检索结果-内蒙古大学图书馆

Firth IEEE International Conference on Cognitive Informatics(第五届认知信息国际会议)

作者： Sulan Zhang Chunqi Shi Zhiyong Zhang Zhongzhi Shi Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of

ISBN: (纸本)9781424404759

We propose two geometric structure based approaches GGCI (global geometric clustering for image) and GSIM (geometric structure based image matching) for image clustering and image matching, respectively. For face images or object images taken with varying factors, the GGCI approach learns the global geometric structure of images space and clusters images based on geodesic distance instead of Euclidean distance and the extended nearest neighbor approach. The GSIM approach uses the minimal Euclidean distance between parts of image and the pattern and its variations as matching criteria and threshold strategy for image matching. We demonstrate experimentally that the GGCI approach achieves lower error rates and the GSIM approach brings down the sensitivity of gray values to change in radiometry and reduces multi local extrema to some extent.

关键词： geometric structure perception geodesic distance image clustering image matching.

来源：评论

学校读者我要写书评

暂无评论

A parallel scheme for three-dimensional reconstruction in large-field electron tomography

A parallel scheme for three-dimensional reconstruction in la...

引用

10th International Symposium on Bioinformatics Research and Applications, ISBRA 2014

作者： Zhang, Jingrong Wan, Xiaohua Zhang, Fa Ren, Fei Wang, Xuan Liu, Zhiyong Key Lab. of Intelligent Information Processing and Advanced Computing Research Lab Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Yanshan University Yanshan China

ISBN: (纸本)9783319081700

Large-field high-resolution electron tomography enables visualizing detailed mechanisms under global structure. As field enlarges, the processing time increases and the distortions in reconstruction become more critical. Adopting a nonlinear projection model instead of a linear one can compensate for curvilinear trajectories, nonlinear electron optics and sample warping. But the processing time for the reconstruction with nonlinear projection model is rather considerable. In this work, we propose a new parallel strategy for block iterative reconstruction algorithms. We also adopt a page-based data transfer in this strategy so as to dramatically reduce the processing time for data transfer and communication. We have tested this parallel strategy and it can yield speedups of approximate 40 times according to our experimental results. © 2014 Springer International Publishing Switzerland.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Bayesian dual neural networks for recommendation

引用

Frontiers of Computer Science 2019年第6期13卷 1255-1265页

作者： Jia HE Fuzhen ZHUANG Yanchi LIU Qing HE Fen LIN Key Lab of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China Rutgers University Newark 07102USA Search Product Center WeChat Search Application DepartmentTencentBeijing 100080China

Most traditional collaborative filtering(CF)methods only use the user-item rating matrix to make recommendations,which usually suffer from cold-start and sparsity *** address these problems,on the one hand,some CF methods are proposed to incorporate auxiliary information such as user/item profiles;on the other hand,deep neural networks,which have powerful ability in learning effective representations,have achieved great success in recommender ***,these neural network based recommendation methods rarely consider the uncertainty of weights in the network and only obtain point estimates of the ***,they maybe lack of calibrated probabilistic predictions and make overly confident *** this end,we propose a new Bayesian dual neural network framework,named BDNet,to incorporate auxiliary information for ***,we design two neural networks,one is to learn a common low dimensional space for users and items from the rating matrix,and another one is to project the attributes of users and items into another shared latent *** that,the outputs of these two neural networks are combined to produce the final ***,we introduce the uncertainty to all weights which are represented by probability distributions in our neural networks to make calibrated probabilistic *** experiments on real-world data sets are conducted to demonstrate the superiority of our model over various kinds of competitors.

关键词： collaborative filtering Bayesian neural network hybrid recommendation algorithm

来源：评论

学校读者我要写书评

暂无评论

Fusion of polarization image based on curvelet transform

Fusion of polarization image based on curvelet transform

引用

2014 2nd International Conference on Mechatronics, Robotics and Automation, ICMRA 2014

作者： Zhang, De Xiang Wang, Hong Hai Xue, Feng The Department of Information and Communication Technology Anhui Sanlian University Hefei 230601 China Key Lab. of Intelligent Computing and Signal Processing Anhui University Hefei 230039 China

ISBN: (纸本)9783038350781

Curvelet transform is the combination of the multi-scale analysis and multi-directional analysis transforms, which is more suitable for objects with curves. Applications of the curvelet transform have increased rapidly in the field of image fusion. Firstly, using the curvelet transform, several polarization images can be decomposed into low-frequency coefficients and high-frequency coefficients with multi-scales and multi-directions. For the low-frequency coefficients, the average fusion method is used. For the each directional high frequency sub-band coefficients, the larger value of region variance information measurement is used to select the better coefficients for fusion. At last the fused image can be obtained by utilizing inverse transform for fused curvelet coefficients. In the present work an algorithm for image fusion based on the curvelet transform was implemented, analyzed, and compared with a wavelet-based fusion algorithm. Experimental results show that the proposed algorithm works better in preserving the edges and texture information compared with the wavelet-based image fusion algorithms. © (2014) Trans Tech Publications, Switzerland.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Memory-enhanced Decoder for neural machine translation

Memory-enhanced Decoder for neural machine translation

引用

2016 Conference on Empirical Methods in Natural Language processing, EMNLP 2016

作者： Wang, Mingxuan Lu, Zhengdong Li, Hang Liu, Qun Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China Noah's Ark Lab Huawei Technologies ADAPT Centre School of Computing Dublin City University Ireland

ISBN: (纸本)9781945626258

We propose to enhance the RNN decoder in a neural machine translator (NMT) with external memory, as a natural but powerful extension to the state in the decoding RNN. This memory-enhanced RNN decoder is called MEMDEC. At each time during decoding, MEMDEC will read from this memory and write to this memory once, both with content-based addressing. Unlike the unbounded memory in previous work(Bahdanau et al., 2014) to store the representation of source sentence, the memory in MEMDEC is a matrix with predetermined size designed to better capture the information important for the decoding process at each time step. Our empirical study on Chinese-English translation shows that it can improve by 4.8 BLEU upon Groundhog and 5.3 BLEU upon on Moses, yielding the best performance achieved with the same training set. © 2016 Association for Computational Linguistics

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

A fast thinning algorithm for fingerprint image

A fast thinning algorithm for fingerprint image

引用

1st International Conference on information Science and Engineering, ICISE2009

作者： Xiang, Ming Wu, Xiaopei Hua, Quanping Key Lab. of Intelligent Computing and Signal Processing Anhui University Hefei230039 China Department of Information Engineering Zhejiang Textile and Fashion College Ningbo315211 China

ISBN: (纸本)9780769538877

Thinning algorithms can be classified into two general types: serial and parallel algorithms. Several algorithms have been proposed, but they have limitations. A new thinning algorithm based on the centroid of the block is presented. The new algorithm checks the 9*9 local neighborhoods around the pixel to find out the centroid pixel of the block, and other pixels are removed. The process is performed iteratively until less than ten pixels are deleted in one loop. To ensure the ridge is one pixel wide, a post-processing loop is designed and the pixels are deleted from the image if they satisfy some conditions. Experimental results are used to compare this new algorithm to other algorithms and their relative performances are assessed. The new algorithm is fast than other algorithms and the ridges are one pixel wide after thinned. ©2009 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

DSMS in ubiquitous-healthcare: A Borealis-based heart rate variability monitor

DSMS in ubiquitous-healthcare: A Borealis-based heart rate v...

引用

2011 4th International Conference on Biomedical Engineering and Informatics, BMEI 2011

作者： Jiang, Xiaorui Yoo, Sooyoung Choi, Jinwook Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China Department of Biomedical Engineering Seoul National University Seoul Korea Republic of

ISBN: (纸本)9781424493524

With tremendous research progress in biomedical sensors and sensor networks, there is an increasingly need for employing new data processing technologies that are capable of online analysis of the streaming medical sensor data, which is a typical health monitoring scenario. This paper describes using the data stream management system (DSMS) in developing ubiquitous health monitoring application. We propose the system architecture suitable for simultaneously processing streaming data from heterogeneous sources and performing different monitoring tasks planned by clinicians. A pilot heart rate variability (HRV) monitor with a graphical user interface is developed based on Borealis and several tasks are implemented, including monitoring Rmssd, MeanHR (mean heart rate), and pNN50. Results of the test runs in the lab environment show the usefulness and potential of DSMS in performing intelligent realtime medical data processing. © 2011 IEEE.

关键词： Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

An analysis of current computational emotion models and systems

An analysis of current computational emotion models and syst...

引用

2nd Indian International Conference on Artificial Intelligence, IICAI 2005

作者： Zhan, Donglei Cao, Cungen Pan, Yu Wang, Haitao Yong, Xi Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences 10080 Beijing China Graduate School Chinese Academy of Sciences 100039 Beijing China

ISBN: (纸本)0972741216

Emotion study is a multi-disciplinary research subject. In the past three decades, a number of theoretical models of emotion and computer applications have been proposed from different perspectives including psychology, physiology, biology, and computer science. AI researchers have been striving to develop emotional systems by developing computational emotion models, in which systems or agents are believable and more human-like. This paper conducts a comprehensive analysis of current emotion research in computer science and different schools of thoughts based on six different perspectives or criteria - emotion type set, emotion simultaneity, role-orientedness, emotion situatedness, distributed emotion, and behavior display. We also propose a few problems which are less scratched and yet we believe are important for future research. Copyright © IICAI 2005.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Artifact reduction of compressed video via three-dimensional adaptive estimation of transform coefficients

Artifact reduction of compressed video via three-dimensional...

引用

作者： Zhang, Xinfeng Xiong, Ruiqin Ma, Siwei Gao, Wen Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Institute of Digital Media Peking University Beijing100871 China

ISBN: (纸本)9781479957514

Block transform compressed videos usually suffer from annoying artifacts at low bit rates, caused by the coarse quantization of transform coefficients. The inter prediction utilized in video coding also induces block boundary artifacts when the neighboring blocks using different motion vectors from previous decoded frames. In this paper, a three-dimensional adaptive estimation method for video transform coefficients is proposed to reduce the artifact in compressed video. In the proposed method, transform coefficients of each block are estimated by adaptively fusing three prediction sources based on their reliabilities. One prediction source is the transform coefficients directly acquired from the decoded video, whose reliability is determined by the distribution of the quantization noise. The other prediction source is derived by a temporal autoregressive model of transform-blocks along motion trajectory among neighboring reference frames. Its reliability is estimated from prediction variance of local blocks. The last prediction source is derived from the nonlocal transform-blocks, whose reliability is estimated based on the distribution of the nonlocal coefficients and their similarity with the estimated block. Experimental results for compressed video sequences by HEVC show that, the proposed method can reduce the compression artifacts and improve both the objective and subjective quality. © 2014 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Enhanced Semantic Head for Cascade Instance Segmentation

Enhanced Semantic Head for Cascade Instance Segmentation

引用

2022 IEEE International Conference on Multimedia and Expo, ICME 2022

作者： Huang, Xuerong Su, Li Li, Guorong Zhang, Xinfeng Qing, Laiyun Huang, Qingming University of Chinese Academy of Sciences Beijing China Cas Key Lab of Big Data Mining and Knowledge Management Beijing China Institute of Computing Technology Cas Key Lab of Intelligent Information Processing Beijing China

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

Recently, cascade instance segmentation inspired by cascade object detection has achieved notable performance. Due to the lack of global information, many methods suffer from incomplete segmentation such as missing edge regions and discontinuities within instances. To solve this problem, we proposed an effective and flexible semantic head to extract enhanced spatial context information. A vision transformer is utilized to generate global context features, and a convolution network is adopted to generate spatial context features. After combining the two modules, we obtain enhanced semantic segmentation features for segmentation. Extensive experiments show that the enhanced semantic head achieves 40.6% and 42.3% mask AP for cascade predictor HTC and DSC, which surpass about 0.9 and 1.4 percentage points respectively. The enhanced semantic head is universal and effective to improve the performance of different cascade predictors. © 2022 IEEE.

关键词： Object detection

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：