检索结果-内蒙古大学图书馆

IEEE Visual Communications and Image Processing (VCIP)

作者： Junteng Zhang Tong Chen Hao Zhu Dong Wang Dandan Ding Zhan Ma Nanjing University Nanjing China Interdisciplinary Research Center for Future Intelligent Chips (Chip-X) Nanjing University Suzhou China OPPO Inc. Nanjing China Hangzhou Normal University Hangzhou China

ISBN: (数字)9798331529543

ISBN: (纸本)9798331529550

As a promising technique for 3D representation, 3D Gaussian Splatting (3DGS) offers fast rendering speed and high fidelity while generating large data volumes. This challenges storage and transmission, so an efficient compression solution is required. Existing implicit methods require pre-scene optimization (online), leading to a long optimization time. By contrast, this paper regards the 3DGS as a point cloud and pre-trains a generalizable (offline) neural coder for compression. After obtaining the 3DGS representation, we focus on the data compression process, which is friendly to applications already equipped with a PCC codec. The neural coder employed is extended from a typical AIbased point cloud compression method, which uses a multiscale and multistage framework to exploit spatial correlations across scales and stages for conditional coding. Experimental results show that our method significantly outperforms existing 3DGS representations without compromising fidelity, achieving more than 39× and 6.8× compression ratio compared to the original 3DGS and SOTA Scaffold-GS, respectively. More importantly, our approach does not require additional time to optimize the compression model.

关键词： Point cloud compression Image coding Three-dimensional displays Correlation Codecs Visual communication Rendering (computer graphics) optimization

来源：评论

学校读者我要写书评

暂无评论

7th Russian Supercomputing Days conference, RuSCDays 2021

7th Russian Supercomputing Days Conference, RuSCDays 2021

引用

7th Russian Supercomputing Days conference, RuSCDays 2021

ISBN: (纸本)9783030928636

The proceedings contain 40 papers. The special focus in this conference is on Russian Supercomputing Day. The topics include: Implementation of Elliptic Solvers Within ParCS Parallel Framework;JAD-Based SpMV Kernels Using Multiple-Precision Libraries for GPUs;Modeling the Process of Mixing Water in the Estuarine Area in the Presence of a Density Gradient of the Aquatic Environment Using Hybrid MPI/OpenMP Technology;multicomp: Software Package for multiscale Simulations;parallel Algorithm for Calculating the Radius of Stability in Multicriteria optimization Conditions for Catalytic Reforming of Gasoline;parallel Global Search Algorithm for optimization of the Kinetic Parameters of Chemical Reactions;parameters optimization of Linear and Nonlinear Solvers in GeRa Code;quantum-Chemical Calculations of the Structure and Thermochemical Properties of 3,6-bis(2,2,2-trinitroethylnitramino)-1,2,4,5-tetrazine;Solution of Large-Scale Black Oil Recovery Problem in Parallel Using INMOST Platform;Application of Docking and Quantum Chemistry to the Search for Inhibitors of SARS-CoV-2 Main Protease;Supercomputer Simulation of Turbulent Flow Around Isolated UAV Rotor and Associated Acoustic Fields;using 16-th Order Multioperators-Based Scheme for Supercomputer Simulation of the Initial Stage of Laminar-Turbulent Transitions;wave Spectrum of Flowing Drops;advanced Genetic Algorithm in the Problem of Linear Solver Parameters optimization;Analysis of Software Package Usage Based on methods for Identifying Similar HPC applications;Comparative Efficiency Analysis of MPI Blocking and Non-blocking Communications with Coarray Fortran;Investigating Performance of the XAMG Library for Solving Linear Systems with Multiple Right-Hand Sides;"Mini-Benchmarking" Approach to Optimize Evolutionary methods of Neural Architecture Search;on the Prospects of Quantum Computing in Models of Social Behavior;Qualitative and Quantitative Study of Modern GPU Synchronization Approaches;calculation of Integral

关键词：

来源：评论

学校读者我要写书评

暂无评论

DATA-DRIVEN DESIGN VIA SCALABLE GAUSSIAN PROCESSES FOR MULTI-RESPONSE BIG DATA WITH QUALITATIVE FACTORS 47

DATA-DRIVEN DESIGN VIA SCALABLE GAUSSIAN PROCESSES FOR MULTI...

引用

ASME International Design Engineering Technical conferences / 41st Annual Computers and Information in Engineering conference (IDETC-CIE) / 47th Design Automation conference (DAC)

作者： Wang, Liwei Yerramilli, Suraj Iyer, Akshay Apley, Daniel Zhu, Ping Chen, Wei Shanghai Jiao Tong Univ Sch Mech Engn Shanghai Key Lab Digital Mfg Thin Walled Struct State Key Lab Mech Syst & Vibrat Shanghai Peoples R China Northwestern Univ Dept Mech Engn Evanston IL 60208 USA Northwestern Univ Dept Ind Engn & Management Sci Evanston IL 60208 USA

ISBN: (纸本)9780791885383

Scientific and engineering problems often require an inexpensive surrogate model to aid understanding and the search for promising designs. While Gaussian processes (GP) stand out as easy-to-use and interpretable learners in surrogate modeling, they have difficulties in accommodating big datasets, qualitative inputs, and multi-type responses obtained from different simulators, which has become a common challenge for a growing number of data-driven design applications. In this paper, we propose a GP model that utilizes latent variables and functions obtained through variational inference to address the aforementioned challenges simultaneously. The method is built upon the latent variable Gaussian process (LVGP) model where qualitative factors are mapped into a continuous latent space to enable GP modeling of mixed-variable datasets. By extending variational inference to LVGP models, the large training dataset is replaced by a small set of inducing points to address the scalability issue. Output response vectors are represented by a linear combination of independent latent functions, forming a flexible kernel structure to handle multi-type responses. Comparative studies demonstrate that the proposed method scales well for large datasets with over 104 data points, while outperforming state-of-the-art machine learning methods without requiring much hyperparameter tuning. In addition, an interpretable latent space is obtained to draw insights into the effect of qualitative factors, such as those associated with "building blocks" of architectures and element choices in metamaterial and materials design. Our approach is demonstrated for machine learning of ternary oxide materials and topology optimization of a multiscale compliant mechanism with aperiodic microstructures and multiple materials.

关键词： Gaussian process Surrogate modeling Big data Qualitative factor Multi-type response Latent variable Topology optimization

来源：评论

学校读者我要写书评

暂无评论

8th International conference on Scale Space and Variational methods in Computer Vision, SSVM 2021

8th International Conference on Scale Space and Variational ...

引用

8th International conference on Scale Space and Variational methods in Computer Vision, SSVM 2021

ISBN: (纸本)9783030755485

The proceedings contain 45 papers. The special focus in this conference is on Scale Space and Variational methods in Computer Vision. The topics include: multiscale Registration;challenges for Optical Flow Estimates in Elastography;an Anisotropic Selection Scheme for Variational Optical Flow methods with Order-Adaptive Regularisation;low-Rank Registration of Images Captured Under Unknown, Varying Lighting;towards Efficient Time Stepping for Numerical Shape Correspondence;first Order Locally Orderless Registration;first-Order Geometric Multilevel optimization for Discrete Tomography;bregman Proximal Gradient Algorithms for Deep Matrix Factorization;Hessian Initialization Strategies for -BFGS Solving Non-linear Inverse Problems;inverse Scale Space Iterations for Non-convex Variational Problems Using Functional Lifting;quantisation Scale-Spaces;A Scaled and Adaptive FISTA Algorithm for Signal-Dependent Sparse Image Super-Resolution Problems;Convergence Properties of a Randomized Primal-Dual Algorithm with applications to Parallel MRI;wasserstein Generative Models for Patch-Based Texture Synthesis;sketched Learning for Image Denoising;Translating Numerical Concepts for PDEs into Neural Architectures;CLIP: Cheap Lipschitz Training of Neural Networks;variational Models for Signal Processing with Graph Neural Networks;synthetic Images as a Regularity Prior for Image Restoration Neural Networks;geometric Deformation on Objects: Unsupervised Image Manipulation via Conjugation;learning Local Regularization for Variational Image Restoration;Equivariant Deep Learning via Morphological and Linear Scale Space PDEs on the Space of Positions and Orientations;on the Correspondence Between Replicator Dynamics and Assignment Flows;learning Linear Assignment Flows for Image Labeling via Exponential Integration;on the Geometric Mechanics of Assignment Flows for Metric Data Labeling;a Deep Image Prior Learning Algorithm for Joint Selective Segmentation and Registration.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MULTIBENCH: multiscale Benchmarks for Multimodal Representation Learning 35

MULTIBENCH: Multiscale Benchmarks for Multimodal Representat...

引用

35th conference on Neural Information Processing Systems - Track on Datasets and Benchmarks, NeurIPS Datasets and Benchmarks 2021

作者： Liang, Paul Pu Lyu, Yiwei Fan, Xiang Wu, Zetian Cheng, Yun Wu, Jason Chen, Leslie Wu, Peter Lee, Michelle A. Zhu, Yuke Salakhutdinov, Ruslan Morency, Louis-Philippe CMU United States Johns Hopkins United States Northeastern United States Stanford United States UT Austin United States

Learning multimodal representations involves integrating information from multiple heterogeneous sources of data. It is a challenging yet crucial area with numerous real-world applications in multimedia, affective computing, robotics, finance, human-computer interaction, and healthcare. Unfortunately, multimodal research has seen limited resources to study (1) generalization across domains and modalities, (2) complexity during training and inference, and (3) robustness to noisy and missing modalities. In order to accelerate progress towards understudied modalities and tasks while ensuring real-world robustness, we release MULTIBENCH, a systematic and unified large-scale benchmark for multimodal learning spanning 15 datasets, 10 modalities, 20 prediction tasks, and 6 research areas. MULTIBENCH provides an automated end-to-end machine learning pipeline that simplifies and standardizes data loading, experimental setup, and model evaluation. To enable holistic evaluation, MULTIBENCH offers a comprehensive methodology to assess (1) generalization, (2) time and space complexity, and (3) modality robustness. MULTIBENCH introduces impactful challenges for future research, including scalability to large-scale multimodal datasets and robustness to realistic imperfections. To accompany this benchmark, we also provide a standardized implementation of 20 core approaches in multimodal learning spanning innovations in fusion paradigms, optimization objectives, and training approaches. Simply applying methods proposed in different research areas can improve the state-of-the-art performance on 9/15 datasets. Therefore, MULTIBENCH presents a milestone in unifying disjoint efforts in multimodal machine learning research and paves the way towards a better understanding of the capabilities and limitations of multimodal models, all the while ensuring ease of use, accessibility, and reproducibility. MULTIBENCH, our standardized implementations, and leaderboards are publicly available, wil

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

An Efficient iterative MoM-PO Hybrid Method for Calculating Scattered Fields of the multiscale and Multiphysics Scatterers

An Efficient iterative MoM-PO Hybrid Method for Calculating ...

引用

International conference on Numerical Electromagnetic Modeling and optimization for RF, Microwave, and Terahertz applications (NEMO)

作者： Zhi Yang Xue Yu Mao Wu Ya Qiu Jin

ISBN: (数字)9781728169668

ISBN: (纸本)9781728169675

Facing the problem of multi-scale electromagnetic calculation, the method of moment (MoM) and physical optics (PO) hybrid (MoM-PO) method is introduced to get the efficient electromagnetic simulation. This method is based on the iterative technology between the MoM region and PO region. Finally, numerical experiments from the electrically large and multi-scale scatterers are provided to benchmark the efficiencies of the MoM-PO hybrid method.

关键词： Physical optics Numerical models Iterative methods Optical scattering Electromagnetics Method of moments optimization

来源：评论

学校读者我要写书评

暂无评论

SUBDIVISION-BASED NONLINEAR multiscale CLOTH SIMULATION

引用

SIAM JOURNAL ON SCIENTIFIC COMPUTING 2019年第5期41卷 S433-S461页

作者： Kopanicakova, Alena Krause, Rolf Tamstorf, Rasmus Univ Svizzera Italiana Inst Computat Sci CH-6900 Lugano Switzerland Walt Disney Animat Studios Burbank CA 91521 USA

Cloth simulation is an important topic for many applications in computer graphics, animation, and augmented virtual reality. The mechanical behavior of cloth objects can be modeled by the Kirchhoff-Love thin shell equations, which lead to large-scale, nonlinear, ill-conditioned algebraic equations. We propose to solve these nonlinear problems efficiently using the recursive multilevel trust region (RMTR) method. Our multilevel framework for cloth simulations is based on Catmull-Clark subdivision surfaces, which facilitates generation of the mesh hierarchy and also provides the basis for the finite element discretization. The prolongation and restriction operators are similarly constructed based on the subdivision rules. Finally, we leverage a reverse subdivision operator to transfer iterates from fine levels to coarser levels. The novel use of this fine-to-coarse operator provides a computationally efficient alternative to the least-square approach used elsewhere. Using the resulting RMTR variant, we present numerical examples showing a reduction in the number of iterations by several orders of magnitude when compared to a single-level trust region method.

关键词： thin shell cloth simulation isogeometric analysis subdivision surfaces trust region methods multilevel optimization

来源：评论

学校读者我要写书评

暂无评论

A multiscale Image Denoising Algorithm Based on Dilated Residual Convolution Network 1

引用

14th conference on Image and Graphics Technologies and applications, IGTA 2019

作者： Liu, Chang Shang, Zhaowei Qin, Anyong College of Computer Science Chongqing University Chongqing400044 China

ISBN: (数字)9789811399176

ISBN: (纸本)9789811399169

Image denoising is a classical problem in low-level computer vision. Model-based optimization methods and deep learning approaches are the two main strategies for solving the problem. Model-based optimization methods are flexible for handling different inverse problems but are usually time-consuming. In contrast, deep learning methods have fast speed but the performance of these convolutional neural networks (CNNs) is still inferior. To address this issue, here we propose a novel deep learning model that combines the dilated residual convolution and multi-scale convolution groups. Due to the complex patterns and structures inside an image, the design of hybrid dilated convolution is utilized to learn those patterns. Specifically, the skipped connection is utilized to speed up the training process while maintaining the denoising performance. In order to show the capacity of the proposed work, we do an ablation study to validate the effect of dilated convolution and multi-scale convolution group. Experimental results have demonstrated that our enhanced denoiser can not only achieve promising denoising results, but also become a strong competitor in practical application. © 2019, Springer Nature Singapore Pte Ltd.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Theory and applications of the Node-based Meshless Method and the Time-Reversal Method 5

Theory and Applications of the Node-based Meshless Method an...

引用

5th IEEE International conference on Computational Electromagnetics, ICCEM 2019

作者： Chen, Zhizhang David Depaerment of Electrical and Computer Enginering Dalhousie University HalifaxNSB3J 1Z1 Canada

ISBN: (纸本)9781538671115

This paper presents our recent work on the node-based meshless numerical method and the time-reversal method. The meshless method can serve as a platform to unify or hybridize numerical methods and is well fit for solving multiscale and Multiphysics problems. The time reversal method is reformulated as an optimization problem and can be used for reconstruction of clustered sources and diagnosis of faulty antenna elements;they pave the way for automatic locations of EMC/EMI radiation sources for automatic synthesis, design and diagnosis of antenna and antenna array. © 2019 IEEE.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Theory and applications of the Node-based Meshless Method and the Time-Reversal Method

Theory and Applications of the Node-based Meshless Method an...

引用

IEEE International conference on Computational Electromagnetics (ICCEM)

作者： Zhizhang Chen Dalhousie University Halifax Nova Scotia Canada

This paper presents our recent work on the node-based meshless numerical method and the time-reversal method. The meshless method can serve as a platform to unify or hybridize numerical methods and is well fit for solving multiscale and Multiphysics problems. The time reversal method is reformulated as an optimization problem and can be used for reconstruction of clustered sources and diagnosis of faulty antenna elements; they pave the way for automatic locations of EMC/EMI radiation sources for automatic synthesis, design and diagnosis of antenna and antenna array.

关键词：

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：