检索结果-内蒙古大学图书馆

IEEE International Conference on Industrial Informatics (INDIN)

作者： Weipeng Cao Xuyang Yao Zhiwu Xu Yinghui Pan Yixuan Sun Dachuan Li Bohua Qiu Muheng Wei Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen) Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Stony Brook University New York United States Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China ZhenDui Industry Artificial Intelligence Co. Ltd Shenzhen China Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China

ISBN: (数字)9798331527471

ISBN: (纸本)9798331527488

Realizing Generalized Zero-Shot Learning (GZSL) based on large models is emerging as a prevailing trend. However, most existing methods merely regard large models as black boxes, solely leveraging the features output by the final layer while disregarding potential performance enhancements from other layers. Indeed, numerous researchers have visually depicted variations in the features learned across different layers of neural networks. Motivated by this observation, we propose a Vision Transformer (ViT)-based GZSL method named Depth-Aware Multi-Modal ViT (DAM2ViT), which exploits multi-level features of ViT. DAM2ViT incorporates a multi-modal interaction block to align semantic information of categories across multiple layers, thereby augmenting the model's capacity to learn associations between visual and semantic spaces. Extensive experiments conducted on three benchmark datasets (i.e., CUB, SUN, AWA2) have showcased that DAM2ViT achieves competitive results compared to state-of-the-art methods.

关键词： Visualization Adaptation models Semantics Zero shot learning Neural networks Termination of employment Transformers Market research Sun Optimization

来源：评论

学校读者我要写书评

暂无评论

Offsite Evaluation of Localization systems: Criteria, systems, and Results From IPIN 2021 and 2022 Competitions

IEEE Journal on Indoor and Seamless Positioning and Navigati...

引用

IEEE Journal on Indoor and Seamless Positioning and Navigation 2024年 2卷 92-129页

作者： Potorti, Francesco Crivello, Antonino Lee, Soyeon Vladimirov, Blagovest Park, Sangjoon Chen, Yushi Wang, Long Chen, Runze Zhao, Fang Zhuge, Yue Luo, Haiyong Perez-Navarro, Antoni Jimenez, Antonio R. Wang, Han Liang, Hengyi De Cock, Cedric Plets, David Cui, Yan Xiong, Zhi Li, Xiaodong Ding, Yiming Franco, Fernando Javier Alvarez Polo, Fernando Jesus Aranda Rodriguez, Felipe Parralejo Moreira, Adriano Pendao, Cristiano Silva, Ivo Ortiz, Miguel Zhu, Ni Li, Ziyou Renaudin, Valerie Wei, Dongyan Ji, Xinchun Zhang, Wenchao Wang, Yan Ding, Longyang Kuang, Jian Zhang, Xiaobing Dou, Zhi Yang, Chaoqun Kram, Sebastian Stahlke, Maximilian Mutschler, Christopher Coene, Sander Li, Chenglong Venus, Alexander Leitinger, Erik Tertinek, Stefan Witrisal, Klaus Wang, Yi Wang, Shaobo Jin, Beihong Zhang, Fusang Su, Chang Wang, Zhi Li, Siheng Li, Xiaodong Li, Shitao Pan, Mengguan Zheng, Wang Luo, Kai Ma, Ziyao Gao, Yanbiao Chang, Jiaxing Ren, Hailong Guo, Wenfang Torres-Sospedra, Joaquin Pisa56124 Italy Electronics and Telecommunications Research Institute Daejeon34129 Korea Republic of Beijing University of Posts and Telecommunications School of Computer Science National Pilot Software Engineering School Beijing100876 China Chinese Academy of Sciences Beijing Key Laboratory of Mobile Computing and Pervasive Device Institute of Computing Technology Beijing100190 China Universitat Oberta de Catalunya Faculty of Computer Sciences Multimedia and Telecommunication Barcelona08035 Spain Arganda del Rey28500 Spain Huawei Technologies Company Ltd. Shenzhen100015 China IMEC-WAVES/Ghent University Department of Information Technology Gent9052 Belgium Nanjing University of Aeronautics and Astronautics College of Automation Nanjing210016 China University of Extremadura Badajoz06006 Spain University of Trás-os-Montes and Alto Douro Department of Engineering School of Sciences and Technology Vila Real5000-801 Portugal Universidade Do Minho Centro Algoritmi Guimarães4800-058 Portugal Ame Department of the University Gustave Eiffel Geoloc Laboratory Bouguenais44344 France Chinese Academy of Sciences Aerospace Information Research Institute Beijing100094 China Wuhan University Gnss Research Center Wuhan430072 China AutoNavi Software Company Ltd. China Fraunhofer Institute for Integrated Circuits Iis Fraunhofer Iis Nuremberg90411 Germany Erlangen91058 Germany Graz University of Technology Christian Doppler Laboratory for Location-Aware Electronic Systems Graz8010 Austria Institute of Software Chinese Academy of Sciences Beijing100190 China Purple Mountain Laboratories Pervasive Communication Research Center Nanjing210000 China Beijing University of Posts and Telecommunications Beijing100876 China

Indoor positioning is a thriving research area, which is slowly gaining market momentum. Its applications are mostly customized, ad hoc installations;ubiquitous applications analogous to Global Navigation Satellite System for outdoors are not available because of the lack of generic platforms, widely accepted standards and interoperability protocols. In this context, the indoor positioning and indoor navigation (IPIN) competition is the only long-term, technically sound initiative to monitor the state of the art of real systems by measuring their performance in a realistic environment. Most competing systems are pedestrian-oriented and based on the use of smartphones, but several competing tracks were set up, enabling comparison of an array of technologies. The two IPIN competitions described here include only off-site tracks. In contrast with on-site tracks where competitors bring their systems on-site - which were impossible to organize during 2021 and 2022 - in off-site tracks competitors download prerecorded data from multiple sensors and process them using the EvaalAPI, a real-time, web-based emulation interface. As usual with IPIN competitions, tracks were compliant with the EvAAL framework, ensuring consistency of the measurement procedure and reliability of results. The main contribution of this work is to show a compilation of possible indoor positioning scenarios and different indoor positioning solutions to the same problem. © 2023 CCBY.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

A reinforcement-learning-based energy-efficient framework for multi-task video analytics pipeline

arXiv

引用

arXiv 2021年

作者： Zhao, Yingying Dong, Mingzhi Wang, Yujiang Feng, Da Lv, Qin Dick, Robert P. Li, Dongsheng Lu, Tun Gu, Ning Shang, Li School of Computer Science Fudan University Shanghai China Shanghai Key Laboratory of Data Science Fudan University Shanghai China Shanghai Institute of Intelligent Electronics & Systems Shanghai China Department of Computing Imperial College London London United Kingdom Software Service Company Limited Beijing China University of Colorado Boulder BoulderCO United States Department of Electrical Engineering and Computer Science College of Engineering University of Michigan Ann ArborMI United States Microsoft Research Asia Shanghai China School of Computer Science Fudan University Shanghai China

Deep-learning-based video processing has yielded transformative results in recent years. However, the video analytics pipeline is energy-intensive due to high data rates and reliance on complex inference algorithms, which limits its adoption in energy-constrained applications. Motivated by the observation of high and variable spatial redundancy and temporal dynamics in video data streams, we design and evaluate an adaptive-resolution optimization framework to minimize the energy use of multitask video analytics pipelines. Instead of heuristically tuning the input data resolution of individual tasks, our framework utilizes deep reinforcement learning to dynamically govern the input resolution and computation of the entire video analytics pipeline. By monitoring the impact of varying resolution on the quality of high-dimensional video analytics features, hence the accuracy of video analytics results, the proposed end-to-end optimization framework learns the best non-myopic policy for dynamically controlling the resolution of input video streams to globally optimize energy efficiency. Governed by reinforcement learning, optical flow is incorporated into the framework to minimize unnecessary spatio-temporal redundancy that leads to re-computation, while preserving accuracy. The proposed framework is applied to video instance segmentation which is one of the most challenging computer vision tasks, and achieves better energy efficiency than all baseline methods of similar accuracy on the YouTube-VIS dataset. Copyright © 2021, The Authors. All rights reserved.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

ADVANCES IN LONG-RANGE, HIGH-SPEED OPTICAL COMMUNICATION

引用

NAVAL ENGINEERS JOURNAL 1981年第4期93卷 39-48页

作者： BARTON, GG FELDMAN, S Mr. Sidney Feldman formerly with the Naval Applied Science Laboratory is presently with the Radiation Division of the Naval Surface Weapons Center White Oak Silver Spring Maryland. He planned and supervised laboratory experiments of many optical systems for fleet evaluation several of his designs now being standard in the fleet. He received his BA degree in Physics from Brooklyn College in 1941 and majored in Physics at the Brooklyn Polytechnic Institute. His professional memberships include the Optical Society of America American Association for the Advancement of Science and The Scientific Research Society of North America. He was the recipient of the Naval Ordnance Development Award in 1945 the Superior Achievement Award in 1957 the Quality Salary Increase Award in 1965 the Superior Accomplishment Award in 1967 1970 and 1979. Additionally he has been granted patents for a relamping tool for searchlights (1962) a lamp positioning mechanism for searchlights (1963) a daylnight digital sextant (1973) a portable sextant-computer system (1974) and with Mr. George Barton the remote-controlled LLLTV camera-sextant (1976) the automatic passive LLLTV-rangefinder (1977) and a patent disclosure for the omnidirectional transceiver (1980). Mr. George G. Barton has been employed by the Naval Research Laboratory Washington D. C. for the past ten years in the scientific and military application design engineering and fabrication of low light level TV camera systems. He was previously associated with the Smithsonian Institution and Northwestern University in the application of TV technology in astronomical investigations. He attended New York University Newark College of Engineering and New Mexico State University where he majored in Physical Optics. Presently he is with his own company BISMARC Inc. Harker's Island N.C. where he is involved principally in the design manufacture and marketing of sonar systems such as the unique VIDISEA fishscope research and development in electrooptic systems an

During periods of radio silence under Emission Control, communication depends on the slow ship-to-ship, manual-visual, 8-10 wpm Morse code signaling shutter searchlight employing the ac 1000-watt incandescent or the ac 1000-watt compact arc mercury-xenon lamp. These sources can be replaced by the dc compact arc xenon lamp to provide longer daylight ranges and highspeed (100 wpm teletype, 150 wpm Morse code, voice, etc.) communication since this source has superior brightness and the facility of considerably more rapid modulation. The excessive weight and size of the ac-dc power convertor and modulating circuitry which had prevented use of the dc xenon lamp have been overcome by developments in solid state electronics such as the rapid, high current, simmer-flash, 100 to one light output xenon lamp pulsing using the reliable, uncomplicated, low-cost silicon controlled rectifier shunt switch which could eliminate the mechanical signaling shutter. laboratory and sea evaluations have proved the feasibility of and provided the long daylight high-speed optical communication ranges that could be attained from operation of the dc 1000-watt and 2200-watt xenon lamps at the focus of 12-inch, 18-inch searchlights and in the Fresnel lens omni-directional beacon which a command ship uses to signal all ships in a task force at once. With these advances, optical communication provides the highspeed capability of radio communication, particularly, also, with the new omnidirectional transceiver.

关键词： SHIPS

来源：评论

学校读者我要写书评

暂无评论

The RTES project - BTeV, and beyond

The RTES project - BTeV, and beyond

引用

IEEE NPSS Conference on Real Time

作者： M.J. Haney S. Ahuja G. Bapty H. Cheung Z. Kalbarczyk A. Khanna J. Kowalkowski D. Messie D. Mosse S. Neema S. Nordstrom Jae Oh P. Sheldon S. Shetty D. Volper Long Wang Di Yao High Energy Physics University of Illinois Urbana IL USA Institute for Software Integrated Systems Vanderbilt University Nashville TN USA Fenni National Accelerator Laboratory Batavia IL USA Electrical and Computer Science University of Illinois Urbana IL USA Electrical Engineering and Computer Science Syracuse University Syracuse NY USA Computer Science University of Pittsburgh Pittsburgh PA USA Physics and Astronomy Department Vanderbilt University Nashville TN USA

The real time embedded systems (RTES) project was created to study the design and implementation of high-performance, heterogeneous, and fault-adaptive real time embedded systems. The driving application for this research was the proposed BTeV high energy physics experiment, which called for large farms of embedded computational elements (DSPs), as well as a large farm of conventional high-performance processors to implement its Level 1 and Level 2/3 triggers. At the time of BTeV's termination early in 2005, the RTES project was within days of completing a prototype implementation for providing a reliable and fault-adaptive infrastructure to the L2/3 farm; a prototype for the L1 farm had been completed in 2003. This paper documents the conclusion of the RTES focus on BTeV, and provides an evaluation of the applicability of the RTES concepts to other systems

关键词： USA Councils Real time systems Physics computing Runtime computer science Embedded system Domain specific languages Embedded computing Prototypes Fault detection

来源：评论

学校读者我要写书评

暂无评论

Gaussian Mixture PHD Smoother for Jump Markov Models in Multiple Maneuvering Targets Tracking

Gaussian Mixture PHD Smoother for Jump Markov Models in Mult...

引用

2011 American Control Conference (ACC)

作者： Wenling Li Yingmin Jia Junping Du Fashan Yu Seventh Research Division and the Department of Systems and Control Beihang University Beijing China Key Laboratory of Mathematics Informatics and Behavioral Semantics (LMIB) Ministry of Education SMSS Beihang University Beijing China Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia School of Computer Science and Technology Beijing University of Posts and Telecommunications Beijing China School of Electrical Engineering and Automation Henan Polytechnic University Jiaozuo Henan China

This paper presents a Gaussian mixture probability hypothesis density (GM-PHD) smoother for tracking multiple maneuvering targets that follow jump Markov models. Unlike the generalization of the multiple model GM-PHD filters, our aim is to approximate the dynamics of the linear Gaussian jump Markov system (LGJMS) by a best-fitting Gaussian (BFG) distribution so that the GM-PHD smoother can be carried out with respect to an approximated linear Gaussian system. Our approach is inspired by the recognition that the BFG approximation provides an accurate performance measure for the LGJMS. Furthermore, the multiple model estimation is avoided and less computational cost is required. The effectiveness of the proposed smoother is verified with a numerical simulation.

关键词： Target tracking Approximation methods Markov processes Covariance matrix Smoothing methods Radar tracking Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Adaptive Iterative Learning Control for Uncertain Delay systems Based on Model Matching Technique

Adaptive Iterative Learning Control for Uncertain Delay Syst...

引用

2011 American Control Conference (ACC)

作者： Haixia Su Yingmin Jia Junping Du Fashan Yu Seventh Research Division and the Department of Systems and Control Beihang University Beijing China Key Laboratory of Mathematics Informatics and Behavioral Semantics (LMIB) Ministry of Education SMSS Beihang University Beijing China Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia School of Computer Science and Technology Beijing University of Posts and Telecommunications Beijing China School of Electrical Engineering and Automation Henan Polytechnic University Jiaozuo Henan China

In this paper, an adaptive iterative learning control (ILC) scheme is proposed for trajectory tracking of uncertain delay systems based on model matching technique. The reference model is a delay system operating over in a finite time interval. An iterative model matching controller is designed and an iteration domain adaptive law is chosen to estimate the unknown parameters. It shows that the model matching technique can be applied in a straightforward method to ILC problem. A simulation example is included to illustrate the designed scheme.

关键词： Adaptation models Polynomials Adaptive systems Delay effects Delay systems

来源：评论

学校读者我要写书评

暂无评论

SEMICON: A Learning-to-hash Solution for Large-scale Fine-grained Image Retrieval

arXiv

引用

arXiv 2022年

作者： Shen, Yang Sun, Xuhao Wei, Xiu-Shen Jiang, Qing-Yuan Yang, Jian School of Computer Science and Engineering Nanjing University of Science and Technology China State Key Laboratory of Integrated Services Networks Xidian University China State Key Laboratory for Novel Software Technology Nanjing University China Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security Nanjing University of Science and Technology China

In this paper, we propose Suppression-Enhancing Mask based attention and Interactive Channel transformatiON (SEMICON) to learn binary hash codes for dealing with large-scale fine-grained image retrieval tasks. In SEMICON, we first develop a suppression-enhancing mask (SEM) based attention to dynamically localize discriminative image regions. More importantly, different from existing attention mechanism simply erasing previous discriminative regions, our SEM is developed to restrain such regions and then discover other complementary regions by considering the relation between activated regions in a stage-by-stage fashion. In each stage, the interactive channel transformation (ICON) module is afterwards designed to exploit correlations across channels of attended activation tensors. Since channels could generally correspond to the parts of fine-grained objects, the part correlation can be also modeled accordingly, which further improves fine-grained retrieval accuracy. Moreover, to be computational economy, ICON is realized by an efficient two-step process. Finally, the hash learning of our SEMICON consists of both global- and local-level branches for better representing fine-grained objects and then generating binary hash codes explicitly corresponding to multiple levels. Experiments on five benchmark fine-grained datasets show our superiority over competing methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Image retrieval

来源：评论

学校读者我要写书评

暂无评论

Multi-error-correcting amplitude damping codes

Multi-error-correcting amplitude damping codes

引用

IEEE International Symposium on Information Theory

作者： Runyao Duan Markus Grassl Zhengfeng Ji Bei Zeng State Key Laboratory of Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and Technology Department of Computer Science and Technology Tsinghua University Beijing China Centre for Quantum Computation and Intelligent Systems (QCIS) Faculty of Engineering and Information Technology University of Technology Sydney NSW Australia Centre for Quantum Technologies National University of Singapore Singapore Perimeter Institute of Theoretical Physics Waterloo ONT Canada State Key Laboratory of Computer Science Institute of Software Chinese Academy and Sciences Beijing China Institute for Quantum Computing and the Department of Combinatorics and Optimization University of Waterloo Waterloo ONT Canada

ISBN: (纸本)9781424478903

We construct new families of multi-error-correcting quantum codes for the amplitude damping channel. Our key observation is that, with proper encoding, two uses of the amplitude damping channel simulate a quantum erasure channel. This allows us to use concatenated codes with quantum erasure-correcting codes as outer codes for correcting multiple amplitude damping errors. Our new codes are degenerate stabilizer codes and have parameters which are better than the amplitude damping codes obtained by any previously known construction.

关键词： Damping Quantum mechanics Quantum computing Error correction codes Noise level Laboratories Phase noise Physics computing Intelligent systems computer science

来源：评论

学校读者我要写书评

暂无评论

Random asynchronous iterations in distributed coordination algorithms

arXiv

引用

arXiv 2018年

作者： Chen, Yao Xia, Weiguo Cao, Ming Lü, Jinhu Department of Computer Science Southwestern University of Finance and Economics Chengdu611130 China School of Control Science and Engineering Dalian University of Technology Dalian116024 China Faculty of Science and Engineering ENTEG University of Groningen Groningen9747 AG Netherlands School of Automation Science and Electrical Engineering State Key Laboratory of Software Development Environment Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China

Distributed coordination algorithms (DCA) carry out information processing processes among a group of networked agents without centralized information fusion. Though it is well known that DCA characterized by an SIA (stochastic, indecomposable, aperiodic) matrix generate consensus asymptotically via synchronous iterations, the dynamics of DCA with asynchronous iterations have not been studied extensively, especially when viewed as stochastic processes. This paper aims to show that for any given irreducible stochastic matrix, even non-SIA, the corresponding DCA lead to consensus successfully via random asynchronous iterations under a wide range of conditions on the transition probability. Particularly, the transition probability is neither required to be independent and identically distributed, nor characterized by a Markov chain. Copyright © 2018, The Authors. All rights reserved.

关键词： Stochastic systems

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：