检索结果-内蒙古大学图书馆

16th European Conference on Computer Vision, ECCV 2020

作者： Yu, Changqian Liu, Yifan Gao, Changxin Shen, Chunhua Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China The University of Adelaide Adelaide Australia

ISBN: (纸本)9783030585709

Non-local operation is widely explored to model the long-range dependencies. However, the redundant computation in this operation leads to a prohibitive complexity. In this paper, we present a Representative Graph (RepGraph) layer to dynamically sample a few representative features, which dramatically reduces redundancy. Instead of propagating the messages from all positions, our RepGraph layer computes the response of one node merely with a few representative nodes. The locations of representative nodes come from a learned spatial offset matrix. The RepGraph layer is flexible to integrate into many visual architectures and combine with other operations. With the application of semantic segmentation, without any bells and whistles, our RepGraph network can compete or perform favourably against the state-of-the-art methods on three challenging benchmarks: ADE20K, Cityscapes, and PASCAL-Context datasets. In the task of object detection, our RepGraph layer can also improve the performance on the COCO dataset compared to the non-local operation. Code is available at https://***/RepGraph. © 2020, Springer Nature Switzerland AG.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Joint Generic Learning and Multi-source Domain Adaptation on Unsupervised Face Recognition 1

引用

6th International Conference on Artificial Intelligence and Security,ICAIS 2020

作者： Xu, Zhi Han, Han Ji, Jianqiu Qiang, Baohua Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin541004 China

ISBN: (数字)9789811580833

ISBN: (纸本)9789811580826

For most machine learning algorithms, the performance of model trained on the source domain degenerates obviously when it is applied to the target domain because the distributions of both domains are different. Besides, in many cases, there is a lack of adequate supervised target domain training samples. In order to solve the mismatch between the domains and the lack of training samples, this paper proposes jointing domain adaptation and generic learning on solving unsupervised face recognition. Firstly, samples are selected randomly from multiple source and target domains which do not contain interest subjects and construct multiple sub-datasets. Secondly, learning a common subspace for each sub-dataset. In the common subspace, source and target domains can mutual interlace and their structures are well preserved, and we can get more discrimination information from multiple feature subspaces. Finally, the recognition is obtained by using combine strategies. The experimental results show that the recognition performance of the framework is better than that of the competitive ones. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Adaptive Multi-Core Real- Time Scheduling Based on Reinforcement Learning

Adaptive Multi-Core Real- Time Scheduling Based on Reinforce...

引用

International Conference on control and Automation (ICCA)

作者： Yonghui Liang Hui Li Fei Shen Qimin Xu Shuna Hua Shanying Zhu Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Re-search Center of Intelligent Control and Management Shanghai China Key Laboratory of Wireless Sensor Network and Communications Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences Shanghai China North Information Control Research Academy Group Company Ltd. Nanjing China

ISBN: (数字)9798350354409

ISBN: (纸本)9798350354416

With the transformation towards industrial intel-ligence, multi-core processors are increasingly being applied in real-time networked control systems to ensure secure exe-cution of sensing, computing and actuating tasks under time constraints. However, existing scheduling methods result in either low CPU utilization or many missed task deadlines in dynamic systems. In this paper, we propose a two-layer scheduling architecture to address this issue by fully exploring the complex dependency between real-time tasks. To be specific, the local layer determines task execution priorities considering both dependency between tasks and deadline constraints by utilizing a reinforcement learning approach. Moreover, to better utilize the parallel capabilities of multi-core processors and reduce temporal collisions, this paper minimizes the requested core count for the task set based on a greedy strategy. The global layer designs a scheduling algorithm based on the pre-empt method and provides schedulability analysis of multiple task sets. Experimental results validate the correctness of the proposed scheduling approach, and efficiency is demonstrated through comparisons with baseline method.

关键词： Job shop scheduling Multicore processing Scheduling algorithms Networked control systems Reinforcement learning Real-time systems Sensors

来源：评论

学校读者我要写书评

暂无评论

image Matching Algorithm Under Adverse Conditions Based on SIFT

Image Matching Algorithm Under Adverse Conditions Based on S...

引用

IEEE International Symposium on Information (IT) in Medicine and Education, ITME

作者： Hao Chen Xinrong Cao Zuoyong Li Lihui Lin College of Computer and Big Data Fuzhou University Fuzhou China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control School of Computer and Big Data Minjiang University Fuzhou China Fujian Key Laboratory of Big Data Application and Intellectualization for Tea Industry School of Mathematics and Computer Science Wuyi University Fujian China

ISBN: (数字)9798350356670

ISBN: (纸本)9798350356687

image matching technology is crucial in computer vision applications. However, the traditional SIFT (Scale-Invariant Feature Transform) algorithm often faces challenges under adverse conditions, such as a high number of mismatched points and few accurately matched points. Additionally, in practical scenarios, environmental factors like lighting changes and image blurring further reduce image similarity. Therefore, this paper proposes an improved SIFT-based image matching algorithm to address these challenges. First, SIFT is used to extract image features, and a bidirectional FLANN (Fast Library for Approximate Nearest Neighbors) matching strategy is employed to initially filter out incorrect features. Then, the RANSAC (Random Sample Consensus) algorithm is used to screen out unreliable matching point pairs. Finally, the matching accuracy is evaluated based on the remaining pure matching point pairs. Experimental results demonstrate that, compared to the traditional SIFT algorithm, this improved algorithm achieves higher matching accuracy and robustness under adverse conditions, exhibiting superior performance.

关键词： Location awareness Matched filters Accuracy image matching Lighting Transforms Feature extraction Robustness Libraries Information technology

来源：评论

学校读者我要写书评

暂无评论

Byzantine-Resilient Multi-Agent Distributed Exact Optimization with Less Data

arXiv

引用

arXiv 2023年

作者： Zhai, Yang Liu, Zhi-Wei Yue, Dong Hu, Songlin Xie, Xiangpeng The Institute of Advanced Technology for Carbon Neutrality Nanjing University of Posts and Telecommunications Nanjing210023 China The School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China The Key Laboratory of Image Processing and Intelligent Control Ministry of Education Huazhong University of Science and Technology Wuhan430074 China

This paper studies the distributed multi-agent resilient optimization problem under the f-total Byzantine attacks. Compared with the previous work on Byzantine-resilient multi-agent exact optimization problems, we do not require the communication topology to be fully connected. Under the redundancy of cost functions, we propose the distributed comparative gradient elimination resilient optimization algorithm based on the traditional assumptions on strongly convex global costs and Lipschitz continuous gradients. Under this algorithm, we successfully prove that if the number of in-neighbors of each normal agent is greater than some constant and the parameter f satisfies certain conditions, all normal agents' local estimations of the global variable will finally reach consensus and converge to the optimized solution. Finally, the numerical experiments successfully verify the correctness of the results. Copyright © 2023, The Authors. All rights reserved.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

A Generalized Subspace Distribution Adaptation Framework for Cross-Corpus Speech Emotion Recognition

A Generalized Subspace Distribution Adaptation Framework for...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Shaokai Li Peng Song Liang Ji Yun Jin Wenming Zheng School of Computer and Control Engineering Yantai University China The State Key Laboratory of Tibetan Intelligent Information Processing and Application Tibetan Information Processing and Machine Translation Key Laboratory of Qinghai Province School of Physics and Electronic Engineering Jiangsu Normal University China Key Laboratory of Child Development and Learning Science (Southeast University) Ministry of Education Research Center for Learning Science Southeast University China

In this paper, we propose a novel transfer learning framework, named generalized subspace distribution adaptation (GSDA), to tackle the challenging cross-corpus speech emotion recognition problem. First, we learn a common low-dimensional feature subspace by utilizing a generalized subspace learning method. Second, we develop a novel distance metric to reduce the divergence between the source and target corpora, which can efficiently explore the similarity and dissimilarity information in the process of knowledge transfer. Third, to demonstrate the effectiveness of our framework, we apply GSDA to the traditional subspace learning algorithms. Finally, we conduct extensive experiments by using the low-level features and deep features on three popular emotional databases, i.e., Berlin, IEMOCAP, and CVE. The results demonstrate that the proposed framework can achieve better performance than several state-of-the-art transfer learning approaches.

关键词： Measurement Learning systems Emotion recognition Databases Transfer learning Signal processing algorithms Speech recognition

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Multimeme Memetic Algorithm for the VLSI Standard Cell Placement Problem 16th

An Adaptive Multimeme Memetic Algorithm for the VLSI Standar...

引用

16th International Conference on intelligent Information Hiding and Multimedia Signal processing, IIH-MSP 2020 in conjunction with the 13th International Conference on Frontiers of Information Technology, Applications and Tools, FITAT 2020

作者： Chen, Xiongfeng Chen, Jianli Wang, Tao Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350108 China Center for Discrete Mathematics and Theoretical Computer Science Fuzhou University Fuzhou350108 China

ISBN: (纸本)9789813367562

Placement has a tremendous impact on the final performance of a VLSI chip, and the problem itself is a combinatorial optimization problem. Memetic algorithms with problem-specific designs can solve the problem with high quality solutions, but they are generally time-consuming. To address this issue, adopting an adaptive strategy has become a key way to reduce the runtime of a memetic algorithm. In this paper, we present an adaptive multimeme memetic algorithm (AMMA) for the VLSI standard cell placement problem. In accordance with the distinctive features of the solution space of the problem, we propose a set of adaptive strategies to greatly improve the runtime efficiency. The main novelty of the proposed strategy lies in its constructing of crossover multimeme and the acceptance criteria of placement candidates. The experimental results and comparisons on Peko suite3 and ISPD04 benchmark circuits verified the efficacy and efficiency of the proposed adaptive strategies. Compared to the memetic algorithm without these main adaptive strategies, the AMMA reduces the runtime by around 32.58% on average. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2021.

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

Selection of Cancer Biomarkers from Microarray Gene Expression Data Utilizing the Bi-Objective Optimization Method

Selection of Cancer Biomarkers from Microarray Gene Expressi...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Hanjing Jiang Jianqing Lin Huachao Zhu Yabing Huang Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China Institute of Artificial Intelligence School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China School of Computer Science Wuhan University Wuhan China Department of Pathology Renmin Hospital of Wuhan University Wuhan China

Cancer-associated biomarker genes play an indispensable role in the intricate tapestry of cancer development and manifestation. The expression of biomarkers in different types of tumor cells has beneficial implications for shedding light on the development of various cancers, guiding clinical diagnosis, and treatment. Microarray technology enables the expression levels of thousands of genes in samples to be sequenced simultaneously. However, sparse and high-dimensional microarray data present a formidable challenge in identifying biomarker genes. This study presents EREF-NSGA2, a novel method for cancer biomarker selection from microarray data, employing a hybrid gene selection approach. Firstly, the combination of the wrapper and embedded gene selection methods is proposed to filter the microarray data, which efficiently decreases the search space of the algorithm. After that, the improved NSGA-II algorithm is used to search the genes subset obtained from the previous step to reach the optimal subset of cancer biomarker genes. The proposed EREF-NSGA2 is compared with other reported methods on six cancer benchmark gene expression datasets. A detailed biological analysis is performed to analyze the relationship between the selected genes and the cancer data sets they belong to. To summarize, EREF-NSGA2 proves its effectiveness in selecting a feature subset comprising the fewest genes while maintaining the highest classification accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MGTN: Multi-scale Graph Transformer Network for 3D Point Cloud Semantic Segmentation

MGTN: Multi-scale Graph Transformer Network for 3D Point Clo...

引用

IEEE Visual Communications and image processing (VCIP)

作者： Da Ai Siyu Qin Zihe Nie Hui Yuan Ying Liu Xi’an Key Laboratory of Image Processing Technology and Applications for Public Security Xi’an University of Posts and Telecommunications Xi’an China School of Communication and Information Engineering Xi’an University of Posts and Telecommunications Xi’an China School of Control Science and Engineering Shandong University Jinan China

ISBN: (数字)9798331529543

ISBN: (纸本)9798331529550

The structural similarity of point clouds presents challenges in accurately recognizing and segmenting semantic information at the demarcation points of complex scenes or objects. In this study, we propose a multi-scale graph transformer network (MGTN) for 3D point cloud semantic segmentation. First, a multi-scale graph convolution (MSG-Conv) is devised to address the limitations faced by existing methods when extracting local and global features of point cloud data with varying densities simultaneously. Subsequently, we employ a graph-transformer (G-T) module to enhance edge details and spatial position information in the point cloud, thereby improving recognition accuracy for small objects and confusing elements such as columns and beams. Extensive testing on ShapeNet parts and S3DIS datasets was conducted to demonstrate the effectiveness of MGTN. Compared to the baseline network DGCNN, our proposed MGTN achieves substantial performance improvements, as evidenced by notable increases in mIoU of 1.5% and 18.5% on the ShapeNet parts and S3DIS datasets respectively. Additionally, MGTN outperforms the recent CFSA- Net by 2.3% and 3.4% on OA and mIoU respectively.

关键词： Point cloud compression Three-dimensional displays Visual communication Convolution Semantic segmentation Semantics Transformers Feature extraction Data mining Testing

来源：评论

学校读者我要写书评

暂无评论

Anti-occlusion Object Tracking Algorithm using Response Template Fusion and Combined Features

Anti-occlusion Object Tracking Algorithm using Response Temp...

引用

Chinese control and Decision Conference, CCDC

作者： Jing Wang Yuan Wei Yisong Liu Weichao Huang Ming Hu Faculty of Printing Packaging Engineerring And Digital Media Technology Xi’an University of Technology Xi’an China Shannxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an University of Technology Xi'an China

The kernel correlation filtering algorithm cannot judge the occlusion by itself when the object is occluded by foreign objects, and the tracking performance is greatly affected. Aiming at this problem, this paper proposes an anti-occlusion object tracking algorithm that fuses response templates and combined features. The peak sidelobe ratio (PSR) is used to determine whether the object is occluded. When the object is partially occluded, a combined feature representation object model is introduced to enhance robustness, and a multi-response template with anti-occlusion performance is constructed to improve the performance of the object when it is occluded by foreign objects. The problem of reducing the available information, thereby improving algorithm performance. Experiments in the OTB-100 data set can prove that the success rate and accuracy of the algorithm have competitive results compared with the comparison algorithms.

关键词：

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：