emphasis on words identifying the brand of a product. We evaluate our model on a dataset of images depicting interactions between humans and branded products. The introduced network improves mean class accuracy by 24.5 percent. Thanks to adding the third output modality, it also considerably improves the quality of generated captions for images depicting branded products. Copyright © 2018, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Automatic sign language recognition: vision based feature extraction and probabilistic recognition scheme from multiple cues 08

Automatic sign language recognition: Vision based feature ex...

引用

1st International Conference on Pervasive Technologies Related to Assistive Environments, PETRA 2008

作者： Caridakis, George Diamanti, Olga Karpouzis, Kostas Maragos, Petros Image Video and Multimedia Systems Lab. National Technical University of Athens Iroon Polytexneiou 9 15780 Athens Greece Computer Vision Speech Communication and Signal Processing Group National Technical University of Athens Iroon Polytexneiou 9 15780 Athens Greece

ISBN: (纸本)9781605580678

This work focuses on two of the research problems comprising automatic sign language recognition, namely robust computer vision techniques for consistent hand detection and tracking, while preserving the hand shape contour which is useful for extraction of features related to the handshape and a novel classification scheme incorporating Self-organizing maps, Markov chains and Hidden Markov Models. Geodesic Active Contours enhanced with skin color and motion information are employed for the hand detection and the extraction of the hand silhouette, while features extracted describe hand trajectory, region and shape. Extracted features are used as input to separate classifiers, forming a robust and adaptive architecture whose main contribution is the optimal utilization of the neighboring characteristic of the SOM during the decoding stage of the Markov chain, representing the sign class. Copyright 2008 ACM.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A kind of service-aware computing method for Web-based mobile application with uncertainty

A kind of service-aware computing method for Web-based mobil...

引用

2010 IEEE 5th International Conference on Bio-Inspired computing: Theories and Applications, BIC-TA 2010

作者： Zhang, De-Gan Kang, Xue-Jing Dai, Wen-Bo Chen, Ying Fayek, Moaty Tianjin Key Lab. of Lntelligent Computing and Novel Software Technology Tianjin University of Technology 300191 China Key Laboratory of Computer Vision and System Tianjin University of Technology Ministry of Education 300191 Tiajin China Department of Computer Science California State University Chico CA 95929 United States

ISBN: (纸本)9781424464388

As we know, service-aware computing is an important part of pervasive computing for Web-based mobile application with uncertainty. We modified the fusion method of evidence information after considering context's reliability, time-efficiency, and relativity, which has improved the classical fusion rule of D-S (Dempster-Shafer) Evidence Theory when being used in the pervasive computing paradigm. We call it EDS. After extending the process, we overcome the drawbacks of classical D-S Evidence Theory. All these suggested technologies have been successfully used in our service-aware computing projects. The efficiency of our researches has been shown by our many application practices. © 2010 IEEE.

关键词： Ubiquitous computing

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：