检索结果-内蒙古大学图书馆

computing Conference, 2019

作者： Liu, Pengyu Niu, Yuzhen Chen, Junhao Shi, Yiqing College of Mathematics and Computer Science Fuzhou University Fuzhou China Fujian Provincial Key Lab of the Network Computing and Intelligent Information Processing Fujian China

ISBN: (纸本)9783030228705

Color correction can eliminate the color difference between similar images in image stitching and 3D video reconstruction. The result images generated by the local color correction algorithms usually show structure inconsistency problem with the input images. In order to solve this problem, we propose a structure consistent color correction algorithm for stereoscopic images based on gradient preservation. This method can not only eliminate color difference between reference and target images, but also optimize structure between the input target image and the result image. Firstly, the algorithm extracts the structure information of the target image and style information of the reference image using the SIFT algorithm and generates the structure image and the pixel matching image. Then an initial result image is generated by local pixel mapping. Finally the initial result image is iteratively optimized by the gradient preserving algorithm. The experimental results show that our algorithm can not only optimize the structure inconsistency, but also effectively process image pairs with large color difference. © 2019, Springer Nature Switzerland AG.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

REVISITING GRAPH ADVERSARIAL ATTACK AND DEFENSE FROM A DATA DISTRIBUTION PERSPECTIVE 11

REVISITING GRAPH ADVERSARIAL ATTACK AND DEFENSE FROM A DATA ...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Li, Kuan Liu, Yang Ao, Xiang He, Qing Key Lab of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences China

Recent studies have shown that structural perturbations are significantly effective in degrading the accuracy of Graph Neural Networks (GNNs) in the semi-supervised node classification (SSNC) task. However, the reasons for the destructive nature of gradient-based methods have not been explored in-depth. In this work, we discover an interesting phenomenon: the adversarial edges are not uniformly distributed on the graph, and a majority of perturbations are generated around the training nodes in poisoning attacks. Combined with this phenomenon, we provide an explanation for the effectiveness of the gradient-based attack method from a data distribution perspective and revisit both poisoning attack and evasion attack in SSNC. From this new perspective, we empirically and theoretically discuss some other attack tendencies. Based on the analysis, we provide nine practical tips on both attack and defense and meanwhile leverage them to improve existing attack and defense methods. Moreover, we design a fast attack method and a self-training defense method, which outperform the state-of-the-art methods and can effectively scale to large graphs like ogbn-arxiv. We validate our claims through extensive experiments on four benchmark datasets. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Bayesian localization microscopy based on intensity distribution of fluorophores

引用

Protein & Cell 2015年第3期6卷 211-220页

作者： Fan Xu Mingshu Zhang Zhiyong Liu Pingyong Xu Fa Zhang Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China University of Chinese Academy of Sciences Beijing 100049 China Laboratory of Non Coding RNA Institute of Biophysics Chinese Academy of Sciences Beijing 100101 China

Super-resolution microscopy techniques have overcome the limit of optical diffraction. Recently, the Bayesian analysis of Bleaching and Blinking data （3B） method has emerged as an important tool to obtain super-resolution fluorescence images. 3B uses the change in information caused by adding or removing fiuorophores in the cell to fit the date. When adding a new fluorophore, 3B selects a random initial position, optimizes this position and then determines its reliability. However, the fluorophores are not evenly distributed in the entire image region, and the fluorescence intensilty at a given position positively correlates with the probability of observing a fluorophore at this position. In this paper, we present a Bayesian analysis of Bleaching and Blinking microscopy method based on fluorescence intensity distribution （FID3B）. We utilize the intensity distribution to select more reliable positions as the initial positions of fluorophores. This approach can improve the reconstruction results and significantly reduce the computational time. We validate the perfor. mance of our method using both simulated date and experimental date from cellular structures. The results confirm the effectiveness of our method.

关键词： super-resolution fluorescence image 3B,intensity distribution

来源：评论

学校读者我要写书评

暂无评论

Adaptive tag selection for image annotation 15

Adaptive tag selection for image annotation

引用

15th Pacific-Rim Conference on Multimedia, PCM 2014

作者： He, Xixi Li, Xirong Yang, Gang Xu, Jieping Jin, Qin Key Lab of DEKE Renmin University of China 100872 China Multimedia Computing Lab Renmin University of China 100872 China Shanghai Key Laboratory of Intelligent Information Processing 200443 China

ISBN: (纸本)9783319131672

Not all tags are relevant to an image, and the number of relevant tags is image-dependent. Although many methods have been proposed for image auto-annotation, the question of how to determine the number of tags to be selected per image remains open. The main challenge is that for a large tag vocabulary, there is often a lack of ground truth data for acquiring optimal cutoff thresholds per tag. In contrast to previous works that pre-specify the number of tags to be selected, we propose in this paper adaptive tag selection. The key insight is to divide the vocabulary into two disjoint subsets, namely a seen set consisting of tags having ground truth available for optimizing their thresholds and a novel set consisting of tags without any ground truth. Such a division allows us to estimate how many tags shall be selected from the novel set according to the tags that have been selected from the seen set. The effectiveness of the proposed method is justified by our participation in the ImageCLEF 2014 image annotation task. On a set of 2,065 test images with ground truth available for 207 tags, the benchmark evaluation shows that compared to the popular top-k strategy which obtains an F-score of 0.122, adaptive tag selection achieves a higher Fscore of 0.223. Moreover, by treating the underlying image annotation system as a black box, the new method can be used as an easy plug-in to boost the performance of existing systems. © Springer International Publishing Switzerland 2014.

关键词： Image annotation

来源：评论

学校读者我要写书评

暂无评论

ETS: An Error Tolerable System for Coreference Resolution 15

ETS: An Error Tolerable System for Coreference Resolution

引用

15th Conference on Computational Natural Language Learning, CoNLL 2011

作者： Xiong, Hao Song, Linfeng Meng, Fandong Liu, Yang Liu, Qun Lü, Yajuan Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences P.O. Box 2704 Beijing100190 China

ISBN: (纸本)9781937284084

This paper presents our error tolerable system for coreference resolution in CoNLL-2011(Pradhan et al., 2011) shared task (closed track). Different from most previous reported work, we detect mention candidates based on packed forest instead of single parse tree, and we use beam search algorithm based on the Bell Tree to create entities. Experimental results show that our methods achieve promising results on the development set. © 2011 Association for Computational Linguistics

关键词： Forestry

来源：评论

学校读者我要写书评

暂无评论

Automatic recognition of noisy Code-39 barcode

Automatic recognition of noisy Code-39 barcode

引用

16th International Conference on Artificial Reality and Telexistence - Workshops, ICAT 2006

作者： Fang, Xianyong Wu, Fuli Luo, Bin Zhao, Haifeng Wang, Peng Key Lab. of Intelligent Computing and Signal Processing Ministry of Education Anhui University College of Information Engineering Zhejiang University of Technology Electronics Ltd.

ISBN: (纸本)076952754X

Barcode has been widely applied in the modern world. This paper presents a fast and robust recognition method of noisy Code 39 barcode. The proposed method can be divided into two steps: search and decoding. In the first step, all asterisks in the image are found with evenly defined scan lines and then those with the same directions are matched together to get a valid barcode region. In the second step, a local denoise method is first applied to eliminate noise in the barcode region and then a middle band filter is used to decode the barcode. Our method is simple in comparison with former methods and experimental results show that it is efficient for fast barcode recognition on noisy images. © 2006 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Memory bandwidth optimization of SpMV on GPGPUs

引用

Frontiers of Computer Science 2015年第3期9卷 431-441页

作者： Chenggang Clarence YAN Hui YU Weizhi XU Yingping ZHANG Bochuan CHEN Zhu TIAN Yuxuan WANG Jian YIN Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China Institute of Microelectronics Tsinghua University Beijing 100084 China Automation Department Tsinghua University Beijing 100084 China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China State Grid Information & Communication Company of Hunan EPC Changsha 410007 China Department of Computer Shandong University Weihai 250101 China

It is an important task to improve performance for sparse matrix vector multiplication （SpMV）, and it is a difficult task because of its irregular memory access. Gen- eral purpose GPU （GPGPU） provides high computing abil- ity and substantial bandwidth that cannot be fully exploited by SpMV due to its irregularity. In this paper, we propose two novel methods to optimize the memory bandwidth for SpMV on GPGPU. First, a new storage format is proposed to exploit memory bandwidth of GPU architecture more effi- ciently. The new storage format can ensure that there are as many non-zeros as possible in the format which is suitable to exploit the memory bandwidth of the GPU. Second, we pro- pose a cache blocking method to improve the performance of SpMV on GPU architecture. The sparse matrix is partitioned into sub-blocks that are stored in CSR format. With the block- ing method, the corresponding part of vector x can be reused in the GPU cache, so the time to access the global memory for vector x is reduced heavily. Experiments are carried out on three GPU platforms, GeForce 9800 GX2, GeForce GTX 480, and Tesla K40. Experimental results show that both new methods can efficiently improve the utilization of GPU mem- ory bandwidth and the performance of the GPU.

关键词： GPGPU performance tuning SpMV cacheblocking memory bandwidth

来源：评论

学校读者我要写书评

暂无评论

Distinguishing patients with gastritis and cholecystitis from the healthy by analyzing wrist radial arterial doppler blood flow signals

Distinguishing patients with gastritis and cholecystitis fro...

引用

International Conference on Pattern Recognition

作者： Jiang, Xiaorui Zhang, Dongyu Wang, Kuanquan Zuo, Wangmeng Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China Department of Computer Science and Technology Harbin Institute of Technology

ISBN: (纸本)9780769541099

This paper tries to fill the gap between Traditional Chinese Pulse Diagnosis (TCPD) and Doppler diagnosis by applying digital signal analysis and pattern classification techniques to wrist radial arterial Doppler blood flow signals. Doppler blood flows signals (DBFS) of patients with cholecystitis, gastritis and healthy people are classified by L2-soft margin SVM and 5 linear classifiers using the proposed feature - piecewise axially integrated bispectra (PAIB). A 5-fold cross validation is used for performance evaluation. The classification accuracies between either two groups of subjects are greater than 93%. Gastritis can be recognized with higher accuracy than cholecystitis. Cholecystitis can be recognized with higher accuracy on left hand data than right. The findings in this paper partly conform to the theory of TCPD. Though the sample size is relatively small, we could still argue that the methods proposed here are effective and could serve as an assistive tool for TCPD. © 2010 IEEE.

关键词： Blood

来源：评论

学校读者我要写书评

暂无评论

ICT: System description for CoNLL-2012

ICT: System description for CoNLL-2012

引用

2012 Joint Conference on Empirical Methods in Natural Language processing and Computational Natural Language Learning, EMNLP-CoNLL 2012 - Shared Task: Modeling Multilingual Unrestricted Coreference in OntoNotes

作者： Xiong, Hao Liu, Qun Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences P.O. Box 2704 Beijing100190 China

ISBN: (纸本)9781937284459

In this paper, we present our system description for the CoNLL-2012 coreference resolution task on English, Chinese and Arabic. We investigate a projection-based model in which we first translate Chinese and Arabic into English, run a publicly available coreference system, and then use a new projection algorithm to map the coreferring entities back from English into mention candidates detected in the Chinese and Arabic source. We compare to a baseline that just runs the English coreference system on the supplied parses for Chinese and Arabic. Because our method does not beat the baseline system on the development set, we submit outputs generated by the baseline system as our final submission. © 2012 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Conditional random fields for machine translation system combination

Conditional random fields for machine translation system com...

引用

International Conference on Asian Language processing

作者： Xia, Tian Zhe, Shandian Liu, Qun Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences P.O. Box 2704 Beijing 100190 China

ISBN: (纸本)9780769542881

Minimum Error Rate Training (MERT) as an effective parameters learning algorithm is widely applied in machine translation and system combination area. However, there exists an ambiguity problem in respect to the training goal and it is hard for MERT to tackle, that is different parameters may lead to the same minimum error rate in training but greatly different performances in testing. We propose a novel training objective as the unique goal for training towards, namely partial references, and by use of conditional random fields (CRF) to cast the decoding procedure in system combination as a sequence labeling problem. Experiments on Chinese-English translation test sets show that our approach significantly outperforms the MERT-based baselines with less training time. © 2010 IEEE.

关键词： Errors

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：