检索结果-内蒙古大学图书馆

2020 International Conference on computer Big Data and Artificial Intelligence, ICCBDAI 2020

作者： Li, Ni Peng, Manman Cao, Buwen Li, Kenli Li, Keqin College of Computer Science and Electric Engineering Hunan University Changsha Hunan410082 China College of Information and Electronic Engineering Yiyang Hunan413000 China Department of Computer Science State University of New York New PaltzNY12561 United States Engineering Research Center of Dong Ting Lake Regional Ecological Environment Intelligent Monitoring Disaster Prevention and Mitigation Hunan Yiyang413000 China Key Laboratory of City Computing and IoT Hunan City UniversityHunan Yiyang413000 China

Spectral clustering is one of the most popular clustering approaches. Despite its good performance and strong theoretical supports, it is limited to high complexity of the graph Laplacian similarity matrix construction and eigen-decomposition problems. Recently, deep learning has been successfully adopted in graph representation. In the paper, we jointly learn the manifold graph construction and non-linear low-dimension mapping of the graph. In addition, we theoretically proved that our model according with spectral clustering theory. Meanwhile, we use the proposed non-linear coders as the building blocks to formulate a deep structure to further refine features of layer wise fashion. Extensive experiments on clustering tasks demonstrate that our method performs well in terms of both clustering accuracy and normalized mutual information( NMI ). © Published under licence by IOP Publishing Ltd.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

3D Face Reconstruction System From A Single Photo Based On Regression Neural Network

引用

IFAC-PapersOnLine 2020年第5期53卷 71-76页

作者： Yatai Ji Keqiang Li Huaiyu Wu Gang Xiong Zhen Shen Xiuqin Shang Bangwen Xi The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China Department of Automation Tsinghua University Beijing 100084 China University of Chinese Academy of Sciences Beijing 100049 China The Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Donggguan 523808 China The Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing 100190 China

3D human face modeling is one of the most popular research directions in the field of computer stereo vision. On the one hand, the complex physiological structure of human face as well as various expressions and attitude changes bring great challenges to three-dimensional modeling, which makes the modeling method of human face have high research value and reference significance. On the other hand, 3D face reconstruction has a broad application prospect, and the application demand attracts more researchers to invest in it. Based on the 3DMM and 3DDFA method, this paper utilizes regression neural network to realize end-to-end face reconstruction. After that, we build a visualization program with the training model to realize face modeling based on a single face image of any pose or expression. It’s a 3D face reconstruction system which has functions such as face alignment, face rotation and so on.

关键词： face reconstruct 3DMM 3DDFA regression network

来源：评论

学校读者我要写书评

暂无评论

RCGA-Net: An Improved Multi-hybrid Attention Mechanism Network in Biomedical Image Segmentation

RCGA-Net: An Improved Multi-hybrid Attention Mechanism Netwo...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Xiao, Feng Shen, Cong Chen, Yu Yang, Tian Chen, Shengyong Liao, Zhijun Tang, Jijun Tianjin University of Technology School of Computer Science and Engineering Tianjin China Engineering Research Center of Learning-Based Intelligent System Ministry of Education Tianjin China School of Basic Medical Sciences Fujian Medical University Fujian Fuzhou China College of Intelligence and Computing Tianjin University Tianjin China Key Laboratory of Systems Bioengineering Ministry of Education Tianjin China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China Department of Computer Science and Engineering University of South Carolina ColumbiaSC United States

ISBN: (纸本)9781665401265

Drawing support from an effective Medical Image Segmentation (MIS) is conducive to a substantial diagnostic basis for the physicians to identify the focus lesion in the patient body and give the subsequent clinical assessment of the patient status. Although various works have tried the challenging quantitative analysis problem, it is still difficult to conduct precise automatic segmentation, especially the soft tissue organs. In this decade, with the increased amount of available datasets, deep learning-based networks have achieved remarkable performance in image processing. Inspired by the state-of-the-art deep learning works, in this paper, we propose an end-to-end multi-layer network named RCGA-Net. It consists of an encoder-decoder backbone that integrates a coordinate attention mechanism based on space and channel and a global context extraction module to highlight more valuable information. To evaluate the performance of RCGA-Net, we apply it to different kinds of clinical and experimental MIS tasks to testify its generalization ability. Extensive experiments represent that our schema has taken the outperform or compatible results among the comparison methods group. Specifically, the numeric result of RCGA-Net on the pulmonary dataset has achieved a 99.12% optimum F1-score. © 2021 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

An efficient post-processing approach for off-line handwritten chinese address recognition

An efficient post-processing approach for off-line handwritt...

引用

International Conference on Signal Processing Proceedings (ICSP)

作者： Chong Long Xiaoyan Zhu Kaizhu Huang Jun Sun Yoshinobu Hotta Satoshi Naoi Department of Computer Science and Technology State Key Laboratory of Intelligent Technology and Systems Tsinghua University Beijing Beijing China Information Technology Laboratory Fujitsu Research and Development Center Company Limited Beijing China Fujitsu Laboratories Limited Kawasaki Japan

Language model is widely used in OCR post-processing. In this paper, based on language model, we propose a two-step method for post-processing of off-line handwritten Chinese address recognition. According to the characteristics of high level and low level addresses, two different strategies are used: for high level addresses, word-based language model is used with weighed matching search algorithm proposed; for low level addresses, ME model is implemented with similar character method. After post-processing, recognition accuracy rises from 41.60% to 78.19%, which means 62.65% errors reduction

关键词： Handwriting recognition Natural languages Optical character recognition software Character recognition Cities and towns Laboratories Postal services Shape computer science intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Incorporating Rotation Invariance with Non-invariant Networks for Point Clouds

Incorporating Rotation Invariance with Non-invariant Network...

引用

International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission (3DIMPVT)

作者： Jiajun Fei Zhidong Deng Department of Computer Science and Technology Tsinghua University State Key Laboratory of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology (BNRist) Institute for Artificial Intelligence at Tsinghua University (THUAI) Beijing China

ISBN: (数字)9798350362459

ISBN: (纸本)9798350362466

Rotation invariance is a fundamental requirement of point cloud processing when input point clouds are not aligned. Many non-invariant networks performing well on aligned point clouds do not perform equivalent to rotated ones. Thus non-invariant and invariant networks are developed separately and only benefit a little from each other, leading to repetitive and wasteful research efforts. In this paper, we aim to bridge this gap and incorporate rotation invariance with non-invariant networks for point clouds. To this end, we propose a novel rotation invariant learning method based on efficient invariant poses (EIPs). EIPs do not rely on novel features or operations. Instead, they only rotate input point clouds into invariant poses and apply non-invariant networks in feature processing. As the name implies, EIPs have negligible complexities (efficient) and solid theoretical foundations (invariant). Experimental results demonstrate that EIPs have competitive performances on several tasks. Without using new features or operations, EIPs yield the best results on ScanObjectNN (PB T50 RS) classification and ShapeNetPart segmentation task. Our code is available at: https://***/JaronTHU/EIP.

关键词： Point cloud compression Bridges Representation learning Three-dimensional displays Codes Solids Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Accommodating Self-attentional Heterophily Topology into High- and Low-pass Graph Convolutional Network for Skeleton-based Action Recognition

Accommodating Self-attentional Heterophily Topology into Hig...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Chao Wei Zhidong Deng Department of Computer Science and Technology Beijing National Research Center for Information Science and Technology (BNRist) State Key Laboratory of Intelligent Technology and Systems Institute for Artificial Intelligence at Tsinghua University (THUAI) Tsinghua University Beijing China

In the scene of human skeleton-based action recognition, graph convolutional network (GCN) is widely applied to model human action dynamics and achieves extraordinary results, where graph topology is in charge of feature extraction and plays a crucial role in learning representation in GCNs. This paper presents a novel high- and low-pass graph convolutional network (HLP-GCN), aiming to effectively aggregate joint features based on learned homophily and heterophily topologies using self-attention modules for skeleton-based action recognition tasks. Specifically, such an HLP-GCN framework first learns homophily and heterophily topologies dynamically so as to capture different correlations between input samples and then combine similar information arising from homophily topologies with dissimilar ones from heterophily topologies to get the final embeddings. Furthermore, a temporal modeling module is added to this HLPGCN framework, and a new pooling strategy called global node (GNode) is cascaded subsequently, in order to have the extraction of more robust spatiotemporal features for skeleton action recognition. Finally, the experimental results demonstrate that our method outperforms previous state-of-the-art methods by 0.2%, 0.4%, and 0.3% on three large-scale action recognition datasets including NTU RGB+D X-Set, NTU RGB+D 120 X-Sub, and NW-UCLA, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fine-Tuning Point Cloud Transformers with Dynamic Aggregation

Fine-Tuning Point Cloud Transformers with Dynamic Aggregatio...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Jiajun Fei Zhidong Deng Department of Computer Science and Technology Institute for Artificial Intelligence Tsinghua University (THUAI) State Key Laboratory of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology (BNRist) Tsinghua University Beijing China

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Point clouds play an important role in 3D analysis, which has broad applications in robotics and autonomous driving. The pre-training fine-tuning paradigm has shown great potential in the point cloud domain. Full fine-tuning is generally effective but leads to a heavy storage and computational burden, which becomes inefficient and unacceptable as the size of pre-trained models scales. Although efficient fine-tuning approaches have significant progress in other domains, they generally perform worse for point clouds. To overcome this dilemma, we revisit the official Point-MAE implementation and find the critical role of aggregation in fine-tuning performances. Inspired by such discoveries, we propose a novel dynamic aggregation (DA) method to replace previous static aggregation like mean or max pooling for pre-trained point cloud Transformers. Besides standard metrics such as accuracy or mIoU, we evaluate the number of tunable parameters and additional FLOPs for a fair comparison of our method to different fine-tuning approaches. We construct several DA variants and validate them through extensive experiments. Experimental results demonstrate that DA has competitive performances against full fine-tuning and other efficient fine-tuning approaches. The code is publicly available at https://***/JaronTHU/DynamicAggregation.

关键词： Point cloud compression Measurement Three-dimensional displays Codes Computational modeling Aggregates Transformers

来源：评论

学校读者我要写书评

暂无评论

Learnable Flow Model Conditioned on Graph Representation Memory for Anomaly Detection

Learnable Flow Model Conditioned on Graph Representation Mem...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Ziyu Zhu Wenlei Liu Zhidong Deng Department of Computer Science and Technology Tsinghua University Beijing China State Key Laboratory of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology (BNRist) Institute for Artificial Intelligence at Tsinghua University (THUAI)

Anomaly detection could be applied in a wide range of fields from industrial scene to medical imaging analysis. Although invertible flow models are developed to accomplish unsupervised anomaly detection, they are usually hard to train and have limited capabilities of accurately modeling the distribution of normal samples. To address this problem, we propose a novel enhanced flow model conditioned on graph representation memory (FlowGRM) for visual surface defect detection. In our FlowGRM, a graph neural network is trained to query graph embedding features from memory bank and incorporate them into a learnable flow model as conditional information. Such memorized conditional information, together with the invertible flow model, is jointly optimized to give rise to a probability density score. Experimental results obtained on the industrial visual anomaly detection datasets including MVTec and MTD show that the proposed model has state-of-the-art performance, which could even reach up to 99.6% and 99.2% AUROC scores on the above two bench-marks, respectively. Meanwhile, it requires fewer parameters and saves over 80% training time compared to existing flow models.

关键词： Training Visualization Time series analysis Signal processing Graph neural networks Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

An empirical analysis of social interaction on tobacco-oriented social networks

An empirical analysis of social interaction on tobacco-orien...

引用

2013 International Conference for Smart Health, ICSH 2013

作者： Liang, Yunji Zheng, Xiaolong Zeng, Daniel Dajun Zhou, Xingshe Leischow, Scott School of Computer Science Northwestern Polytechnical University Xi'an China Department of Management Information System University of Arizona Tucson AZ United States State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Dongguan Research Institute of CASIA Cloud Computing Center Chinese Academy of Sciences Songshan Lake Dongguan China Mayo Clinic in Arizona Phoenix AZ United States

ISBN: (纸本)9783642398438

Social media is widely utilized in the tobacco control campaigns. It is a great challenge to evaluate the efficiency of tobacco control policies on social network sites and find gaps among tobacco-oriented social networks. In this paper, we construct three tobacco-oriented social networks according to user interaction on Facebook tobacco-related fan pages. We further investigate the interaction patterns including temporal distribution and interaction patterns to reveal the differences of tobacco-oriented social networks. Our empirical analysis demonstrates that: 1) the user interaction on the pro-tobacco fan pages is more active. Fan pages for tobacco promotion are more successful in obtaining more user attention. 2) The gap between tobacco promotion and tobacco control is widening. These empirical results can provide us significant insights into understanding the evolutionary patterns of social interaction in tobacco-oriented social networks and further help the government departments of tobacco control to make reasonable decisions. © 2013 Springer-Verlag.

关键词： Tobacco

来源：评论

学校读者我要写书评

暂无评论

Quantum state and process tomography via adaptive measurements

引用

Science China(Physics,Mechanics & Astronomy) 2016年第10期59卷 25-32页

作者： HengYan Wang WenQiang Zheng NengKun Yu KeRen Li DaWei Lu Tao Xin Carson Li ZhengFeng Ji David Kribs Bei Zeng XinHua Peng JiangFeng Du Hefei National Laboratory for Physical Sciences at Microscale and Department of Modern Physics University of Science and Technology of ChinaHefei 230026China Department of Applied Physics Zhejiang University of TechnologyHangzhou 310023China Institute for Quantum Computing University of WaterlooWaterloo N2L 3G1Canada 4Department of Mathematics&Statistics University of GuelphGuelph N1G 2W1Canada Centre for Quantum Computation&Intelligent Systems Faculty of Engineering and Information TechnologyUniversity of Technology SydneySydney NSW 2007Australia State Key Laboratory of Low-Dimensional Quantum Physics and Department of Physics Tsinghua UniversityBeijing 100084China Department of Physics University of GuelphGuelph N1G 2W1Canada State Key Laboratory of Computer Science Institute of SoftwareChinese Academy of SciencesBeijing 100190China Canadian Institute for Advanced Research Toronto M5G 1Z8Canada

We investigate quantum state tomography(QST) for pure states and quantum process tomography(QPT) for unitary channels via adaptive measurements. For a quantum system with a d-dimensional Hilbert space, we first propose an adaptive protocol where only 2d. 1 measurement outcomes are used to accomplish the QST for all pure states. This idea is then extended to study QPT for unitary channels, where an adaptive unitary process tomography(AUPT) protocol of d2+d.1measurement outcomes is constructed for any unitary channel. We experimentally implement the AUPT protocol in a 2-qubit nuclear magnetic resonance system. We examine the performance of the AUPT protocol when applied to Hadamard gate, T gate(/8 phase gate), and controlled-NOT gate,respectively, as these gates form the universal gate set for quantum information processing purpose. As a comparison, standard QPT is also implemented for each gate. Our experimental results show that the AUPT protocol that reconstructing unitary channels via adaptive measurements significantly reduce the number of experiments required by standard QPT without considerable loss of fidelity.

关键词： quantum tomography state reconstruction nuclear magnetic resonance

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：