检索结果-内蒙古大学图书馆

Deep generative network for image inpainting with gradient semantics and spatial-smooth attention

Journal of Visual Communication and Image Representation 2024年 98卷

作者： Sheng, Ziqi Xu, Wenbo Lin, Cong Lu, Wei Ye, Long School of Computer Science and Engineering Guangdong Province Key Laboratory of Information Security Technology Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing Sun Yat-sen University Guangzhou510006 China Applied Laboratory of Dig Data and Education Statistics School of Statistics and Mathematics Guangdong University of Finance and Economics Guangzhou510320 China State Key Laboratory of Media Convergence and Communication Communication University of China Beijing100024 China

As a powerful forgery operation in the image content security area, image inpainting based on deep generative networks can yield visually appealing outputs but often produces ambiguous artifacts, especially in boundary and high semantic areas. To address this issue, a novel end-to-end network with gradient semantics and spatial-smooth attention (GS-SSA) is proposed, which combines a gradient learning network and an image inpainting network. The gradient learning network is meant to properly anticipate the gradient semantics in the hole region and get a complete gradient semantic map. The image inpainting network utilizes the complete gradient semantic map to better repair the missing pixels and obtain the final inpainting results. Moreover, spatial-smooth attention is introduced into the image inpainting network, considering both the spatial structural relations and the surrounding information in the hole region. Experimental results on public datasets show the superiority of the proposed method, especially in large-hole region tasks. © 2023 Elsevier Inc.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Towards Depth-continuous Scene Representation with Displacement Field for Robust Light Field Depth Estimation

引用

IEEE Transactions on Multimedia 2025年 27卷 3637-3649页

作者： Chen, Rongshan Sheng, Hao Yang, Da Cong, Ruixuan Cui, Zhenglong Wang, Sizhe Wang, Tun Zhao, Mingyuan Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing100191 China Beihang University Key Laboratory of Data Science and Intelligent Computing International Innovation Institute 166 Shuanghongqiao Street Pingyao Town Yuhang District Hangzhou31 1115 China Macao Polytechnic University Faculty of Applied Sciences Macao999078 China

The light field (LF) captures both the spatial and angular information of scenes, enabling accurate depth estimation. However, previous deep learning methods typically model surface depth only while ignoring the continuous nature of depth in 3D scenes. In this paper, we use the displacement field (DF) to describe this continuous property, and propose a novel depth-continuous scene representation for robust LF depth estimation. Experiments demonstrate that our representation enables the network to generate highly detailed depth maps with fewer parameters and faster speeds. Specifically, inspired by the signed distance field in 3D object descriptions, we aim to exploit the intrinsic depth-continuous property of 3D scenes via DF and define a novel depth-continuous scene representation. Then, we introduce a simple, yet general, learning framework for depth-continuous scene embedding, and the proposed network, DepthDF, achieves state-of-the-art performance on both synthetic and real-world LF datasets, ranking 1st on the HCI 4D light field benchmark. Furthermore, previous LF depth estimation methods can also be seamlessly integrated into this framework. Finally, we extend this framework beyond LF depth estimation to various tasks, including multiview stereo depth inference, LF superresolution, and LF salient object detection. Our experiments demonstrate an improved performance when continuous scene representation is applied, suggesting that our framework can potentially provide insights for more fields. © 1999-2012 IEEE.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

GAPPY AE: A NONLINEAR APPROACH FOR GAPPY DATA RECONSTRUCTION USING AUTO-ENCODER

arXiv

引用

arXiv 2023年

作者： Kim, Youngkyu Choi, Youngsoo Yoo, Byounghyun Center for Artificial Intelligence Korea Institute of Science and Technology Seongbuk-gu Seoul02792 Korea Republic of Center for Applied Scientific Computing Lawrence Livermore National Laboratory LivermoreCA94550 United States

We introduce a novel data reconstruction algorithm known as Gappy auto-encoder (Gappy AE) to address the limitations associated with Gappy proper orthogonal decomposition (Gappy POD), a widely used method for data reconstruction when dealing with sparse measurements or missing data. Gappy POD has inherent constraints in accurately representing solutions characterized by slowly decaying Kolmogorov N-widths, primarily due to its reliance on linear subspaces for data prediction. In contrast, Gappy AE leverages the power of nonlinear manifold representations to address data reconstruction challenges of conventional Gappy POD. It excels at real-time state prediction in scenarios where only sparsely measured data is available, filling in the gaps effectively. This capability makes Gappy AE particularly valuable, such as for digital twin and image correction applications. To demonstrate the superior data reconstruction performance of Gappy AE with sparse measurements, we provide several numerical examples, including scenarios like 2D diffusion, 2D radial advection, and 2D wave equation problems. Additionally, we assess the impact of four distinct sampling algorithms - discrete empirical interpolation method, the S-OPT algorithm, Latin hypercube sampling, and uniformly distributed sampling - on data reconstruction accuracy. Our findings conclusively show that Gappy AE outperforms Gappy POD in data reconstruction when sparse measurements are given. © 2023, CC BY-NC-ND.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

XNL-CNN: An Improved Version Of The NL-CNN Model, For Running With TPU Accelerators And Large Image Datasets

XNL-CNN: An Improved Version Of The NL-CNN Model, For Runnin...

引用

International Symposium on Electrical and Electronics Engineering (ISEEE)

作者： Radu Dogaru Adrian-Dumitru Mirică Ioana Dogaru Dept. of Applied Electronics and Information Eng. Natural Computing Laboratory University “Politehnica” of Bucharest Bucharest Romania Doctoral School of Electronics Telecommunications and Information Technology University “Politehnica” of Bucharest Bucharest Romania

This paper introduces XNL-CNN, an extended version of the previously introduced, compact NL-CNN model. While the NL-CNN was designed with typical Tiny-ML constraints in order to make possible integration of various AI image recognition solutions into low power, low complexity computing platforms, the same stands for its extended version discussed herein. In addition, we consider additional layers to cope with larger image sizes, as found in most actual relevant datasets (e.g. the Cars196 or Flowers104). Moreover, since working with large image sizes requires intensive computational power, TPU accelerators readily available on Kaggle platform were used for training and evaluation of our model. In comparison to other, widely known resources-constrained architectures, such as EfficientNet or MobileNet our model offers the following advantages: i) a larger set of hyper-parameters allowing the user to do better designs (maximal accuracy for minimal resources), adapted for a wide variety of datasets; ii) has a low number of layer primitives, thus making easier their specific design for deployment on various TinyML or EdgeAI platforms, including FPGAS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Rectangular multiple-relaxation-time lattice Boltzmann method for the Navier-Stokes and nonlinear convection-diffusion equations: General equilibrium and some important issues

引用

Physical Review E 2023年第1期108卷 015304-015304页

作者： Zhenhua Chai (柴振华) Xiaolei Yuan (袁晓垒) Baochang Shi (施保昌) School of Mathematics and Statistics Huazhong University of Science and Technology Wuhan 430074 China Institute of Interdisciplinary Research for Mathematics and Applied Science Huazhong University of Science and Technology Wuhan 430074 China Hubei Key Laboratory of Engineering Modeling and Scientific Computing Huazhong University of Science and Technology Wuhan 430074 China College of Mathematics and Information Science Hebei University Baoding 071002 China

In this paper, we develop a general rectangular multiple-relaxation-time lattice Boltzmann (RMRT-LB) method for the Navier-Stokes equations (NSEs) and nonlinear convection-diffusion equation (NCDE) by extending our recent unified framework of the multiple-relaxation-time lattice Boltzmann (MRT-LB) method [Chai and Shi, Phys. Rev. E 102, 023306 (2020)], where an equilibrium distribution function (EDF) [Lu et al., Philos. Trans. R. Soc. A 369, 2311 (2011)] on a rectangular lattice is utilized. The anisotropy of the lattice tensor on a rectangular lattice leads to anisotropy of the third-order moment of the EDF, which is inconsistent with the isotropy of the viscous stress tensor of the NSEs. To eliminate this inconsistency, we extend the relaxation matrix related to the dynamic and bulk viscosities. As a result, the macroscopic NSEs can be recovered from the RMRT-LB method through the direct Taylor expansion method. Whereas the rectangular lattice does not lead to the change of the zero-, first- and second-order moments of the EDF, the unified framework of the MRT-LB method can be directly applied to the NCDE. It should be noted that the RMRT-LB model for NSEs can be derived on the rDdQq (q discrete velocities in d-dimensional space, d≥1) lattice, including rD2Q9, rD3Q19, and rD3Q27 lattices, while there are no rectangular D3Q13 and D3Q15 lattices within this framework of the RMRT-LB method. Thanks to the block-lower triangular relaxation matrix introduced in the unified framework, the RMRT-LB versions (if existing) of the previous MRT-LB models can be obtained, including those based on raw (natural) moment, central moment, Hermite moment, and central Hermite moment. It is also found that when the parameter cs is an adjustable parameter in the standard or rectangular lattice, the present RMRT-LB method becomes a kind of MRT-LB method for the NSEs and NCDE, and the commonly used MRT-LB models on the DdQq lattice are only its special cases. We also perform some numeric

关键词： Lattice-Boltzmann methods

来源：评论

学校读者我要写书评

暂无评论

Advancing Simulations of Coupled Electron and Phonon Nonequilibrium Dynamics Using Adaptive and Multirate Time Integration

arXiv

引用

arXiv 2024年

作者： Yao, Jia Maliyov, Ivan Gardner, David J. Woodward, Carol S. Bernardi, Marco Department of Applied Physics and Materials Science Department of Physics California Institute of Technology PasadenaCA91125 United States Mathematics for Materials Modeling Institute of Mathematics Institute of Materials EPFL LausanneCH-1015 Switzerland Center for Applied Scientific Computing Lawrence Livermore National Laboratory LivermoreCA94550 United States

Electronic structure calculations in the time domain provide a deeper understanding of nonequilibrium dynamics in materials. The real-time Boltzmann equation (rt-BTE), used in conjunction with accurate interactions computed from first principles, has enabled reliable predictions of coupled electron and lattice dynamics. However, the timescales and system sizes accessible with this approach are still limited, with two main challenges being the different timescales of electron and phonon interactions and the cost of computing collision integrals. As a result, only a few examples of these calculations exist, mainly for two-dimensional (2D) materials. Here we leverage adaptive and multirate time integration methods to achieve a major step forward in solving the coupled rt-BTEs for electrons and phonons. Relative to conventional (non-adaptive) time-stepping, our approach achieves a 10x speedup for a given target accuracy, or greater accuracy by 3–6 orders of magnitude for the same computational cost, enabling efficient calculations in both 2D and bulk materials. This efficiency is showcased by computing the coupled electron and lattice dynamics in graphene up to ∼100 ps, as well as modeling ultrafast lattice dynamics and thermal diffuse scattering maps in a bulk material (silicon). These results open new opportunities for quantitative studies of nonequilibrium physics in materials. Copyright © 2024, The Authors. All rights reserved.

关键词： Boltzmann equation

来源：评论

学校读者我要写书评

暂无评论

Explainable-AI-based two-stage solution for WSN object localization using zero-touch mobile transceivers

引用

Science China(Information Sciences) 2024年第7期67卷 27-45页

作者： Kai FANG Junxin CHEN Han ZHU Thippa Reddy GADEKALLU Xiaoping WU Wei WANG School of Mathematics and Computer Science Zhejiang A&F University School of Software Dalian University of Technology Faculty of Applied Sciences Macao Polytechnic University Department of Electrical and Computer Engineering Lebanese American University School of Information Engineering Huzhou University Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing Artificial Intelligence Research Institute Shenzhen MSU-BIT University

Artificial intelligence technology is widely used in the field of wireless sensor networks(WSN).Due to its inexplicability, the interference factors in the process of WSN object localization cannot be effectively eliminated. In this paper, an explainable-AI-based two-stage solution is proposed for WSN object localization. In this solution, mobile transceivers are used to enlarge the positioning range and eliminate the blind area for object localization. The motion parameters of transceivers are considered to be unavailable,and the localization problem is highly nonlinear with respect to the unknown parameters. To address this,an explainable AI model is proposed to solve the localization problem. Since the relationship among the variables is difficult to fully include in the first-stage traditional model, we develop a two-stage explainable AI solution for this localization problem. The two-stage solution is actually a comprehensive consideration of the relationship between variables. The solution can continue to use the constraints unused in the firststage during the second-stage, thereby improving the performance of the solution. Therefore, the two-stage solution has stronger robustness compared to the closed-form solution. Experimental results show that the performance of both the two-stage solution and the traditional solution will be affected by numerical changes in unknown parameters. However, the two-stage solution performs better than the traditional solution, especially with a small number of mobile transceivers and sensors or in the presence of high noise. Furthermore,we have also verified the feasibility of the proposed explainable-AI-based two-stage solution.

关键词： explainable AI object localization semidefinite relaxation mobile transceiver two-stage solution closed-form solution

来源：评论

学校读者我要写书评

暂无评论

Code Refactoring for Software Reusability: An Experimental Study

Code Refactoring for Software Reusability: An Experimental S...

引用

Emerging Smart Technologies and Applications (eSmarTA), International Conference on

作者： Abdullah Almogahed Hairulnizam Mahdin Mazidah Mat Rejab Abdulwadood Alawadhi Samera Obaid Barraood Manal Othman Omar Al-Jamili Abdulwahab Ali Almazroi Shazlyn Milleana Shaharudin Faculty of Computer Science and Information Technology Universiti Tun Hussein Onn Malaysia Parit Raja Johor Malaysia InterNetWorks Research Laboratory School of Computing Universiti Utara Malaysia Sintok Malaysia College of Computers and Information Technology Hadhramout University Hadhramout Yemen Computer Science Department College of Applied Science Taiz University Taiz Yemen Faculty of Engineering and Computing University of Science and Technology Yemen Department of Information Technology College of Computing and Information Technology at Khulais University of Jeddah Jeddah Saudi Arabia Faculty of Science and Mathematics Universiti Pendidikan Sultan Idris Tanjong Malim Malaysia

ISBN: (数字)9798350354133

ISBN: (纸本)9798350354140

Refactoring plays a critical role in enhancing the quality of software systems, enabling them to accommodate growing user bases, feature sets, and performance demands. Software reusability is an essential aspect of software quality. It is crucial in modern software development as it offers several benefits, including increased productivity, improved code quality, and cost-effectiveness. However, there is a lack of studies investigating how specific refactoring techniques affect reusability. Therefore, this study aims to explore the effects of code refactoring on software reusability. This study was conducted in four stages: selecting refactoring techniques, selecting a large dataset, selecting software metrics to measure the reusability, and applying the refactoring techniques. The five most common refactoring techniques (Extract Interface, Encapsulate Field, Extract Class, Inline Class, and Inline Method) used in practices were selected and applied in the jEdit dataset. The refactoring techniques were carried out 338 times through five experiments in the jEdit dataset. The finding reveals that Extract Interface, Encapsulate Field, and Extract Class significantly improve the code reusability while Inline Class and Inline Method impair it. Developers and software architects can use this knowledge to make well-informed judgments about refactoring techniques and develop more robust and reusable software systems.

关键词： Productivity Industries Codes Software quality Software systems Maintenance Software measurement

来源：评论

学校读者我要写书评

暂无评论

Multimodal Dialogue Emotion Recognition Based on Label Optimization and Coarse-Grained Assisted Fine-Grained

Multimodal Dialogue Emotion Recognition Based on Label Optim...

引用

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

作者： Zhibo Zhang Zhenyu Yang Yan Huang Baojie Xu Wenyue Hu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Multimodal dialogue emotion recognition integrates data from multiple modalities to accurately identify emotional states in conversations. However, differences in expression and information density across modalities complicate the fusion of features. Traditional methods may introduce redundant information from other utterances, reducing the accuracy of emotion recognition. Existing one-hot labels often fail to capture the full range of emotional expressions, leading to biased results. To address these issues, we propose a model that fuses different modalities within the same utterance to avoid redundancy. It employs a progressive classification process, refining emotion recognition from coarse to fine granularity. Additionally, we use emotion polarity probabilities as weights for fine-grained classification and introduce a multimodal information-rich label that considers both the data and their interactions. Experiments on IEMOCAP and MELD datasets demonstrate the model’s effectiveness, significantly improving dialog emotion recognition accuracy. Our code is available at https://***/r/LOCG-188E.

关键词： Emotion recognition Accuracy Fuses Refining Termination of employment Speech recognition Signal processing Speech processing Optimization Faces

来源：评论

学校读者我要写书评

暂无评论

SYNOPSET: MULTISCALE VISUAL ABSTRACTION SET FOR EXPLANATORY ANALYSIS OF DNA NANOtechnology SIMULATIONS

arXiv

引用

arXiv 2022年

作者： Luo, Deng Kouyoumdjian, Alexandre Strnad, Ondřej Miao, Haichao Barišić, Ivan Viola, Ivan Saudi Arabia Center for Applied Scientific Computing Lawrence Livermore National Laboratory United States Center for Health and Bioresources Austrian Institute of Technology Austria

We propose a new abstraction set (SynopSet) that has a continuum of visual representations for the explanatory analysis of molecular dynamics simulations (MDS) in the DNA nanotechnology domain. By re-purposing the commonly used progress bar and designing novel visuals, as well as transforming the data from the domain format to a format that better fits the newly designed visuals, we compose this new set of representations. This set is also designed to be capable of showing all spatial and temporal details, and all structural complexity, or abstracting these to various degrees, enabling both the slow playback of the simulation for detailed examinations or very fast playback for an overview that helps to efficiently identify events of interest, as well as several intermediate levels between these two extremes. For any pair of successive representations, we demonstrate smooth, continuous transitions, enabling users to keep track of relevant information from one representation to the next. By providing multiple representations suited to different temporal resolutions and connected by smooth transitions, we enable time-efficient simulation analysis, giving users the opportunity to examine and present important phases in great detail, or leverage abstract representations to go over uneventful phases much faster. Domain experts can thus gain actionable insight about their simulations and communicate it in a much shorter time. Further, the novel representations are more intuitive and also enable researchers unfamiliar with MDS analysis graphs to better understand the simulation results. We assessed the effectiveness of SynopSet on 12 DNA nanostructure simulations together with a domain expert. We have also shown that our set of representations can be systematically located in a visualization space, dubbed SynopSpace, composed of three axes: granularity, visual idiom, and information layout type. Proposed at the end are general guidelines on the use of SynopSpace to generate

关键词： Molecular dynamics

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：