检索结果-内蒙古大学图书馆

TECMH:Transformer-Based Cross-Modal Hashing For Fine-Grained Image-Text Retrieval

computers, Materials & Continua 2023年第5期75卷 3713-3728页

作者： Qiqi Li Longfei Ma Zheng Jiang Mingyong Li Bo Jin College of Computer and Information Science Chongqing Normal UniversityChongqing401331China Institute of Systems and Robotics(ISR) Department of Electrical and Computer Engineering(DEEC)University of CoimbraCoimbraPortugal

In recent years,cross-modal hash retrieval has become a popular research field because of its advantages of high efficiency and low ***-modal retrieval technology can be applied to search engines,crossmodalmedical processing,*** existing main method is to use amulti-label matching paradigm to finish the retrieval ***,such methods do not use fine-grained information in the multi-modal data,which may lead to suboptimal *** avoid cross-modal matching turning into label matching,this paper proposes an end-to-end fine-grained cross-modal hash retrieval method,which can focus more on the fine-grained semantic information of multi-modal ***,the method refines the image features and no longer uses multiple labels to represent text features but uses BERT for ***,this method uses the inference capabilities of the transformer encoder to generate global fine-grained ***,in order to better judge the effect of the fine-grained model,this paper uses the datasets in the image text matching field instead of the traditional label-matching *** article experiment on Microsoft COCO(MS-COCO)and Flickr30K datasets and compare it with the previous *** experimental results show that this method can obtain more advanced results in the cross-modal hash retrieval field.

关键词： Deep learning cross-modal retrieval hash learning transformer

来源：评论

学校读者我要写书评

暂无评论

Stereo parallel tracking and mapping for robot localization

Stereo parallel tracking and mapping for robot localization

引用

IEEE/RSJ International Conference on Intelligent Robots and systems, IROS 2015

作者： Pire, Taihu Fischer, Thomas Civera, Javier De Cristoforis, Pablo Berlles, Julio Jacobo Computer Science Department University of Buenos Aires Argentina Robotics Perception and Real-Time Group University of Zaragoza Spain

ISBN: (纸本)9781479999941

This paper describes a visual SLAM system based on stereo cameras and focused on real-time localization for mobile robots. To achieve this, it heavily exploits the parallel nature of the SLAM problem, separating the time-constrained pose estimation from less pressing matters such as map building and refinement tasks. On the other hand, the stereo setting allows to reconstruct a metric 3D map for each frame of stereo images, improving the accuracy of the mapping process with respect to monocular SLAM and avoiding the well-known bootstrapping problem. Also, the real scale of the environment is an essential feature for robots which have to interact with their surrounding workspace. A series of experiments, on-line on a robot as well as off-line with public datasets, are performed to validate the accuracy and real-time performance of the developed method. © 2015 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Evaluating design trade-offs in customizable processors 09

Evaluating design trade-offs in customizable processors

引用

2009 46th ACM/IEEE Design Automation Conference, DAC 2009

作者： Bordoloi, Unmesh D. Huynh, Phung Huynh Chakraborty, Samarjit Mitra, Tulika Verimag Labs. France Department of Computer Science National University of Singapore Singapore Institute for Real-Time Computer Systems TU Munich Germany

ISBN: (纸本)9781605584973

The short time-to-market window for embedded systems demands automation of design methodologies for customizable processors. Recent research advances in this direction have mostly focused on single criteria optimization, e.g., optimizing performance though custom instructions under pre-defined area constraint. From the designer's perspective, however, it would be more interesting if the conflicting trade-offs among multiple objectives (e.g., performance versus area) are exposed enabling an informed decision making. Unfortunately, identifying the optimal trade-off points turns out to be computationally intractable. In this paper, we present a polynomial-time approximation algorithm to systematically evaluate the design trade-offs. In particular, we explore performance-area trade-offs in the context of multi-tasking real-time embedded applications to be implemented on a customizable processor. Copyright 2009 ACM.

关键词： Embedded systems

来源：评论

学校读者我要写书评

暂无评论

Joint Design of Radar Receive Filter and Unimodular ISAC Waveform with Sidelobe Level Control

arXiv

引用

arXiv 2025年

作者： Zhang, Kecheng Liu, Ya-Feng Wang, Zhongbin Yuan, Weijie Keskin, Musa Furkan Wymeersch, Henk Xia, Shuqiang School of System Design and Intelligent Manufacturing The Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology Shenzhen518055 China State Key Laboratory of Scientific and Engineering Computing Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China Department of Electrical Engineering Chalmers University of Technology Gothenburg41296 Sweden ZTE Corporation The State Key Laboratory of Mobile Network and Mobile Multimedia Technology Shenzhen518055 China

Integrated sensing and communication (ISAC) has been considered a key feature of next-generation wireless networks. This paper investigates the joint design of the radar receive filter and dual-functional transmit waveform for the multiple-input multiple-output (MIMO) ISAC system. While optimizing the mean square error (MSE) of the radar receive spatial response and maximizing the achievable rate at the communication receiver, besides the constraints of full-power radar receiving filter and unimodular transmit sequence, we control the maximum range sidelobe level, which is often overlooked in existing ISAC waveform design literature, for better radar imaging performance. To solve the formulated optimization problem with convex and nonconvex constraints, we propose an inexact augmented Lagrangian method (ALM) algorithm. For each subproblem in the proposed inexact ALM algorithm, we custom-design a block successive upper-bound minimization (BSUM) scheme with closed-form solutions for all blocks of variable to enhance the computational efficiency. Convergence analysis shows that the proposed algorithm is guaranteed to provide a stationary and feasible solution. Extensive simulations are performed to investigate the impact of different system parameters on communication and radar imaging performance. Comparison with the existing works shows the superiority of the proposed algorithm. © 2025, CC BY-NC-SA.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Characterizing feedback signal drop patterns in formal verification of networked control systems

Characterizing feedback signal drop patterns in formal verif...

引用

2013 IEEE Conference on computer Aided Control System Design, CACSD 2013

作者： Goswami, Dip Chakraborty, Samarjit Bhaduri, Purandar Mitter, Sanjoy K. Institute for Real-Time Computer Systems TU Munich Germany Department of Computer Science and Engineering IIT Guwahati India Laboratory for Information and Decision Systems MIT United States

ISBN: (纸本)9781479915651

In order to obtain resource efficient implementations of control loops on embedded platforms, recently there has been a renewed interest in studying stability and various other quality-of-control (QoC) metrics in the presence of control message drops. Towards this, different methods have been proposed to quantify the impact of message drops on stability and control performance. In this paper we will survey these techniques and clarify the relationship between them. Given a drop pattern that satisfies stability and specified QoC constraints, it is important to check whether an implementation platform satisfies this pattern. In other words, whether the control loop in question may be implemented on this platform. Given an architecture, we will also show how certain notions of expressing drop patterns are easier to verify compared to others. © 2013 IEEE.

关键词： Drops

来源：评论

学校读者我要写书评

暂无评论

Generalized Norm Optimal Iterative Learning Control with Intermediate Point and Sub-interval Tracking

引用

International Journal of Automation and computing 2015年第3期12卷 243-253页

作者： David H.Owens Chris T.Freeman Bing Chu Department of Automatic Control and Systems Engineering University of Sheffield School of Electronics and Computer Science University of Southampton Advanced Robotics Division Italian Institute of Technology

Norm optimal iterative learning control(NOILC) has recently been applied to iterative learning control(ILC) problems in which tracking is only required at a subset of isolated time points along the trial duration. This problem addresses the practical needs of many applications, including industrial automation, crane control, satellite positioning and motion control within a medical stroke rehabilitation context. This paper provides a substantial generalization of this framework by providing a solution to the problem of convergence at intermediate points with simultaneous tracking of subsets of outputs to reference trajectories on subintervals. This formulation enables the NOILC paradigm to tackle tasks which mix "point to point" movements with linear tracking requirements and hence substantially broadens the application domain to include automation tasks which include welding or cutting movements, or human motion control where the movement is restricted by the task to straight line and/or planar segments. A solution to the problem is presented in the framework of NOILC and inherits NOILC s well-defined convergence properties. Design guidelines and supporting experimental results are included.

关键词： Iterative learning control learning control optimization linear systems robotics.

来源：评论

学校读者我要写书评

暂无评论

Model-based diagnosis of complex systems: Structuring and temporal reasoning

引用

IFAC Proceedings Volumes 1991年第10期24卷 41-45页

作者： T. Hübner Institute for Real Time Computer Systems and Robotics Faculty of Computer Science University of Karlsruhe Karlsruhe Germany

Model-based diagnosis of industrial applications (i.e., complex systems) has to face a lot of problems inherent in complexity. Most applications involve thousands of components and are dynamic. The approach outlined in this paper is based on semantic nets representing causal and temporal knowledge to be used for fault diagnosis. A view and a hierarchy-concept serve for structured modelling and focused diagnosis. An efficient diagnostic inference mechanism is based on a pre-computation phase, where diagnostic knowledge is restructured to grant efficient access operations during a diagnostic session phase.

关键词： Failure detection artificial intelligence expert systems modeling causal reasoning temporal reasoning structuring model-based

来源：评论

学校读者我要写书评

暂无评论

An optimisation algorithm for minimising energy dissipation in NoC-based hard real-time embedded systems 13

An optimisation algorithm for minimising energy dissipation ...

引用

21st International Conference on real-time Networks and systems, RTNS 2013

作者： Mohd Sayuti, M. Norazizi Sham Indrusiak, Leandro Soares Garcia-Ortiz, Alberto Real-Time Systems Group Department of Computer Science University of York United Kingdom Institute of Electrodynamics and Microelectronics University of Bremen Germany

ISBN: (纸本)9781450320580

This paper introduces an evolutionary multi-objective optimisation algorithm to facilitate fast and efficient task allocation of hard real-time embedded systems with Networks-On-Chip (NoC) as the interconnection at the early design stage, where evaluating as many as possible solutions is crucial. Our approach uses analytical fitness functions to provide fast evaluation of large number of solutions;a contrast to simulation-based optimisation technique, whereby it tends to be not only impractical when the design space is very large but also unfeasible as far as hard real-time systems are concerned. The proposed algorithm guarantees the predictability in timing behaviour of the systems whilst minimising energy dissipation whenever tasks are reallocated and their packets are rerouted, which differs from the state-of-the-art approaches. In addition, not only it can explore the allocation of tasks but also the encoding of the data packets. The evidence gathered from case studies shows that the proposed algorithm is able to find schedulable allocation of tasks, preserving it whilst further minimising energy dissipation. © 2013 ACM.

关键词： Energy dissipation

来源：评论

学校读者我要写书评

暂无评论

The virtual lover： variable and easily guided 3D fish animations as an innovative tool inmate-choice experiments with sailfinmollies-II. Validation

引用

Current Zoology 2017年第1期63卷 65-74页

作者： Stefanie GIERSZEWSKI Klaus MuLLER levgen SMIELIK Jan-Marco HUTWOHL Klaus-Dieter KUHNERT Klaudia WITTE Research Group of Ecology and Behavioral Biology Institute of Biology University of Siegen Adolf-Reichwein- StraBe 2 Siegen 57068 Germany Institute of Real-Time Learning Systems Department of ElectricalEngineering & Computer Science University of Siegen HSIderlinstraBe 3 Siegen 57076 Germany

The use of computer animation in behavioral research is a state-of-the-art method for designing andpresenting animated animals to live test animals. The major advantages of computer animations are：（1） the creation of animated animal stimuli with high variability of morphology and even behavior; （2）animated stimuli provide highly standardized, controlled and repeatable testing procedures; and （3）they allow a reduction in the number of live test animals regarding the 3Rs principle. But the use of ani-mated animals should be attended by a thorough validation for each test species to verify that behaviormeasured with live animals toward virtual animals can also be expected with natural stimuli. Here wepresent results on the validation of a custom-made simulation for animated 3D sailfin mollies Poecilialatipinna and show that responses of live test females were as strong to an animated fish as to a videoor a live male fish. Movement of an animated stimulus was important but female response was stron-ger toward a swimming 3D fish stimulus than to a ＂swimming＂ box. Moreover, male test fish wereable to discriminate between animated male and female stimuli; hence, rendering the animated 3D fisha useful tool in mate-choice experiments with sailfin mollies.

关键词： computer animation, fish behavior, mate-choice experiment, validation, virtual fish model.

来源：评论

学校读者我要写书评

暂无评论

Multisite co-allocation algorithms for computational grid 20

Multisite co-allocation algorithms for computational grid

引用

20th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2006

作者： Zhang, Weizhe Cheng, Albert M. K. Hu, Mingzeng School of Computer Science and Technology Harbin Institute of Technology China Real-Time Systems Laboratory Department of Computer Science University of Houston Houston TX 77204-3010 United States

ISBN: (纸本)1424400546

Efficient multisite job scheduling facilitates the cooperation of multi-domain massively parallel processor systems in a computing grid environment. However, co-allocation, heterogeneity, adaptability, and scalability emerge as tough challenges for the design of multisite job scheduling models and algorithms. This paper presents a new multisite job scheduling schema based on the multisite job scheduling model and the performance model for a heterogeneous grid environment. There are three key components: resource selection, reservation, and backfilling. The optimal and greedy-heuristic adaptive resource selection strategies are introduced. The conservative and easy backfilling are incorporated into the backfilling procedure. Experiments indicate that the scheduler and the algorithm are effective and perform better than a non-adaptive algorithm. © 2006 IEEE.

关键词： Computational methods

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：