检索结果-内蒙古大学图书馆

Congress on image and Signal Processing, CISP

作者： Jiao Wu Fang Liu Licheng Jiao Key Laboratory of Intelligent Perception Image Understanding of Ministry of Education of China Xian China College of Sciences China Jiliang University Hangzhou China School of Computer Science and Technology Xidian University Xian China

ISBN: (纸本)9781467309653

The prior information of image plays an important role in compressive sensing (CS) reconstruction. The edge is one of the important information which exists in the image to be recovered. In this work, the edge of images is used as a prior information and extracted from CS measurements in the wavelet-based CS inversion. An edge-based matching pursuit algorithm is developed by merging edge information to guide the pursuit process. Edge information well defines the locations of the significant coefficients to be recovered, thus it contributes so much to the reconstruction quality. Experiment results demonstrate that the proposed algorithm returns superior reconstruction performance for the images with obvious edges and high sparsity compared with other CS algorithms.

关键词： image edge detection image reconstruction Matching pursuit algorithms Data mining Compressed sensing Wavelet transforms Computed tomography

来源：评论

学校读者我要写书评

暂无评论

Sequential 3D Human Pose and Shape Estimation From Point Clouds

Sequential 3D Human Pose and Shape Estimation From Point Clo...

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： Kangkan Wang Jin Xie Guofeng Zhang Lei Liu Jian Yang Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology China State Key Laboratory of CAD&CG Zhejiang University China ZJU-SenseTime Joint Lab of 3D Vision

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

This work addresses the problem of 3D human pose and shape estimation from a sequence of point clouds. Existing sequential 3D human shape estimation methods mainly focus on the template model fitting from a sequence of depth images or the parametric model regression from a sequence of RGB images. In this paper, we propose a novel sequential 3D human pose and shape estimation framework from a sequence of point clouds. Specifically, the proposed framework can regress 3D coordinates of mesh vertices at different resolutions from the latent features of point clouds. Based on the estimated 3D coordinates and features at the low resolution, we develop a spatial-temporal mesh attention convolution (MAC) to predict the 3D coordinates of mesh vertices at the high resolution. By assigning specific attentional weights to different neighboring points in the spatial and temporal domains, our spatial-temporal MAC can capture structured spatial and temporal features of point clouds. We further generalize our framework to the real data of human bodies with a weakly supervised fine-tuning method. The experimental results on SURREAL, Human3.6M, DFAUST and the real detailed data demonstrate that the proposed approach can accurately recover the 3D body model sequence from a sequence of point clouds.

关键词： Three-dimensional displays Solid modeling Shape Biological system modeling Estimation Spatial resolution Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Aligning Multiple Knowledge Graphs in a Single Pass

arXiv

引用

arXiv 2024年

作者： Yang, Yaming Wang, Zhe Guan, Ziyu Zhao, Wei Lu, Weigang Huang, Xinyan Cui, Jiangtao He, Xiaofei State Key Laboratory of Integrated Services Networks School of Computer Science and Technology Xidian University Xi’an China Key Laboratory of Intelligent Perception and Image UnDerstanding The Ministry of Education The School of Artificial Intelligence Xidian University Xi’an China State Key Laboratory of CAD&CG Zhejiang University Hangzhou China

Entity alignment (EA) is to identify equivalent entities across different knowledge graphs (KGs), which can help fuse these KGs into a more comprehensive one. Previous EA methods mainly focus on aligning a pair of KGs, and to the best of our knowledge, no existing EA method considers aligning multiple (more than two) KGs. To fill this research gap, in this work, we study a novel problem of aligning multiple KGs and propose an effective framework named MultiEA to solve the problem. First, we embed the entities of all the candidate KGs into a common feature space by a shared KG encoder. Then, we explore three alignment strategies to minimize the distances among pre-aligned entities. In particular, we propose an innovative inference enhancement technique to improve the alignment performance by incorporating high-order similarities. Finally, to verify the effectiveness of MultiEA, we construct two new real-world benchmark datasets and conduct extensive experiments on them. The results show that our MultiEA can effectively and efficiently align multiple KGs in a single pass. We release the source codes of MultiEA at: https://***/kepsail/MultiEA. Copyright © 2024, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Maximizing Mutual Information Across Feature and Topology Views for Learning Graph Representations

arXiv

引用

arXiv 2021年

作者： Fan, Xiaolong Gong, Maoguo Wu, Yue Li, Hao The School of Electronic Engineering Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education Xidian University Shaanxi Province Xi’an China The School of Computer Science and Technology Xidian University Shaanxi Province Xi’an China

Recently, maximizing mutual information has emerged as a powerful method for unsupervised graph representation learning. The existing methods are typically effective to capture graph information from the topology view but consistently ignore the feature view. To circumvent this issue, we propose a novel approach by exploiting mutual information maximization across feature and topology views. Specifically, we first utilize a multi-view representation learning module to better capture both local and global information content across feature and topology views on graphs. To model the information shared by the feature and topology spaces, we then develop a common representation learning module via using mutual information maximization and reconstruction loss minimization. Here, minimizing reconstruction loss forces the model to learn the shared information of feature and topology spaces. To explicitly encourage diversity between graph representations from the same view, we also introduce a disagreement regularization to enlarge the distance between representations from the same view. Experiments on synthetic and real-world datasets demonstrate the effectiveness of integrating feature and topology views. In particular, compared with the previous supervised methods, our proposed method can achieve comparable or even better performance under the unsupervised representation and linear evaluation protocol. Copyright © 2021, The Authors. 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

LiDAR-SGMOS: Semantics-Guided Moving Object Segmentation with 3D LiDAR

LiDAR-SGMOS: Semantics-Guided Moving Object Segmentation wit...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Shuo Gu Suling Yao Jian Yang Chengzhong Xu Hui Kong PCA Laboratory Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Laboratory of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China State Key Laboratory of Internet of Things for Smart City (SKL-IOTSC) University of Macau Macau China

Most of the existing moving object segmentation (MOS) methods regard MOS as an independent task, in this paper, we associate the MOS task with semantic segmentation, and propose a semantics-guided network for moving object segmentation (LiDAR-SGMOS). We first transform the range image and semantic features of the past scan into the range view of current scan based on the relative pose between scans. The residual image is obtained by calculating the normalized absolute difference between the current and transformed range images. Then, we apply a Meta-Kernel based cross scan fusion (CSF) module to adaptively fuse the range images and semantic features of current scan, the residual image and transformed features. Finally, the fused features with rich motion and semantic information are processed to obtain reliable MOS results. We also introduce a residual image augmentation method to further improve the MOS performance. Our method outperforms most LiDAR-MOS methods with only two sequential LiDAR scans as inputs on the SemanticKITTI MOS dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Live demonstration: Spatial-temporal color video reproduction from noisy CFA sequence track: Digital signal processing

Live demonstration: Spatial-temporal color video reproductio...

引用

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： Lei Zhang Weisheng Dong Chiu-Wai Hui Xiaolin Wu Guangming Shi Department of computing Hong Kong Polytechnic University Hong Kong China Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education Xidian University Xi'an China Department of Electrical and Computer Engineering McMaster University Canada

This demonstration shows a spatial-temporal denoising and demosaicking scheme for noisy CFA videos. This scheme can significantly reduce the noise-caused color artifacts and effectively preserve the image edge structures. The experimental results showed that this scheme achieves promising color video reproduction in terms of both PSNR and visual perception.

关键词： Color Colored noise Digital signal processing Noise reduction PSNR Principal component analysis Digital cameras image processing Laboratories computer science education

来源：评论

学校读者我要写书评

暂无评论

Polarimetric SAR image Classification Based on Deep Learning and Hierarchical Semantic Model

引用

Zidonghua Xuebao/Acta Automatica Sinica 2017年第2期43卷 215-226页

作者： Shi, Jun-Fei Liu, Fang Lin, Yao-Hai Liu, Lu College of Computer Science and Technology Xidian University Xi'an710071 China School of Computer Science and Technology Xi'an University of Technology Xi'an710048 China Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China Xidian University Xi'an710071 China School of Computer Science and Technology Fujian Agriculture and Forest University Fuzhou350002 China

Stacked auto-encoder model can effectively represent the complex terrain structures, such as the urban and the forest, by automatically learning high-level features. However, it has difficulty in preserving details and edges. In order to overcome this shortcoming, a new unsupervised polarimetric synthetic aperture radar (PolSAR) classification method is proposed by combining the deep learning and the polarimetric hierarchical semantic model (PHSM). According to the PHSM, a PolSAR image is partitioned into aggregated, homogeneous and structural regions. For aggregated regions, a stacked auto-encoder model is applied to learn high-level features, and further the sparse representation and classification is constructed by learning a dictionary with high-level features. For homogeneous regions, hierarchical segmentation and classification is applied. In addition, edges are located and line objects are preserved for structural regions. Experimental results demonstrate that the proposed method can obtain good performance in both region homogeneity and edge preservation. Copyright © 2017 Acta Automatica Sinica. All rights reserved.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

Multi-task learning for object keypoints detection and classification

引用

Pattern Recognition Letters 2020年 130卷 182-188页

作者： Jie Xu Lin Zhao Shanshan Zhang Chen Gong Jian Yang PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education and Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing 210094 China State Key Laboratory of Integrated Services Networks Xidian Univeristy Xi’an 710071 China

Object keypoints detection and classification are both central research topics in computer vision . Due to their wide range potential applications in the real world, substantial efforts have been taken to advance their performance. However, these two related tasks are mainly treated separately in previous works. We argue that keypoints detection and classification can be complementary tasks and beneficial to each other. Knowing the category of a object is able to reduce the searching space of keypoints detection models and facilitate more precise localization . On the other hand, having the knowledge of object keypoints can make classification models pay more attention on areas that are more associated with the object, which will inevitably promote classification accuracy . Embracing this observation, we propose to model keypoints detection and classification in a multi-task learning framework. Specifically, a multi-task deep network is designed and trained to conduct both tasks, where we devise the model structure delicately to carry out sufficient training of both tasks. Extensive experiments are set up on the AIFASHION DATASET and Human3.6M DATASET to validate our proposal, we show that our algorithm outperforms separate models trained individually on each task.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimization of Ultrasonic Imaging Using Persistence and Filter Technology

Optimization of Ultrasonic Imaging Using Persistence and Fil...

引用

2013 2nd International Conference on Materials Science and Technology(ICMST 2013)

作者： Dequan Guo Hongyu Yang Congyao Zhang Dong C.Liu Key Laboratory of Fundamental Synthetic Vision Graphics and Image Science for National Defense Sichuan University Department of Machinery Engineering Neijiang Vocational and Technical College College of Computer Science Sichuan University

B-mode ultrasonic images are often pervaded by the electronics noise and speckle artifact, which may make the interpretation of medical images difficult. In this paper, a legible method for ultrasonic image is constructed and it can be effective to suppress the noise and improve the images quality. Dynamic persistence technology based on temporal multi-frames is utilized to smooth the electronics noise and even lower speckle artifact. To reduce computing complexity, a sum table method and conjugate direction search approaches are applied to speed up estimation of motion vector. The guided image filter strategy is used to enhance the contrast and detail resolution for the processed image by persistence. Experimental results show that the proposed method is effective to smooth noise and enhance contrast of ultrasound image in vivo.

关键词： noise contrast sum table conjugate direction search guided image filter

来源：评论

学校读者我要写书评

暂无评论

Graph Convolutional Neural Network with Inter-layer Cascade Based on Attention Mechanism

Graph Convolutional Neural Network with Inter-layer Cascade ...

引用

IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS)

作者： Lu Wei Yiting Liu Kaiyuan Feng Jianzhao Li Kai Sheng Yue Wu Key Laboratory of Big Data and Intelligent Vision School of Computer Science and Technology Xidian University Xi’an China Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Electronic Engineering Xidian University Xi’an China Academy of Advanced Interdisciplinary Research Xidian University Xi’an China Dongfeng USharing Technology Co. Ltd. Dongfeng Motor Corporation Wuhan China

ISBN: (纸本)9781665441506

In recent years, graph data in the non-Euclidean space has been widely used, and the methods and techniques for learning graph data in many deep learning fields have been continuously developed, such as the Graph neural network (GNN). The structural characteristics of graph data, the aggregation mode and representation mode of node information, and the node neighbor information are the core issues of GNN. However, most of the existing graph convolutional neural networks have an excessive smoothing problem, which limits the learning ability of the model. Aiming at the over-smoothing problem of the current algorithm, this paper enhances the learning of graph data by improving the expression ability of local information and global features. This paper constructs a cascade structure between graph convolutional layers. This kind of network structure realizes the dense connection of convolutional layers, makes the local feature information is effectively used, and further enhances the graph representation ability. Introduce self-attention and TopK into the Readout module, selectively aggregate and express feature information, and use graph-level information more efficiently. Graph classification is a downstream task to verify the performance of the proposed model. Experimental results prove that this densely structured graph convolutional network can effectively aggregate local node information and global graph-level information.

关键词： Training Deep learning Smoothing methods Aggregates Conferences Graph neural networks Data models

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：