检索结果-内蒙古大学图书馆

IEEE Conference on computer Vision and Pattern Recognition

作者： Chunfeng Yuan Xi Li Weiming Hu Haibin Ling Stephen Maybank National Laboratory of Pattern Recognition Institute of Automation School of Computer Science University of Adelaide Department of Computer and Information Sciences Temple University School of Computer Science and Information Systems Birkbeck College

ISBN: (纸本)9781467364102

Spatio-temporal interest points serve as an elementary building block in many modern action recognition algorithms, and most of them exploit the local spatio-temporal volume features using a Bag of Visual Words (BOVW) representation. Such representation, however, ignores potentially valuable information about the global spatio-temporal distribution of interest points. In this paper, we propose a new global feature to capture the detailed geometrical distribution of interest points. It is calculated by using the R transform which is defined as an extended 3D discrete Radon transform, followed by applying a two-directional two-dimensional principal component analysis. Such R feature captures the geometrical information of the interest points and keeps invariant to geometry transformation and robust to noise. In addition, we propose a new fusion strategy to combine the R feature with the BOVW representation for further improving recognition accuracy. We utilize a context-aware fusion method to capture both the pairwise similarities and higher-order contextual interactions of the videos. Experimental results on several publicly available datasets demonstrate the effectiveness of the proposed approach for action recognition.

关键词： BOVW points keeps ROENTGEN Recognition (Psychology) fusion method Transform Bag device

来源：评论

学校读者我要写书评

暂无评论

Deep learning for object detection and grasping: A survey

Deep learning for object detection and grasping: A survey

引用

2018 IEEE International Conference on information and automation, ICIA 2018

作者： Jia, Qun Cai, Jun Cao, Zhiqiang Wu, Yelan Zhao, Xionglei Yu, Junzhi State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing101408 China School of Computer and Information Engineering Beijing Technology and Business University Beijing100048 China

ISBN: (纸本)9781538680698

Detecting and grasping objects in unstructured environments is an important yet difficult task. Fortunately, the breakthroughs from deep convolutional networks stimulate the development of object detection and grasping. The survey aims to serve as a comparison for region-based and region-free detection framework based on deep learning, and supplies the latest research results of object grasping with deep learning. Firstly, we briefly analyze the object detection and grasping. Then, the representative object detection methods based on deep learning are overviewed. Thirdly, we introduce the application of convolutional neural networks in object grasping. Finally, the potential trends in object detection and grasping based on deep learning are discussed. © 2018 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Learning with only multiple instance positive bags

Learning with only multiple instance positive bags

引用

2016 International Joint Conference on Neural Networks, IJCNN 2016

作者： Wang, Zhigang Zhao, Zengshun Zhang, Changshui Computer and Communication Engineering School Tianjin University of Technology Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology China Key Laboratory of Computer Vision and System Tianjin University of Technology Ministry of Education China College of Electronics Communication and Physics Shandong University of Science and Technology China Automation Department Tsinghua University State Key Laboratory of Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and Technology China

ISBN: (纸本)9781509006199

In traditional multiple instance learning (MIL), both positive and negative bags are required to learn a prediction function. However, a high human cost is needed to know the label of each bag - positive or negative. Only positive bags contain our focus (positive instances) while negative bags consist of noise or background (negative instances). So we do not expect to spend too much to label the negative bags. Contrary to our expectation, nearly all existing MIL methods require enough negative bags besides positive ones. In this paper we propose an algorithm called 'Positive Multiple Instance' (PMI), which learns a classifier given only a set of positive bags. So the annotation of negative bags becomes unnecessary in our method. PMI is constructed based on the assumption that the unknown positive instances in positive bags be similar each other and constitute one compact cluster in feature space and the negative instances locate outside this cluster. The experimental results demonstrate that PMI achieves the performances close to or a little worse than those of the traditional MIL algorithms on benchmark and real data sets. However, the number of training bags in PMI is reduced significantly compared with traditional MIL algorithms. © 2016 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Distributed Flow Shop Scheduling with Sequence-Dependent Setup Times Using an Improved Iterated Greedy Algorithm

引用

Complex System Modeling and Simulation 2021年第3期1卷 198-217页

作者： Xue Han Yuyan Han Qingda Chen Junqing Li Hongyan Sang Yiping Liu Quanke Pan Yusuke Nojima the School of Computer Science Liaocheng UniversityLiaocheng 252000China the State Key Laboratory of Synthetical Automation for Process Industries Northeastern UniversityShenyang 110819China the School of Information Science and Engineering Shandong Normal UniversityJinan 252000China the College of Computer Science and Electronic Engineering Hunan UniversityChangsha 410082China the School of Mechatronic Engineering and Automation Shanghai UniversityShanghai 200072China the Department of Computer Science and Intelligent Systems Osaka Prefecture UniversityOsaka 599-8531Japan

To meet the multi-cooperation production demand of enterprises,the distributed permutation flow shop scheduling problem(DPFSP)has become the frontier research in the field of manufacturing *** this paper,we investigate the DPFSP by minimizing a makespan criterion under the constraint of sequence-dependent setup *** solve DPFSPs,significant developments of some metaheuristic algorithms are *** this context,a simple and effective improved iterated greedy(NIG)algorithm is proposed to minimize makespan in *** to the features of DPFSPs,a two-stage local search based on single job swapping and job block swapping within the key factory is designed in the proposed *** compare the proposed algorithm with state-of-the-art algorithms,including the iterative greedy algorithm(2019),iterative greedy proposed by Ruiz and Pan(2019),discrete differential evolution algorithm(2018),discrete artificial bee colony(2018),and artificial chemical reaction optimization(2017).Simulation results show that NIG outperforms the compared algorithms.

关键词： distributed permutation flow shop iterated greedy local search swapping strategy

来源：评论

学校读者我要写书评

暂无评论

A Migration Path to IEC 61499 for the Batch Process Industry

A Migration Path to IEC 61499 for the Batch Process Industry

引用

IEEE International Conference on Industrial Informatics (INDIN)

作者： J. Peltola J. Christensen S. Sierla K. Koskinen Laboratory of Information and Computer Systems in Automation Helsinki University of Technology Finland Holobloc Inc. Cleveland Heights OH USA

Many recent contributions in the field of embedded, networked control and collaborative manufacturing, such as dynamic reconfiguration, are based on the IEC 61499 standard, which defines a general-purpose architecture for control applications. The industrial acceptance of the standard remains unclear at this time, largely because there is no obvious way to apply domain-specific, industrially accepted engineering methodologies and concepts in the context of IEC 61499. This paper proposes a way to support the established practices of the batch process domain with IEC 61499, and assesses the feasibility of the approach with an experiment involving professional designers.

关键词： IEC standards Manufacturing industries Software standards Standards development Investments Industrial control Application software Software tools Process control Instruction sets

来源：评论

学校读者我要写书评

暂无评论

Output synchronization of multiple mobile agents

Output synchronization of multiple mobile agents

引用

2010 International Conference on Networking, Sensing and Control, ICNSC 2010

作者： Tan, Fuxiao Liu, Derong Guan, Xinping School of Computer and Information Sciences Fuyang Teachers College Fuyang Anhui 236041 China Key Laboratory of Complex Systems and Intelligence Science Institute of Automation Chinese Academy of Sciences Beijing 100190 China College of Electrical Engineering Yanshan University Qinhuangdao Hebei 066004 China

ISBN: (纸本)9781424464531

In real-life, many practical applications involve agents that are nonlinear and nonholonomic. This paper investigates output synchronization of multiple mobile agents in a plane. The output synchronization of mobile agent's aims are two aspects: making the speed of each agent synchronized and tracking desired trajectories in a group. First, each agent dynamics is described by an affine control system and the communication topology among the agents is represented by a digraph. Using adjacent information and incidence matrix, a decentralized control law is acquired, which is composed of alignment control and cohesion control. Second, the stability of the group is proved by the decentralized control law and the synchronization control objective is realized. Finally, ten mobile agents are simulated to show the effectiveness of the present control law. ©2010 IEEE.

关键词： Mobile agents

来源：评论

学校读者我要写书评

暂无评论

Fuzzy approach based on Quantum-inspired MRF for SOFC anode optical microscope images segmentation 2017

Fuzzy approach based on Quantum-inspired MRF for SOFC anode ...

引用

9th International Conference on Machine Learning and Computing, ICMLC 2017

作者： Guo, Chengzhen Fu, Xiaowei Chen, Li Xu, Xin Li, Xi College of Computer Science and Technology Wuhan University of Science and Technology Wuhan430065 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial Systems Wuhan430065 China College of Automation Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9781450348171

Microstructural information acquired from image analysis can be used in cell modeling. In order to obtain more precise Solid Oxide Fuel Cell (SOFC) microstructure parameters, an adaptive fuzzy approach is developed for three-phase identification of YSZ/Ni anode Optical Microscopic (OM) images. A new quantum-inspired clique potential Markov random field (MRF) function is proposed to considerate spatial information in fuzzy logic model, where the space distance based weight is introduced to reflect the influence of neighborhood pixels. Simulated images and real SOFC anode OM images are used to compare the effectiveness and practicability of the proposed algorithm with others. Experiment results demonstrate that the proposed methods can accurately separate there-phase of SOFC OM images, which lays the foundation of subsequent microstructural parameters extracting. © 2017 ACM.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Dense Video Captioning through Convolutional-Transformer Integration 4

Dense Video Captioning through Convolutional-Transformer Int...

引用

4th IEEE International Conference on Digital Twins and Parallel Intelligence, DTPI 2024

作者： Cao, Jiaxi Zhang, Chunjie Zheng, Xiaolong Beijing Jiaotong University Beijing Key Laboratory of Advanced Information Science and Network Technology School of Computer Science and Technology Beijing China Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Beijing China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing China

ISBN: (纸本)9798350349252

Dense video captioning, a task that has recently garnered attention in the field of computer vision, focuses on generating detailed captions for multiple events along with their temporal locations within untrimmed videos. Existing transformer-based methods have achieved notable success. However, some methods utilizing deformable transformer face challenges in processing long videos, as the encoder may struggle to capture the long-term dependencies of events in the video. This issue is partly due to not integrating Convolutional Neural Networks (CNN) with the deformable transformer architecture. In this work, we introduce Dense Video Captioning through Convolutional-Transformer Integration (CTDVC), which links Layer Normalization, the Scalable-Granularity Perception (SGP), and Group Normalization into a network, replacing the encoder part of the deformable transformer. This model better accounts for the sequential relationship between events, especially those events in the video that span over a longer duration, allowing it to generate video captions that are not only more coherent but also more precise in their narrative. We evaluated our method on ActivityNet Captions and YouCook2 datasets. Experiments demonstrate that our proposed method CTDVC achieves an improvement in performance. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Proactive Computing in Process Monitoring: information Agents for Operator Support

Proactive Computing in Process Monitoring: Information Agent...

引用

International Conference on Emerging Technologies and Factory automation (ETFA)

作者： Antti Pakonen Teppo Pirttioja Ilkka Seilonen Teemu Tommila VTT Technical Research Center of Finland Finland Automation Technology Laboratory Helsinki University of Technology Finland Information and Computer Systems Automation Helsinki University of Technology Finland

While automation systems can track thousands of measurements it is still up to human process operators to determine the operational situation of the controlled process, particularly in abnormal situations. To fully exploit the computing power of embedded processors and to release humans from simple data harvesting activities, the concept of proactive computing tries to exploit the strengths of both man and machine. Proactive features can be implemented using intelligent agent technology, enabling humans to move from simple interaction with computers into supervisory tasks. Autonomous information agents can handle massive amounts of heterogeneous data. They perform tedious tasks of information retrieving, combining and monitoring on the behalf of their users. This paper presents a multi-agent-based architecture for process automation, which aims to support process operators in their monitoring activities. The approach is tested with a scenario inspired by a real-world industrial challenge.

关键词： Humans automation Embedded computing computerized monitoring Particle measurements Automatic control Process control Control systems Intelligent agent information retrieval

来源：评论

学校读者我要写书评

暂无评论

Adversarial attack method with adaptive step size for ID card text recognition 4

Adversarial attack method with adaptive step size for ID car...

引用

4th IEEE International Conference on Digital Twins and Parallel Intelligence, DTPI 2024

作者： Feng, Weidong Zhang, Chunjie Zheng, Xiaolong Beijing Jiaotong University Beijing Key Laboratory of Advanced Information Science and Network Technology School of Computer Science and Technology Beijing China Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Beijing China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing China

ISBN: (纸本)9798350349252

In the field of text recognition models, existing adversarial attack algorithms mainly target white-box scenarios, which are usually limited to single-color backgrounds and short text length. However, with the complex color textures of ID card images and long text length, these methods are not satisfactory when performing adversarial attacks on ID card text data. To overcome these challenges, this paper introduces a novel black-box attack method tailored for ID card text recognition models. The proposed approach accounts for the complexities of intricate image backgrounds, extended text data, and the limitations inherent in black-box conditions. The proposed algorithm introduces an adaptive step-size search method based on line search, aiming to overcome the limitations of traditional methods that rely on fixed step sizes and projection techniques for perturbation generation. This refinement aims to enhance the success rate of black-box attacks while maintaining efficacy in white-box scenarios. Spatial transformations and random noise are incorporated to fortify the robustness of adversarial samples. Experimental results, conducted under various norms, demonstrate that the fusion of the traditional method with the adaptive step-size search method yields superior attack performance. © 2024 IEEE.

关键词： Adversarial machine learning

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：