检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

10,079 篇 会议
276 篇 期刊文献
37 册 图书
2 篇 科技报告

馆藏范围

10,394 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

7,296 篇 工学
- 5,761 篇 计算机科学与技术...
- 3,645 篇 软件工程
- 1,369 篇 信息与通信工程
- 1,289 篇 电气工程
- 878 篇 控制科学与工程
- 829 篇 电子科学与技术（可...
- 465 篇 机械工程
- 463 篇 生物工程
- 392 篇 光学工程
- 372 篇 动力工程及工程热...
- 365 篇 生物医学工程（可授...
- 289 篇 仪器科学与技术
- 261 篇 化学工程与技术
- 239 篇 交通运输工程
- 231 篇 网络空间安全
- 206 篇 材料科学与工程（可...
- 192 篇 土木工程
- 188 篇 建筑学
- 184 篇 安全科学与工程
2,762 篇 理学
- 1,412 篇 数学
- 873 篇 物理学
- 504 篇 生物学
- 363 篇 统计学（可授理学、...
- 344 篇 化学
- 240 篇 系统科学
1,336 篇 管理学
- 821 篇 管理科学与工程(可...
- 631 篇 图书情报与档案管...
- 367 篇 工商管理
445 篇 医学
- 346 篇 临床医学
- 192 篇 基础医学(可授医学...
186 篇 教育学
143 篇 法学
126 篇 经济学
48 篇 农学
41 篇 军事学
31 篇 文学
10 篇 艺术学
1 篇 哲学
1 篇 历史学

主题

1,025 篇 program processo...
727 篇 computer archite...
417 篇 computational mo...
384 篇 hardware
340 篇 high performance...
260 篇 parallel process...
238 篇 computer science
192 篇 optimization
171 篇 benchmark testin...
164 篇 concurrent compu...
163 篇 application soft...
159 篇 runtime
156 篇 computer vision
149 篇 bandwidth
129 篇 registers
129 篇 libraries
129 篇 deep learning
123 篇 parallel program...
120 篇 scalability
120 篇 throughput

机构

69 篇 college of compu...
57 篇 school of comput...
55 篇 university of ch...
45 篇 school of comput...
33 篇 department of co...
32 篇 college of compu...
31 篇 univ chinese aca...
30 篇 school of comput...
30 篇 tsinghua univers...
27 篇 school of comput...
25 篇 school of data a...
23 篇 college of compu...
23 篇 computer network...
23 篇 high energy astr...
22 篇 graduate school ...
21 篇 graduate school ...
20 篇 center for astro...
20 篇 department of ph...
20 篇 department of ph...
20 篇 the graduate sch...

作者

25 篇 tokuno h.
24 篇 ikeda d.
23 篇 belz j.w.
22 篇 jui c.c.h.
22 篇 oshima a.
22 篇 tsuda r.
22 篇 kim j.h.
22 篇 bergman d.r.
22 篇 allen m.
22 篇 matsuyama t.
22 篇 wong t.
22 篇 ishii t.
22 篇 kim s.w.
22 篇 takamura m.
22 篇 yashiro k.
22 篇 kadota k.
22 篇 mayta r.
22 篇 ozawa s.
22 篇 kasami s.
22 篇 rodriguez d.c.

语言

9,981 篇 英文
372 篇 其他
53 篇 中文
3 篇 西班牙文
2 篇 土耳其文
1 篇 葡萄牙文

检索条件"任意字段=Conference on High Performance Computer Modernization Program"

共 10394 条记录，以下是771-780 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Object Localization under Single Coarse Point Supervision

Object Localization under Single Coarse Point Supervision

引用

IEEE/CVF conference on computer Vision and Pattern Recognition (CVPR)

作者： Yu, Xuehui Chen, Pengfei Wu, Di Hassan, Najmul Li, Guorong Yan, Junchi Shi, Humphrey Ye, Qixiang Han, Zhenjun Univ Chinese Acad Sci Beijing Peoples R China Univ Oregon Eugene OR 97403 USA Shanghai Jiao Tong Univ Shanghai Peoples R China Picsart AI Res PAIR Eugene OR USA

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Point-based object localization (POL), which pursues high-performance object sensing under low-cost data annotation, has attracted increased attention. However, the point annotation mode inevitably introduces semantic variance for the inconsistency of annotated points. Existing POL methods heavily reply on accurate key-point annotations which are difficult to define. In this study, we propose a POL method using coarse point annotations, relaxing the supervision signals from accurate key points to freely spotted points. To this end, we propose a coarse point refinement (CPR) approach, which to our best knowledge is the first attempt to alleviate semantic variance from the perspective of algorithm. CPR constructs point bags, selects semantic-correlated points, and produces semantic center points through multiple instance learning (MIL). In this way, CPR defines a weakly supervised evolution procedure, which ensures training high-performance object localizer under coarse point supervision. Experimental results on COCO, DOTA and our proposed SeaPerson dataset validate the effectiveness of the CPR approach. The dataset and code will be available at https://***/ucas- vg/PointTinyBenchmark/.

关键词： Location awareness Training computer vision Codes Annotations Semantics Sensors

来源：评论

学校读者我要写书评

暂无评论

Optimizing Irregular Communication with Neighborhood Collectives and Locality-Aware Parallelism

Optimizing Irregular Communication with Neighborhood Collect...

引用

2023 International conference on high performance Computing, Network, Storage, and Analysis, SC Workshops 2023

作者： Collom, Gerald Li, Rui Peng Bienz, Amanda Department of Computer Science University of New Mexico Albuquerque United States Center for Advanced Scientific Computing Lawrence Livermore National Laboratory Livermore United States

ISBN: (纸本)9798400707858

Irregular communication often limits both the performance and scalability of parallel applications. Typically, applications individually implement irregular communication as point-to-point, and any optimizations are integrated directly into the application. As a result, these optimizations lack portability. It is difficult to optimize point-to-point messages within MPI, as the interface for single messages provides no information on the collection of all communication to be performed. However, the persistent neighbor collective API, released in the MPI 4 standard, provides an interface for portable optimizations of irregular communication within MPI libraries. This paper presents methods for implementing existing optimizations for irregular communication within neighborhood collectives, analyzes the impact of replacing point-to-point communication in existing codebases such as Hypre BoomerAMG with neighborhood collectives, and finally shows up to a 1.38x speedup on sparse matrix-vector multiplication communication within a BoomerAMG solve through the use of our optimized neighbor collectives. The authors analyze three implementations of persistent neighborhood collectives for Alltoallv: an unoptimized wrapper of standard point-to-point communication, and two locality-aware aggregating methods. The second locality-aware implementation exposes an non-standard interface to perform additional optimization, and the authors present the additional 0.07x speedup from the extended interface. All optimizations are available in an open-source codebase, MPI Advance, which sits on top of MPI, allowing for optimizations to be added into existing codebases regardless of the system MPI install. © 2023 ACM.

关键词： Application programming interfaces (API)

来源：评论

学校读者我要写书评

暂无评论

EMIF-Bench: A Benchmark for Embodied Multi-Modal Instruction Following 21

EMIF-Bench: A Benchmark for Embodied Multi-Modal Instruction...

引用

21st International computer conference on Wavelet Active Media Technology and Information Processing, ICCWAMTIP 2024

作者： Yixin, Qin Peng, Yin Zhiqi, Yu The School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China

ISBN: (纸本)9798331519254

In daily life, combining textual and visual instructions in an interleaved manner is typical and natural to boost communication efficiency and, more importantly, aid children's cognitive learning in both language and visual realms. However, in the field of AI and robotics, there is currently a lack of developed evaluation frameworks for evaluating embodied agents that understand visual-language instructions and break instructions down into a sequence of precise plans for performing the desired tasks with the environment. To facilitate this research, we build the first, to our knowledge, a new challenging benchmark, namely Embodied Multi-modal Instruction Following (EMIF-Bench). Our EMIF-Bench has several appealing properties: 1) Interleaved manner: Both instruction and its corresponding plans consist of both textual and visual information. 2) Rich instructions: It comprises 917 visual language instructions with corresponding sequences of plans, including seven types, from Cooking to Leisure, and involving 137 objects. 3) Diverse environments. We arranged 772 environments which involve 165 object classes and 1,009 corresponding prefabs. Powered by this challenging dataset and to highlight the task challenges, we further provide a baseline model, a multi-modal task planner, to evaluate its performance within the aspect of reasoning and generalization. The dataset and evaluation results are publicly available, and we hope EMIF-Bench can serve as a benchmark platform that inspires future research in embodied agents. All the code and data for EMIF-Bench is available at: https://***/qyx1121/EMIF-Bench. © 2024 IEEE.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Portability and Scalability of OpenMP Offloading on State-of-the-Art Accelerators 38th

Portability and Scalability of OpenMP Offloading on State...

引用

38th International conference on high performance Computing, ISC high performance 2023

作者： Fridman, Yehonatan Tamir, Guy Oren, Gal Department of Computer Science Ben-Gurion University of the Negev Be’er Sheva Israel Department of Physics Nuclear Research Center - Negev Be’er Sheva Israel Scientific Computing Center Nuclear Research Center - Negev Be’er Sheva Israel Intel Corporation Santa Clara United States Department of Computer Science Technion - Israel Institute of Technology Haifa Israel

ISBN: (纸本)9783031408427

Over the last decade, most of the increase in computing power has been gained by advances in accelerated many-core architectures, mainly in the form of GPGPUs. While accelerators achieve phenomenal performances in various computing tasks, their utilization requires code adaptations and transformations. Thus, OpenMP, the most common standard for multi-threading in scientific computing applications, introduced offloading capabilities between host (CPUs) and accelerators since v4.0, with increasing support in the successive v4.5, v5.0, v5.1, and the latest v5.2 versions. Recently, two state-of-the-art GPUs – the Intel Ponte Vecchio Max 1100 and the NVIDIA A100 GPUs – were released to the market, with the oneAPI and NVHPC compilers for offloading, correspondingly. In this work, we present early performance results of OpenMP offloading capabilities to these devices while specifically analyzing the portability of advanced directives (using SOLLVE’s OMPVV test suite) and the scalability of the hardware in representative scientific mini-app (the LULESH benchmark). Our results show that the coverage for version 4.5 is nearly complete in both latest NVHPC and oneAPI tools. However, we observed a lack of support in versions 5.0, 5.1, and 5.2, which is particularly noticeable when using NVHPC. From the performance perspective, we found that the PVC1100 and A100 are relatively comparable on the LULESH benchmark. While the A100 is slightly better due to faster memory bandwidth, the PVC1100 reaches the next problem size (4003 ) scalably due to the larger memory size. The results are available at: https://***/Scientific-Computing-Lab-NRCN/Accel-OpenMP-Portability-Scalability. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

TopKmer: Parallel high Frequency K-mer Counting on Distributed Memory 19th

TopKmer: Parallel High Frequency K-mer Counting on Distribut...

引用

19th International conference on Network and Parallel Computing (NPC)

作者： Li Mocheng Chen Zhiguang Xiao Nong Liu Yang Luo Xi Chen Tao Natl Univ Def Technol Coll Comp Inst Quantum Informat Changsha Peoples R China Natl Univ Def Technol Coll Comp State Key Lab High Performance Comp Changsha Peoples R China Sun Yat Sen Univ Sch Comp Guangzhou Peoples R China Shenzhen 2 Vocat & Tech Sch Automot Dept Shenzhen Peoples R China Beijing Inst Life Beijing Proteome Res Ctr State Key Lab Prote Natl Ctr Prot Sci Beijing Beijing Peoples R China

ISBN: (纸本)9783031213946;9783031213953

high-throughput DNA sequencing is a crucial technology for genomics research. As genetic data grows to hundreds of gigabytes or even terabytes that traditional devices cannot support, high-performance computing plays an important role. However, current high-performance approaches to extracting k-mers cost a large memory footprint due to the high error rate of short-read sequences. This paper proposes Top-Kmer, a parallel k-mer counting workflow that indexes high-frequency k-mers within a tiny counting structure. On the 2048 cores of Tianhe-2, we construct k-mer index tables in 18 s for 174 GB fastq files and complete queries in 1 s for 1 billion k-mers, with a scaling efficiency of 95%. Compared with the state of the art, the counting table's memory usage is reduced by 50% with no performance degradation.

关键词： k-mer counting Distributed hash table Space saving algorithm high scalability Hybrid parallel

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Compensated Gram-Schmidt Algorithm 24

Design and Implementation of Compensated Gram-Schmidt Algori...

引用

24th IEEE International conference on high performance Computing and Communications, 8th IEEE International conference on Data Science and Systems, 20th IEEE International conference on Smart City and 8th IEEE International conference on Dependability in Sensor, Cloud and Big Data Systems and Application, HPCC/DSS/SmartCity/DependSys 2022

作者： Jin, Jiexi Xie, Hehu Du, Peibing Quan, Zhe Jiang, Hao College of Computer Science and Electronic Engineering Hunan University Changsha China Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing China Northwest Insititute of Nuclear Technology Xian China College of Computer Science and Technology National University of Defense Technology Changsha China

ISBN: (纸本)9798350319934

Due to the cumulative effect of rounding errors, the Gram-Schmidt orthogonalization algorithm and its variants often exhibit numerical instability phenomena. Therefore, we analyze the data dependencies of the Modified Gram-Schmidt algorithm (MGS), and propose the compensated MGS algorithm (CompMGS) based on the idea of error-free transformation (EFT) technology and compensated algorithms. The theoretical analysis demonstrates that our algorithm has O(u) loss of orthogonality(in double working precision, u=10-16) with the relaxed conditions (κ2(A) © 2022 IEEE.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Shuttle Bus Scheduling Optimization Based on Spatio-Temporal Networks

Shuttle Bus Scheduling Optimization Based on Spatio-Temporal...

引用

International conference on SmartRail, Traffic, and Transportation Engineering, ICSTTE 2023

作者： Yao, Yuhan Chen, Zhibin Division of Engineering and Computer Science NYU Shanghai Shanghai China

ISBN: (纸本)9789819736812

Many universities, companies, hospitals, and government agencies provide shuttle bus services for their staff’s daily commute. Given that the routes of these shuttle buses are fixed, how to optimize the shuttle bus schedule, i.e., timetable, to reduce the operation costs while maintaining high service satisfaction becomes the biggest challenge facing the shuttle manager. To this end, a spatio-temporal network is first proposed to describe the possible work schedule of shuttle buses. Based on the established network, a mathematical program with an implicit objective function is developed to optimize the shuttle bus schedule. A tailored genetic algorithm is presented and implemented to solve the proposed model efficiently. A numerical example based on the shuttle bus and demand data of New York University Shanghai is presented to illustrate the performance of the proposed model and algorithm. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

HandS3C: 3D Hand Mesh Reconstruction with State Space Spatial Channel Attention from RGB images

HandS3C: 3D Hand Mesh Reconstruction with State Space Spatia...

引用

2025 IEEE International conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Jiao, Zixun Wang, Xihan Xia, Zhaoqiang Shao, Lianhe Gao, Quanli Xi'an Polytechnic University Xi'an China Northwestern Polytechnical University Xi'an China

ISBN: (纸本)9798350368741

Reconstructing the hand mesh from one single RGB image is a challenging task because hands are often occluded by other objects. Most previous works attempt to explore more additional information and adopt attention mechanisms for improving 3D reconstruction performance, while it would increase computational complexity simultaneously. To achieve a performance preserving architecture with high computational efficiency, in this work, we propose a simple but effective 3D hand mesh reconstruction network (i.e., HandS3C), which is the first time to incorporate state space model into the task of hand mesh reconstruction. In the network, we design a novel state-space spatial-channel attention module that extends the effective receptive field, extracts hand features in the spatial dimension, and enhances regional features of hands in the channel dimension. This helps to reconstruct a complete and detailed hand mesh. Extensive experiments conducted on well-known datasets facing heavy occlusions (such as FREIHAND, DEXYCB, and HO3D) demonstrate that our proposed HandS3C achieves state-of-the-art performance while maintaining minimal parameters. Code can be available in https://***/JiaoZixun/HandS3C. © 2025 IEEE.

关键词： 3D Hand Mesh Reconstruction Deep Learning Effective Receptive Field Human-computer Interaction State Space Model

来源：评论

学校读者我要写书评

暂无评论

Intelligent Maintenance System for Wind Turbine Based on Deep Belief Federated Learning 25

Intelligent Maintenance System for Wind Turbine Based on Dee...

引用

25th IEEE International conferences on high performance Computing and Communications, 9th International conference on Data Science and Systems, 21st IEEE International conference on Smart City and 9th IEEE International conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC/DSS/SmartCity/DependSys 2023

作者： Xie, Hu Tao, Jie Yang, Dalian Chen, Hewen Li, Zhiying Yin, Shilei School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China Hunan University of Science and Technology Key Laboratory of Mechanical Equipment Health Maintenance Xiangtan China

ISBN: (纸本)9798350330014

Federated learning can complete multi-party collaborative training without exchanging local data, effectively solving the problem of data privacy protection in the wind power field. However, when facing non independent and identically distributed industrial data, the local model updates may cause global model drift. In response to the above issues, this article applies deep belief network to build federated learning mechanism and proposes a dynamic federated weighted learning method under non independent wind power big data. This method utilizes the federated distance algorithm to eliminate the influence of local models with excessive offset. Then use dynamic weighting algorithm to optimize the weight of local models with high contribution. This method not only solves the global offset problem caused by local updates, but also considers the impact of local important models on the global model. The experiments are conducted on three wind farms, namely Nanshan, Zhurihe, and Chuanshan, with the same type of 1.5 MW wind turbines. The results show that the method proposed in this paper can achieve higher accuracy and good generalization ability in the global model. © 2023 IEEE.

关键词： Wind power

来源：评论

学校读者我要写书评

暂无评论

Synthesis-Embedded Verification 8

Synthesis-Embedded Verification

引用

8th South-East Europe Design Automation, computer Engineering, computer Networks and Social Media conference, SEEDA-CECNSM 2023

作者： Dossis, Michael University of Western Macedonia Dept. of Computer Science Kastoria Greece

ISBN: (纸本)9798350383676

The proliferation of computing systems and subsystems combined with the need for high performance, product security and low energy have forced the development of tools that generate hardware systems and hardware components automatically from higher-level of algorithmic descriptions. The technology background behind this phenomenon is called high-Level Synthesis (HLS) and it has been an active research topic for at least the last 3 decades. HLS hasn't been established as a de facto design approach in industry because of problems with the quality of the generated hardware descriptions and the lack of complete automation and compatibility with all the programming constructs that sometimes require manual rewriting of the whole module in order for the HLS tool to be able to process it. One greater problem is that often the available HLS tools generate bugs in the generated hardware which are difficult to trace and correct, as the generated architecture usually contains hundreds of FSM states. Moreover, verification tasks and flows which are disjoint from the synthesis flows often fails to find all bugs and it is difficult to learn and run easy as in the case of formal verification. Here, we discuss a unique verification strategy that it is integrated in the synthesis flow and it doesn't require any verification skills at all, but only how to compile and run C programs, which are driven by run-time options activated by keystrokes. Moreover, because the verified model is the same as this of the synthesis process, it reassures that the verified module is exactly the same as the generated hardware, so the same regression tests can run as in the high-level specification C/Ada program model. The generated cycle accurate simulators are C programs that model the execution of the formal synthesized FSMs. Because of the synthesis transformation formal model with logic inference that we use, the whole synthesis/verification flow of our approach is formal. © 2023 IEEE.

关键词： Formal verification

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共500页 << < 74 75 76 77 78 79 80 81 82 83 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：