检索结果-内蒙古大学图书馆

26th Irish Machine Vision and Image Processing conference, IMVIP 2024

作者： Raymond, Mary Sistu, Ganesh Gallagher, Louis Valeo Vision Systems Ireland Maynooth University Ireland

ISBN: (纸本)9781837242672

Neural Radiance Fields (NeRF) rendering is a promising Artificial intelligence (AI) technology for generating photorealistic views, with significant potential for automotive applications. However, traditional metrics such as Structural Similarity Index Measure (SSIM), Peak Signal-to-Noise Ratio (PSNR), and Learned Perceptual Image Patch Similarity (LPIPS) often fail to evaluate the model's quality for novel viewpoints outside the dataset range, which is crucial for real-life use. this study introduces the Fréchet Inception Distance (FID) as a no-reference image quality metric for novel viewpoints. Our experiments demonstrate that FID aligns well with human quality assessments and is effective in automotive scenarios with fisheye images. the need for further research on FID normalization, the sample sizes of generated viewpoints used to calculate FID, and measures of viewpoint difficulty is highlighted. Adopting FID advances NeRF evaluation, enhancing assessments in real life scenarios within automotive and robotics, and improving autonomous system performance and safety. More results from our experiments are available here https://***/watch?v=Lb8azH79EI0. © this is an open access article published by the IET under the Creative Commons Attribution License (http://***/licenses/by/3.0/)

关键词： Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

Parallel architecture for conversion of NURBS curves to Be/spl acute/zier curves

Parallel architecture for conversion of NURBS curves to Be/s...

引用

EUROMICRO conference

作者： P.N. Mallon M. Boo J.D. Bruguera Department of Electronic and Computer Engineering University of Santiago de Compostela Spain

NURBS are one of the most common methods of representing curves and surfaces in the geometric modeling and computer graphics fields, whilst numerous computer graphics algorithms are based on the utilization of a simpler representation of the same curves and surfaces: Be/spl acute/zier representations. In this paper, we present a parallel architecture to perform the decomposition of a NURBS curve into its constituent Be/spl acute/zier polynomial pieces. this architecture presents a regular and easily scalable structure, suitable for VLSI implementation, which can be efficiently exploited for the decomposition process. the performance of the proposed architecture is improved by the use of carry-save arithmetic, which permits the reduction of the system cycle time.

关键词： Parallel architectures Spline Surface topography Surface reconstruction computer graphics Solid modeling Polynomials computer architecture Very large scale integration Arithmetic

来源：评论

学校读者我要写书评

暂无评论

On the communication complexity of 3D FFTs and its implications for exascale 12

On the communication complexity of 3D FFTs and its implicati...

引用

26th ACM International conference on Supercomputing, ICS'12

作者： Czechowski, Kenneth Battaglino, Casey McClanahan, Chris Iyer, Kartik Yeung, P.-K. Vuduc, Richard School of Computer Science Georgia Institute of Technology Atlanta GA United States School of Computational Science and Engineering Georgia Institute of Technology Atlanta GA United States School of Aerospace Engineering Georgia Institute of Technology Atlanta GA United States

ISBN: (纸本)9781450313162

this paper revisits the communication complexity of large-scale 3D fast Fourier transforms (FFTs) and asks what impact trends in current architectures will have on FFT performance at exascale. We analyze both memory hierarchy traffic and network communication to derive suitable analytical models, which we calibrate against current software implementations;we then evaluate models to make predictions about potential scaling outcomes at exascale, based on extrapolating current technology trends. Of particular interest is the performance impact of choosing high-density processors, typified today by graphics co-processors (GPUs), as the base processor for an exascale system. Among various observations, a key prediction is that although inter-node all-to-all communication is expected to be the bottleneck of distributed FFTs, intra-node communication - expressed precisely in terms of the relative balance among compute capacity, memory bandwidth, and network bandwidth - will play a critical role. Copyright 2012 ACM.

关键词： Fast Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

Collisions (2D) between diatomic molecules

Collisions (2D) between diatomic molecules

引用

Frontiers in Education (FIE) conference

作者： E. Martin R. Chicon CoLoS GroupDepartment of Physics University of Murcia Murcia Spain

the formalism to deal with collisions between two rigid bodies of arbitrary shape in two dimensions is described. this formalism is applied to the collision between rigid diatomic molecules. A simulation to show the behavior of a diatomic gas has been developed, and the Principle of Equipartition of Energy is explicitly demonstrated.

关键词： Shape Motion analysis Physics Computational modeling computer graphics computer simulation Containers Temperature Real time systems Visualization

来源：评论

学校读者我要写书评

暂无评论

A model for using productivity software in the engineering classroom: MAP VARS & DOC

A model for using productivity software in the engineering c...

引用

Frontiers in Education (FIE) conference

作者： J.A. Puckett J.C. Hamann College of Engineering University of Wurzburg Laramie WY USA

the paper addresses software's place in the engineering classroom. the authors present an eight-step process to develop effective, computer-based solutions to engineering problems using standard productivity software: i.e., off-the-self applications that facilitate mathematics, arithmetic, CAD, presentation graphics, and other day-to-day engineering tasks. Examples of such applications include spreadsheets, equation solvers, symbolic manipulators, matrix manipulators, graphic routines, and CAD. Other systems in specific disciplines are also used.

关键词： Productivity Reactive power Mathematical model Application software computer graphics Education Software standards Standards development Mathematics Equations

来源：评论

学校读者我要写书评

暂无评论

AIIE ANNUAL conference AND CONVENTION, 26th, proceedings, spring 1975.

Proceedings, American Institute of Industrial Engineers, Ann...

引用

proceedings, American Institute of Industrial Engineers, Annual conference and Convention 1975年

作者： Conf

this symposium of 70 papers was presented at the 26th Annual conference and Convention held in Washington, D. C. on May 20-23, 1975. these papers cover such topics as: aerospace technology; computer and information systems; engineering economy; ergonomics; facilities planning and design; government, hospital and health services; management; manufacturing systems; operations research; production planning and control; research and development; transportation and distribution; and work measurement and methods. Selected papers are indexed separately.

关键词： INDUSTRIAL ENGINEERING

来源：评论

学校读者我要写书评

暂无评论

A summer workshop in 3D computer graphics and the World Wide Web

A summer workshop in 3D computer graphics and the World Wide...

引用

Frontiers in Education (FIE) conference

作者： A.M. Spalter Graphics and Visualization Center USA

Anne Morgan Spalter works with Professor Andries van Dam to design and teach an intensive three week workshop held at Brown University. For the past three summers, local high school teachers have attended the workshop to learn about concepts in 3D graphics and ways in which computer graphics can be used to motivate the teaching of math, science, and art. Using examples provided by workshop participants and mentor teachers, Spalter discusses ways in which institutions like the graphics and Visualization Center can help teachers learn about a field that now requires knowledge for many disciplines but did not exist as an academic subject when they were in school. Spalter also presents examples of ways in which research scientists can help build bridges between universities and K-12 institutions, helping to ensuring that students will arrive at college or in the workforce with the necessary preparation. During the summer of 1996, Center staff members, Brown University undergraduates, and teacher workshop participants created curricular resources that will be made available over the World Wide Web. Spalter demonstrates these efforts and introduces the Greenhouse Web site that supports them. Such projects will help future workshop participants and the public at large to better understand and teach concepts in computer graphics and their application to other fields such as mathematics, the physical sciences, and art and design.

关键词： computer graphics

来源：评论

学校读者我要写书评

暂无评论

Vehicle Detection and Classification in Traffic Images Using ConvNets With Constrained Resources 26

Vehicle Detection and Classification in Traffic Images Using...

引用

26th International conference on Systems, Signals and Image Processing (IWSSIP)

作者： Roecker, Max N. Costa, Yandre M. G. Britto, Alceu S., Jr. Oliveira, Luiz E. S. Bertolini, Diego Univ Estadual Maringa Maringa Parana Brazil Pontificia Univ Catolica Parana Curitiba Parana Brazil Univ Fed Parana Curitiba Parana Brazil Fed Technol Univ Parana Curitiba Parana Brazil

ISBN: (纸本)9781728132273

this paper proposes a convolutional neural network model for detection and classification of vehicles present in digital images into six categories, namely Bus, Microbus, Minivan, Sedan, SUV, and Truck. Experimental results with the BIT-Vehicle Dataset report a mean average precision (mAP) of 92.40% and the average intersection over a union (IoU) of 81.26% with the average inference latency under 70 milliseconds in an environment equipped with a graphics processing unit. We conclude that the model is discriminative and capable of generalizing the patterns of the vehicle type classification task while not requiring expensive computational resources. these features suggest that the model can be useful in the development of embedded intelligent traffic systems improving accuracy and decision latency.

关键词： computer vision convolutional neural networks machine learning vehicle classification vehicle detection

来源：评论

学校读者我要写书评

暂无评论

An optimized large-scale hybrid DGEMM design for CPUs and ATI GPUs 12

An optimized large-scale hybrid DGEMM design for CPUs and AT...

引用

26th ACM International conference on Supercomputing, ICS'12

作者： Li, Jiajia Li, Xingjian Tan, Guangming Chen, Mingyu Sun, Ninghui State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781450313162

In heterogeneous systems that include CPUs and GPUs, the data transfers between these components play a critical role in determining the performance of applications. Software pipelining is a common approach to mitigate the overheads of those transfers. In this paper we investigate advanced software-pipelining optimizations for the double-precision general matrix multiplication (DGEMM) algorithm running on a heterogeneous system that includes ATI GPUs. Our approach decomposes the DGEMM workload to a finer detail and hides the latency of CPU-GPU data transfers to a higher degree than previous approaches in literature. We implement our approach in a five-stage software pipelined DGEMM and analyze its performance on a platform including x86 multi-core CPUs and an ATI Radeon™ HD5970 GPU that has two Cypress GPU chips on board. Our implementation delivers 758 GFLOPS (82% floating-point efficiency) when it uses only the GPU, and 844 GFLOPS (80% efficiency) when it distributes the workload on both CPU and GPU. We analyze the performance of our optimized DGEMM as the number of GPU chips employed grows from one to two, and the results show that resource contention on the PCIe bus and on the host memory are limiting factors. Copyright 2012 ACM.

关键词： graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence and Applications 1

Artificial Intelligence and Applications

引用

丛书名： Communications in computer and Information Science

1000年

作者： Hamid R. Arabnia Leonidas Deligiannidis Soheyla Amirian Farzan Shenavarmasouleh Farid Ghareh Mohammadi David de la Fuente

ISBN: (数字)9783031866234

ISBN: (纸本)9783031866227

this book constitutes the proceedings of the 26th International conference on Artificial Intelligence and Applications, ICAI 2024, held as part of the 2024 World Congress in computer Science, computer Engineering and Applied Computing, in Las Vegas, USA, during July 22 to July 25, 2024. the 38 full papers included in this book were carefully reviewed and selected from 376 submissions. they have been organized in topical sections as follows: Deep convolutional neural networks, ANNs, and applications; machine learning and novel applications; large language models and applications; data science, recognition and authentication methods and applications; artificial intelligence and applications; XXIV Technical Session on Applications of Advanced AI Techniques to information management for solving company-related problems.

关键词： Systems and Data Security Software Engineering/Programming and Operating Systems computer Imaging, Vision, Pattern Recognition and graphics Artificial Intelligence computer Science, general

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：