检索结果-内蒙古大学图书馆

International Conference on Transparent Optical Networks

作者： Xinyu Wang Fahan Chen Zengfu Wang Tianjiao Wang Elias Tahchi Bill Moran Moshe Zukerman Department of Electrical Engineering City University of Hong Kong Hong Kong SAR China School of Automation Northwestern Polytechnical University Xi’an China Center for Intelligent Multidimensional Data Analysis Hong Kong SAR China Fugro Germany Marine GmbH Bremen Germany Department of Electrical and Electronic Engineering University of Melbourne Victoria Australia

ISBN: (数字)9798350377323

ISBN: (纸本)9798350377330

Undersea optical fiber cables that span vast distances are integral to the Internet’s infrastructure. Manual path planning of such cables is an arduous task. The Fast Marching Method (FMM), a precise numerical approach capable of solving the Eikonal equation, offers a viable, rigorous, and efficient alternative by optimizing the path between source and destination, taking account of a summary objective function of costs and risk factors. However, its implementation often neglects the crucial curvature constraints arising from the flexural rigidity of cables and maneuvering capabilities of the laying vessels in real-world scenarios. In an attempt to address this issue in real-world cable path planning, our work incorporates these constraints. We propose modifying our previous FMM-based work to generate paths by systematically expanding forbidden regions and replacing sharp angular changes with circular arcs of a predefined radius to ensure compliance with the curvature constraints. By factoring curvature into cable system design, we ensure robust, real-world applicability of cable path design methods. While this modification may result in a departure from the FMM’s optimally calculated path, potentially compromising its cost-effectiveness or risk minimization, the adjusted route adheres to essential curvature constraints and the structural integrity of cables. A more rigorously optimal approach to curvature is possible, but its implementation in our context appears to be difficult and does not appear to yield significant improvements.

关键词： Costs Risk minimization Optical fiber cables Optical fiber networks Path planning Mathematical models Rigidity

来源：评论

学校读者我要写书评

暂无评论

Signature and Log-signature for the Study of Empirical Distributions Generated with GANs

TechRxiv

引用

TechRxiv 2022年

作者： de Curtò, J. de Zarzà, I. Yan, Hong Calafate, Carlos T. Centre for Intelligent Multidimensional Data Analysis HK Science Park Hong Kong Universitat Politècnica de València València Spain The Department of Electrical Engineering City University of Hong Kong Kowloon Hong Kong

In this paper, we bring forward the use of the recently developed Signature Transform as a way to measure the similarity between image distributions and provide detailed acquaintance and extensive evaluations. We are the first to pioneer RMSE and MAE Signature, along with log-signature1 as an alternative to measure GAN convergence, a problem that has been extensively studied. We are also forerunners to introduce analytical measures based on statistics to study the goodness of fit of the GAN sample distribution that are both efficient and effective. Current GAN measures involve lots of computation normally done at the GPU and are very time consuming. In contrast, we diminish the computation time to the order of seconds and computation is done at the CPU achieving the same level of goodness. Lastly, a PCA adaptive t-SNE approach, which is novel in this context, is also proposed for data visualization. © 2022, CC BY.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Learning with Signatures

arXiv

引用

arXiv 2022年

作者： de Curtò Díaz, J. de Zarzà, I. Yan, Hong Calafate, Carlos T. Centre for Intelligent Multidimensional Data Analysis HK Science Park Shatin Hong Kong Department of Electrical Engineering City University of Hong Kong Kowloon Hong Kong Department of Computer Engineering Universitat Politècnica de València València Spain

In this work we investigate the use of the Signature Transform in the context of Learning2. Under this assumption, we advance a supervised framework that potentially provides state-of-the-art classification accuracy with the use of few labels without the need of credit assignment and with minimal or no overfitting. We leverage tools from harmonic analysis by the use of the signature and log-signature, and use as a score function RMSE and MAE Signature and log-signature. We develop a closed-form equation to compute probably good optimal scale factors, as well as the formulation to obtain them by optimization. Techniques of Signal Processing are addressed to further characterize the problem. Classification is performed at the CPU level orders of magnitude faster than other methods. We report results on AFHQ, MNIST and CIFAR10, achieving 100% accuracy on all tasks assuming we can determine at test time which probably good optimal scale factor to use for each category. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Directional And Topological Transformer With Topology Priors For 4D Cellular Image Segmentation

Directional And Topological Transformer With Topology Priors...

引用

IEEE International Conference on Image Processing

作者： Zelin Li Zhaoke Huang Zhen Zhu Sicheng You Zhongying Zhao Hong Yan Centre for Intelligent Multidimensional Data Analysis Hong Kong Science Park Hong Kong SAR Department of Electrical Engineering City University of Hong Kong Hong Kong SAR Department of Biology Hong Kong Baptist University Hong Kong SAR

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

Cellular segmentation is a crucial step in creating cell shape maps and morphological graphs for living embryos from time-lapse 3D fluorescence images (laser confocal). One reliable method for segmenting cell shapes through deep learning networks is to incorporate voxel distance and topology priors to model shapes in topological structures. However, automated and CNN-based segmentation methods often suffer from low signal-to-noise ratios and insufficient training data. Previous works on semantic segmentation have ignored directional distance and topological information. In this paper, we propose a 3D directional and topological transformer named DTTR (Directional distance mapping and Topological learning TRansformer), which uses topology priors to binarization, and demonstrates an effective directional latent space. We use attention calculation on directional distance maps and utilize topological loss and priors, along with an optimized Delaunay-clustering algorithm, to measure voxel predictions in higher dimensional topology space. DTTR outperforms other existing deep learning models and provides a reliable segmented cell instance dataset (22 new living C. elegans embryos) for establishing 4D cellular morphology map.

关键词： Image segmentation Three-dimensional displays Embryo Shape Manuals Fluorescence Transformers

来源：评论

学校读者我要写书评

暂无评论

Domain Generalization with Small data

arXiv

引用

arXiv 2024年

作者： Chen, Kecheng Gal, Elena Yan, Hong Li, Haoliang Department of Electrical Engineering Center for Intelligent Multidimensional Data Analysis City University of Hong Kong Tat Chee Avenue Kowloon Hong Kong Department of Engineering University of Oxford Old Road Campus Research Building Roosevelt Drive OxfordOX3 7DQ United Kingdom

In this work, we propose to tackle the problem of domain generalization in the context of insufficient samples. Instead of extracting latent feature embeddings based on deterministic models, we propose to learn a domain-invariant representation based on the probabilistic framework by mapping each data point into probabilistic embeddings. Specifically, we first extend empirical maximum mean discrepancy (MMD) to a novel probabilistic MMD that can measure the discrepancy between mixture distributions (i.e., source domains) consisting of a series of latent distributions rather than latent points. Moreover, instead of imposing the contrastive semantic alignment (CSA) loss based on pairs of latent points, a novel probabilistic CSA loss encourages positive probabilistic embedding pairs to be closer while pulling other negative ones apart. Benefiting from the learned representation captured by probabilistic models, our proposed method can marriage the measurement on the distribution over distributions (i.e., the global perspective alignment) and the distribution-based contrastive semantic alignment (i.e., the local perspective alignment). Extensive experimental results on three challenging medical datasets show the effectiveness of our proposed method in the context of insufficient data compared with state-of-the-art methods. © 2024, CC BY.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Minimax principle for right eigenvalues of dual quaternion matrices and their generalized inverses

arXiv

引用

arXiv 2022年

作者： Ling, Chen Qi, Liqun Yan, Hong Department of Mathematics Hangzhou Dianzi University Hangzhou310018 China Department of Applied Mathematics The Hong Kong Polytechnic University Hung Hom Kowloon Hong Kong Department of Electrical Engineering Centre for Intelligent Multidimensional Data Analysis City University of Hong Kong Kowloon Hong Kong

Dual quaternions can represent rigid body motion in 3D spaces, and have found wide applications in robotics, 3D motion modelling and control, and computer graphics. In this paper, we introduce three different right linear independency concepts for a set of dual quaternion vectors, and study some related basic properties for dual quaternion vectors and dual quaternion matrices. We present a minimax principle for eigenvalues of dual quaternion Hermitian matrices. Based upon a newly established Cauchy-Schwarz inequality for dual quaternion vectors and singular value decomposition of dual quaternion matrices, we propose an inequality for singular values of dual quaternion matrices. Finally, we introduce the concept of generalized inverses of dual quaternion matrices, and present necessary and sufficient conditions for a dual quaternion matrix to be one of four types of generalized inverses of another dual quaternion matrix. © 2022, CC BY.

关键词： Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

Orthonormal Product Quantization Network for Scalable Face Image Retrieval

arXiv

引用

arXiv 2021年

作者： Zhang, Ming Zhe, Xuefei Yan, Hong Department of Electrical Engineering City University of Hong Kong Hong Kong Centre for Intelligent Multidimensional Data Analysis Limited Hong Kong Hong Kong Applied Science and Technology Research Institute Company Limited Hong Kong Tencent AI Lab Shenzhen China

Existing deep quantization methods provided an efficient solution for large-scale image retrieval. However, the significant intra-class variations, like pose, illumination, and expressions in face images, still pose a challenge. In light of this, face image retrieval requires sufficiently powerful learning metrics, which are absent in current deep quantization works. Moreover, to tackle the growing unseen identities in the query stage, face image retrieval drives more demands regarding model generalization and scalability than general image retrieval tasks. This paper integrates product quantization with orthonormal constraints into an end-to-end deep learning framework to effectively retrieve face images. Specifically, we propose a novel scheme that uses predefined orthonormal vectors as codewords to enhance the quantization informativeness and reduce codewords’ redundancy. A tailored loss function maximizes discriminability among identities in each quantization subspace for both the quantized and original features. An entropy-based regularization term is imposed to reduce the quantization error. Experiments are conducted on four commonly-used face datasets under both seen and unseen identity retrieval settings. Our method outperforms all the compared state-of-the-art under both settings. The proposed orthonormal codewords consistently boost both models’ standard retrieval performance and generalization ability, demonstrating the superiority of our method for scalable face image retrieval. © 2021, CC BY-NC-SA.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A regularization-patching dual quaternion optimization method for solving the hand-eye calibration problem

arXiv

引用

arXiv 2022年

作者： Chen, Zhongming Ling, Chen Qi, Liqun Yan, Hong Department of Mathematics School of Science Hangzhou Dianzi University Hangzhou310018 China Department of Applied Mathematics The Hong Kong Polytechnic University Hung Hom Kowloon Hong Kong Center for Intelligent Multidimensional Data Analysis Science Park Shatin Hong Kong Department of Electrical Engineering City University of Hong Kong Kowloon Hong Kong

The hand-eye calibration problem is an important application problem in robot research. Based on the 2-norm of dual quaternion vectors, we propose a new dual quaternion optimization method for the hand-eye calibration problem. The dual quaternion optimization problem is decomposed to two quaternion optimization subproblems. The first quaternion optimization subproblem governs the rotation of the robot hand. It can be solved efficiently by the eigenvalue decomposition or singular value decomposition. If the optimal value of the first quaternion optimization subproblem is zero, then the system is rotationwise noiseless, i.e., there exists a "perfect" robot hand motion which meets all the testing poses rotationwise exactly. In this case, we apply the regularization technique for solving the second subproblem to minimize the distance of the translation. Otherwise we apply the patching technique to solve the second quaternion optimization subproblem. Then solving the second quaternion optimization subproblem turns out to be solving a quadratically constrained quadratic program. In this way, we give a complete description for the solution set of hand-eye calibration problems. This is new in the hand-eye calibration literature. The numerical results are also presented to show the efficiency of the proposed method. © 2022, CC BY.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Signature and Log-signature for the Study of Empirical Distributions Generated with GANs

arXiv

引用

arXiv 2022年

作者： de Curtò, Joaquim de Zarzà, Irene Yan, Hong Calafate, Carlos T. Centre for Intelligent Multidimensional Data Analysis HK Science Park Hong Kong Universitat Politècnica de València València Spain Universitat Oberta de Catalunya Barcelona Spain The Department of Electrical Engineering City University of Hong Kong Kowloon Hong Kong

In this paper, we bring forward the use of the recently developed Signature Transform as a way to measure the similarity between image distributions and provide detailed acquaintance and extensive evaluations. We are the first to pioneer RMSE and MAE Signature, along with log-signature as an alternative to measure GAN convergence, a problem that has been extensively studied. We are also forerunners to introduce analytical measures based on statistics to study the goodness of fit of the GAN sample distribution that are both efficient and effective. Current GAN measures involve lots of computation normally done at the GPU and are very time consuming. In contrast, we diminish the computation time to the order of seconds and computation is done at the CPU achieving the same level of goodness. Lastly, a PCA adaptive t-SNE approach, which is novel in this context, is also proposed for data visualization. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Efficient algorithms for Tucker decomposition via approximate matrix multiplication

arXiv

引用

arXiv 2023年

作者： Che, Maolin Wei, Yimin Yan, Hong School of Mathematics Southwestern University of Finance and Economics Chengdu611130 China School of Mathematical Sciences Key Laboratory of Mathematics for Nonlinear Sciences Fudan University Shanghai200433 China Department of Electrical Engineering Center for Intelligent Multidimensional Data Analysis City University of Hong Kong 83 Tat Chee Avenue Kowloon Hong Kong

This paper develops fast and efficient algorithms for computing Tucker decomposition with a given multilinear rank. By combining random projection and the power scheme, we propose two efficient randomized versions for the truncated high-order singular value decomposition (T-HOSVD) and the sequentially T-HOSVD (ST-HOSVD), which are two common algorithms for approximating Tucker decomposition. To reduce the complexities of these two algorithms, fast and efficient algorithms are designed by combining two algorithms and approximate matrix multiplication. The theoretical results are also achieved based on the bounds of singular values of standard Gaussian matrices and the theoretical results for approximate matrix multiplication. Finally, the efficiency of these algorithms are illustrated via some test tensors from synthetic and real datasets. Copyright © 2023, The Authors. All rights reserved.

关键词： Tensors

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：