检索结果-内蒙古大学图书馆

2016 IEEE information Technology,Networking,Electronic and Automation Control Conference(ITNEC 2016)

作者： Ouyang py Hu Hong Shi zhongzhi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences

ISBN: (纸本)9781467391955

Traditional methods for measuring and monitoring plankton populations are time consuming and can not scale to the granularity or scope necessary for large-scale *** approaches are needed. Manual analysis of the imagery captured by underwater camera system is infeasible. Automated image classification using machine learning tools is an alternative to the manual approach. In this paper, we present a deep neural network model for plankton classification which exploits translational and rotational symmetry. In this work, we propose two constrains in the design of deep convolutional neural network structure to guarantee the performance gain when going ***, for each convolutional layer, its capacity of learning more complex patterns should be guaranteed;Secondly, the receptive field of the topmost layer should be no larger than the image region. We also developed a "inception layer" like structure to deal with multi-size imagery input with convolutional neural network. The experimental result on Plankton Set 1.0 imagery data set show the feasibility and effectiveness of the proposed method.

关键词： deep learning image classification convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Superconvergence and asymptotic expansions for bilinear finite volume element approximation on non-uniform grids

引用

Journal of Computational and Applied Mathematics 2017年 321卷 323-335页

作者： Cunyun Nie Shi Shu Haiyuan Yu Wenhua Xia The School of Science Hunan Institute of Engineering 411104 China Hunan Key Laboratory for Computation & Simulation in Science and Engineering Xiangtan University Hunan 411105 China Key Laboratory of Intelligent Computing & Information Processing of Ministry of Education Xiangtan University Hunan 411105 China

We initially derive an asymptotic expansion and a high accuracy combination formula of the derivatives in the sense of pointwise for the isoparametric bilinear finite volume element scheme by employing the energy-embedded method on some non-uniform grids. Furthermore, we prove that the approximate derivatives are convergent of order two. Numerical examples confirm theoretical results.

关键词： Isoparametric bilinear finite volume element scheme Non-uniform grids Asymptotic expansion Superconvergence

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous convolutional neural networks for visual recognition 17th

Heterogeneous convolutional neural networks for visual recog...

引用

17th Pacific-Rim Conference on Multimedia, PCM 2016

作者： Li, Xiangyang Herranz, Luis Jiang, Shuqiang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9783319488950

Deep convolutional neural networks (CNNs) have shown impressive performance for image recognition when trained over large scale datasets such as ImageNet. CNNs can extract hierarchical features layer by layer starting from raw pixel values, and representations from the highest layers can be efficiently adapted to other visual recognition tasks. In this paper, we propose heterogeneous deep convolutional neural networks (HCNNs) to learn features from different CNN models. Features obtained from heterogeneous CNNs have different characteristics since each network has a different architecture with different depth and the design of receptive fields. HCNNs use a combination network (i.e. another multi-layer neural network) to learn higher level features combining those obtained from heterogeneous base neural networks. The combination network is also trained and thus can better integrate features obtained from heterogeneous base networks. To better understand the combination mechanism, we backpropagate the optimal output and evaluate how the network selects features from each model. The results show that the combination network can automatically leverage the different descriptive abilities of the original models, achieving comparable performance on many challenging benchmarks. © Springer International Publishing AG 2016.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Where and what to eat: Simultaneous restaurant and dish recognition from food image 17th

Where and what to eat: Simultaneous restaurant and dish reco...

引用

17th Pacific-Rim Conference on Multimedia, PCM 2016

作者： Wang, Huayang Min, Weiqing Li, Xiangyang Jiang, Shuqiang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9783319488899

This paper considers the problem of simultaneous restaurant and dish recognition from food images. Since the restaurants are known because of their some special dishes (e.g., the dish "hamburger" in the restaurant "KFC"), the dish semantics from the food image provides partial evidence for the restaurant identity. Therefore, instead of exploiting the binary correlation between food images and dish labels by existing work, we model food images, their dish names and restaurant information jointly, which is expected to enable novel applications, such as food image based restaurant visualization and recommendation. For solution, we propose a model, namely Partially Asymmetric Multi- Task Convolutional Neural Network (PAMT-CNN), which includes the dish pathway and the restaurant pathway to learn the dish semantics and the restaurant identity, respectively. Considering the dependence of the restaurant identity on the dish semantics, PAMT-CNN is capable of learning the restaurant’s identity under the guidance of the dish pathway using partially asymmetric shared network architecture. To evaluate our model, we construct one food image dataset with 24,690 food images, 100 classes of restaurants and 100 classes of dishes. The evaluation results on this dataset have validated the effectiveness of the proposed approach. © Springer International Publishing AG 2016.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A novel HEFTS-L algorithm for scheduling large number of DAG tasks

A novel HEFTS-L algorithm for scheduling large number of DAG...

引用

2017 3rd Workshop on Advanced Research and Technology in Industry Applications(WARTIA 2017)

作者： Xin Liu Rongbin Xu Yongliang Cheng Pengfei Zhang Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education School of Computer Science and Technology Anhui University Co-Innovation Center for Information Supply & Assurance Technology Anhui University

In recent years, along with the development of technologies for distributed computing such as big data and clouds workflow systems, efficiency of workflow scheduling has become very impotent. Hence sc

关键词：

来源：评论

学校读者我要写书评

暂无评论

A High Performance Asynchronous Non-blocking Data Communication Protocol 7

A High Performance Asynchronous Non-blocking Data Communicat...

引用

2016 IEEE 7th International Conference on Software Engineering and Service Science

作者： Guimin Huang Zhi Zheng Ya Zhou Key Laboratory of Cognitive Radio and Information Processing of Ministry of Education Guangxi Experiment Center of Information Science Research Center on Data Science & Social Computing Guilin University of Electronic Technology

ISBN: (纸本)9781467399050

In this paper,we design a high-performance data communication message-oriented protocol(ECP),which is based on asynchronous non-blocking I/O model,used reactor design mode,introduced pipeline,and is on top of TCP without modifying the operating system underlying *** is very effective in the environment that has a great demand of network communication,especially in the case of large-scale data communication and high concurrent requests.

关键词： asynchronous non-blocking pipeline protocol communication

来源：评论

学校读者我要写书评

暂无评论

Time matters: Multi-scale temporalization of social media popularity

arXiv

引用

arXiv 2017年

作者： Wu, Bo Cheng, Wen-Huang Zhang, Yongdong Mei, Tao Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Research Center for Information Technology Innovation Academia Sinica Taiwan Microsoft Research China

The evolution of social media popularity exhibits rich temporality, i.e., popularities change over time at various levels of temporal granularity. This is influenced by temporal variations of public attentions or user activities. For example, popularity patterns of street snap on Flickr are observed to depict distinctive fashion styles at specific time scales, such as season-based periodic fluctuations for Trench Coat or one-off peak in days for Evening Dress. However, this fact is often overlooked by existing research of popularity modeling. We present the first study to incorporate multiple time-scale dynamics into predicting online popularity. We propose a novel computational framework in the paper, named Multi-scale Temporalization, for estimating popularity based on multi-scale decomposition and structural reconstruction in a tensor space of user, post, and time by joint low-rank constraints. By considering the noise caused by context inconsistency, we design a data rearrangement step based on context aggregation as preprocessing to enhance contextual relevance of neighboring data in the tensor space. As a result, our approach can leverage multiple levels of temporal characteristics and reduce the noise of data decomposition to improve modeling effectiveness. We evaluate our approach on two large-scale Flickr image datasets with over 1.8 million photos in total, for the task of popularity prediction. The results show that our approach significantly outperforms state-of-the-art popularity prediction techniques, with a relative improvement of 10.9%-47.5% in terms of prediction accuracy. Copyright © 2017, The Authors. All rights reserved.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

4D ISIP: 4D implicit surface interest point detection

arXiv

引用

arXiv 2017年

作者： Li, Shirui Yilmaz, Alper Xiao, Changlin Li, Hua Key Laboratory of Intelligent Information Processing Chinese Academy of Sciences Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Ohio State University OH United States

In this paper, we proposed a new method to detect 4D spatiotemporal interest point called 4D-ISIP(4 dimension implicit surface interest point). We implicitly represent the 3D scene by 3D volume which has a truncated signed distance function (TSDF) in every voxel. The TSDF represents the distance between the spatial point and object surface which is a kind of implicit surface representation. The basic idea of 4D-ISIP detection is to detect the points whose local neighborhood has significant variations along both spatial and temporal dimensions. In order to test our 4D-ISIP detection, we built a system to acquire 3D human motion dataset using only one Kinect. Experimental results show that our method can detect 4D-ISIP for different human actions. Copyright © 2017, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

A subtree-based factorization of dependency parsing 26

A subtree-based factorization of dependency parsing

引用

26th International Conference on Computational Linguistics, COLING 2016

作者： Zhao, Qiuye Liu, Qun Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China ADAPT Centre School of Computing Dublin City University Ireland

ISBN: (纸本)9784879747020

We propose a dependency parsing pipeline, in which the parsing of long-distance projections and localized dependencies are explicitly decomposed at the input level. A chosen baseline dependency parsing model performs only on 'carved' sequences at the second stage, which are transformed from coarse constituent parsing outputs at the first stage. When k-best constituent parsing outputs are kept, a third-stage is required to search for an optimal combination of the overlapped dependency subtrees. In this sense, our dependency model is subtree-factored. We explore alternative approaches for scoring subtrees, including feature-based models as well as continuous representations. The search for optimal subset to combine is formulated as an ILP problem. This framework especially benefits the models poor on long sentences, generally improving baselines by 0.75-1.28 (UAS) on English, achieving comparable performance with high-order models but faster. For Chinese, the most notable increase is as high as 3.63 (UAS) when the proposed framework is applied to first-order parsing models. © 1963-2018 ACL.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Block-Based Projection Matrix Design for Compressed Sensing

引用

Chinese Journal of Electronics 2016年第3期25卷 551-555页

作者： LI Zhetao XIE Jingxiong ZHU Gengming PENG Xin XIE Yanrong CHOI Youngjune The College of Information Engineering Xiangtan University School of Computer National University of Defense Technology Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University School of Computer Science and Engineering Hunan University of Science and Technology College of Information and Communication Engineering Hunan Institute of Science and Technology Department of Information and Computer Engineering Ajou University

The objective of optimizing a projection matrix is to decrease the mutual coherence between a projection matrix and a basis matrix. In this paper, a novel block-based method is proposed to design a projection matrix in compressed sensing. Here, the projection matrix is divided into two blocks. The relationship between the two blocks was obtained by reasoning and proving. Theoretical analysis demonstrates that the mutual coherence between the whole projection matrix and the whole basis matrix keeps as good as the mutual coherence between the block matrix and blocked basis matrix. Experimental results show that the proposed method obtains better performance compared to existing methods.

关键词： Compressed sensing Projection matrix Block optimization Mutual coherence

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：