检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Ntavelis, Evangelos Romero, Andrés Kastanis, Iason van Gool, Luc Timofte, Radu Computer Vision Lab. ETH Zurich Switzerland Robotics and Machine Learning CSEM SA Switzerland PSI ESAT KU Leuven Belgium

Recent advances in image generation gave rise to powerful tools for semantic image editing. However, existing approaches can either operate on a single image or require an abundance of additional information. They are not capable of handling the complete set of editing operations, that is addition, manipulation or removal of semantic concepts. To address these limitations, we propose SESAME, a novel generator-discriminator pair for Semantic Editing of Scenes by Adding, Manipulating or Erasing objects. In our setup, the user provides the semantic lab.ls of the areas to be edited and the generator synthesizes the corresponding pixels. In contrast to previous methods that employ a discriminator that trivially concatenates semantics and image as an input, the SESAME discriminator is composed of two input streams that independently process the image and its semantics, using the latter to manipulate the results of the former. We evaluate our model on a diverse set of datasets and report state-of-the-art performance on two tasks: (a) image manipulation and (b) image generation conditioned on semantic lab.ls. Copyright © 2020, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Support vector machine for suppressing error method

Support vector machine for suppressing error method

引用

1st International Conference on Information Science and Engineering, ICISE2009

作者： Lu, Shuxia Shi, Pu Chen, Ming Key Lab. of Machine Learning and Computational Intelligence College of Mathematics and Computer Science Hebei University Baoding China Baoding Pascali Cable TV Integrater Information Network Co. Ltd. Baoding China College of Mathematics and Computer Science Hebei University Baoding China

ISBN: (纸本)9780769538877

Support Vector machine (SVM) is sensitive to noises and outliers. For reducing the effect of noises and outliers, we propose a novel SVM for suppressing error function. The error function is limited to the interval of [0, 1]. The separation hypersurface is simplified and the margin of hypersurface is widened. Experimental results show that our proposed method is able to simultaneously increase the classification efficiency and the generalization ability of the SVM.

关键词： Support vector machines

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

A text classification method based on the improved CR-tree and the weighted association rule

引用

Journal of Computational Information Systems 2009年第6期5卷 1577-1584页

作者： Wang, Yu Zhao, Yao Yuan, Fang College of Mathematics and Computer Science Hebei University Baoding 071002 China Key Lab. in Machine Learning and Computational Intelligence of Hebei Province Baoding 071002 China

Classification based on association rules is a common and easily understand algorithm for text classification. To improve its classification accuracy, the key is to generate more effective rules. Sometimes, it will overdraw the role of some training texts. To avoiding this and generate more effective rules, this paper defines the Classification Path and proposes a new text classifier (CP-tree) based on CR-tree. When a new text is coming, to avoid overdrawing, association rules are generated through scanning Classification Path;in addition, to make the role of association rules in class prediction more reasonable, the association rules and weight for the new text are obtained not only according to the training texts, but also the new texts. Experimental results show that the accuracy of text classification is improved with the algorithm based on CP-tree. 1553-9105/ Copyright © 2009 Binary Information Press.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Unsupervised feature selection based on feature relevance

Unsupervised feature selection based on feature relevance

引用

International Conference on machine learning and Cybernetics (ICMLC)

作者： Feng Zhang Ya-Jun Zhao Jun-Fen Key Lab. of Machine Learning and computational Intelligence Hebei University Baoding China College of Physics Science and Technology Hebei University Baoding China Key Lab. of Machine Learning and computational Intelligence College of Mathematics and Computer Science Hebei University Baoding 071002 China

Feature selection is an essential technique used in data mining and machine learning. Many feature selection methods have been studied for supervised problems. However feature selection for unsupervised learning is rarely studied. In this paper, we proposed an approach to select features for unsupervised problems. Firstly, the original features are clustered according to their relevance degree defined by mutual information. And then the most informative feature is selected from each cluster based on the contribution-information of each feature. The experimental results show that the proposed method can match some popular supervised feature selection methods. And the features selected by our method do include most of the information hidden in the overall original features.

关键词： machine learning Mutual information Random variables Entropy Unsupervised learning Information theory Cybernetics Educational institutions Data mining Computational intelligence

来源：评论

学校读者我要写书评

暂无评论

A HSC-based sample selection method for Support Vector machine

A HSC-based sample selection method for Support Vector Machi...

引用

International Conference on machine learning and Cybernetics

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

ISBN: (纸本)9781424465262

Support Vector machine (SVM) is a classification technique of machine learning based on statistical learning theory. A quadratic optimization problem needs to be solved in the algorithm, and with the increase of the samples, the time complexity will also increase. So it is necessary to shrink training sets to reduce the time complexity. A sample selection method for SVM is proposed in this paper. It is inspired from the Hyper surface classification (HSC), which is a universal classification method based on Jordan Curve Theorem, and there is no need for mapping from lower-dimensional space to higher-dimensional space. The experiments show that the algorithm shrinks training sets keeping the accuracy for unseen vectors high. © 2010 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A deep web interface integration approach based on domain knowledge and submitting queries

引用

Journal of Information and Computational Science 2009年第3期6卷 1103-1111页

作者： Yuan, Fang Liu, Hongfei Wei, Yonggang Yao, Zengli College of Mathematics and Computer Science Hebei University Hebei Baoding 071002 China Key Lab. in Machine Learning and Computational Intelligence of Hebei Province Hebei Baoding 071002 China

Deep Web can provide us a great amount of high quality information. In order to make full use of the information, it is becoming urgent to establish Deep Web data integration system, in which Deep Web interface integration is an important component. This paper proposes a deep web interface integration method based on domain knowledge and submitting queries for certain domains. Before application this method, we categorize Deep Web interfaces according to their structures and introduce the concept of interface element, which be used to represent the interface. This approach first selects the required attributes, and then matches these attributes in each interface element, after that integrates each interface element which matches the same attribute to generate the global interface. This method includes interface template matching, domain knowledge-based interface elements matching and submitting queries-based interface elements matching, etc. Experimental results show that the proposed method has higher matching accuracy and lower dependency on preparatory work. 1548-7741/ Copyright © 2009 Binary Information Press.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation

arXiv

引用

arXiv 2021年

作者： Li, Wenhao Liu, Hong Tang, Hao Wang, Pichao Van Gool, Luc Key Laboratory of Machine Perception Shenzhen Graduate School Peking University China Computer Vision Lab. ETH Zurich Switzerland Alibaba Group China

Estimating 3D human poses from monocular videos is a challenging task due to depth ambiguity and self-occlusion. Most existing works attempt to solve both issues by exploiting spatial and temporal relationships. However, those works ignore the fact that it is an inverse problem where multiple feasible solutions (i.e., hypotheses) exist. To relieve this limitation, we propose a Multi-Hypothesis Transformer (MHFormer) that learns spatio-temporal representations of multiple plausible pose hypotheses. In order to effectively model multi-hypothesis dependencies and build strong relationships across hypothesis features, the task is decomposed into three stages: (i) Generate multiple initial hypothesis representations;(ii) Model self-hypothesis communication, merge multiple hypotheses into a single converged representation and then partition it into several diverged hypotheses;(iii) Learn cross-hypothesis communication and aggregate the multi-hypothesis features to synthesize the final 3D pose. Through the above processes, the final representation is enhanced and the synthesized pose is much more accurate. Extensive experiments show that MHFormer achieves state-of-the-art results on two challenging datasets: Human3.6M and MPI-INF-3DHP. Without bells and whistles, its performance surpasses the previous best result by a large margin of 3% on Human3.6M. Code and models are availab.e at https://***/Vegetebird/MHFormer. Copyright © 2021, The Authors. All rights reserved.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

A new instance selection algorithm based on contribution for nearest neighbour classification

A new instance selection algorithm based on contribution for...

引用

International Conference on machine learning and Cybernetics

作者： Cai, Yong-Hua Wu, Bo He, Yu-Lin Zhang, Ye Department of Mathematics and Computer Science Hebei Normal University for Nationalities Chengde067000 Hebei China Automation Department Chengde Iron and Steel Branch Hebei Iron and Steel Group Co. Ltd. Chengde 067000 Hebei China Key Lab. of Machine Learning and Computational Intelligence College of Mathematics and Computer Science Hebei University Baoding 071002 Hebei China

ISBN: (纸本)9781424465262

Nearest Neighbor Classifier is one of the most classical lazy learning schemes. The basic nearest neighbor classifiers suffer from the common problem that the instances used to train the classifier are all stored indiscriminately, and as a result, the required memory storage is huge and response time becomes slow with a large database. In this paper, a new Instances Selection algorithm based on Classification Contribution Function shortly named ISCC is presented. In this algorithm, a function is introduced to evaluate the classification ability of the instances. For each instance, the function considers its contribution to the neighbor instances not only with same class but also with different class. Then an instance with the highest value of Classification Contribution Function is added to the condensed subset and the instances which can be classified correctly are deleted in each iteration. This process is repeated until the subset is no longer getting larger. The time complexity of ISCC is Ο (in2). The experimental results on two artificial databases and some real databases demonstrate the effectiveness and the feasibility of the proposed algorithm. Compared to traditional methods, such as MCS, ICF and ENN, the condensed sets obtained by ISCC is superior in storage and classification accuracy. © 2010 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Inconsistency Distillation For Consistency:Enhancing Multi-View Clustering via Mutual Contrastive Teacher-Student Leaning

Inconsistency Distillation For Consistency:Enhancing Multi-V...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Dunqiang Liu Shu-Juan Peng Xin Liu Lei Zhu Zhen Cui Taihao Li Dept. of Comput. Sci. & Fujian Key Lab. of Big Data Intelligence and Security Huaqiao University Xiamen China Zhejiang Lab Hangzhou China Xiamen Key Lab. of Computer Vision and Pattern Recognition Huaqiao University Xiamen China Key Lab. of Computer Vision and Machine Learning (Huaqiao University) Fujian Province University Xiamen China School of Information Sci. and Eng. Shandong Normal University Jinan China School of Computer Sci. and Eng. Nanjing University of Science and Technology Nanjing China

Multi-view clustering has attracted more attention recently since many real-world data are comprised of different representations or views. Recent multi-view clustering works mainly exploit the instance consistency to obtain the shared representations across different views, and apply a single-view clustering method to perform data partitions. However, these existing methods often ignore the inconsistency of instance associations within the views, which may enlarge the intra-class diversity among the views and therefore degrade the clustering performance. To address this issue, this paper proposes an efficient mutual contrastive teacher-student leaning (MC-TSL) model to enhance the multi-view clustering, which is the first attempt to study the inconsistency distillation for consistency learning. First, the proposed MC-TSL approach exploits a view-specific encoder with two heads, an instance encoding head and a semantic distillation head, respectively, for capturing the consistent and discriminative feature representations. To be specific, the former head exploits a cross-view contrastive learning method to obtain a redundancy-free consistent representation at the instance level, while the latter head designs a mutual teacher-student learning module to capture the intra-view information at semantic level. By training these two heads in an end-to-end manner, the discriminative multi-view embeddings are efficiently obtained and refined by minimizing the weighted sum of the reconstruction loss, contrastive loss and contrast distillation loss. Extensive experiments verify the superiorities of the proposed MC-TSL framework and show its competitive clustering performances.

关键词： Training learning systems Clustering methods Semantics Encoding Data mining

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：