检索结果-内蒙古大学图书馆

IEEE International Conference on Systems, Man and Cybernetics

作者： Nong Sang Ruolin Wang Tianxu Zhang Institute for Pattern Recognition and Artificial Intelligence State E ducation Commission Laboratory for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan Hubei China Department of Civil Engineering Wuhan University of Hydraulic and Electrical Engineering Hubei China

ISBN: (纸本)0780340531

Matching confidence is an important element for evaluating image matching quality. A method is presented which uses the technique of tests of hypotheses to determine image matching confidence under a certain testing level. The authors use similarity measurement values to be the statistics. Experimental results with large real images prove the effectiveness of the method to determine image matching confidence.

关键词： Testing image matching Stereo image processing image reconstruction Statistics Navigation Remotely operated vehicles pattern matching Layout Optimized production technology

来源：评论

学校读者我要写书评

暂无评论

Sub-manifold distance based object recognition in clutter

Sub-manifold distance based object recognition in clutter

引用

International Conference on Natural Computation (ICNC)

作者： Hua Zhou Chao Cai Mingyue Ding Institute of Pattern Recognition and Artificial Intelligence National Laboratory of Multi-spectral Information Processing Technologies Huazhong University of Science and Technology Wuhan China School of Life Science and Technology Imaging Processing and Intelligence Control Key Laboratory of Education Ministry Huazhong University of Science and Technology Wuhan China

Object recognition is challenging problem in computer vision due to appearance variation and presence of visual clutter and occlusions. Recently manifolds are thought to be fundamental for visual perception, and manifold learning algorithms are developed for discovering intrinsical features. Selective visual attention mechanism provides tools to reduce computation cost and avoid the influence of clutter background. In this paper, we described a new object recognition method, the submanifold distance (SMD) algorithm, which is induced by the visual attention mechanism to provide complex object recognition. Experiments with airport remote sensing images illustrated that our proposed algorithm can recognize complex objects accurately, robustly and quickly.

关键词： Manifolds Visualization Airports Clutter Target recognition image recognition

来源：评论

学校读者我要写书评

暂无评论

RECALL: A Benchmark for LLMs Robustness against External Counterfactual Knowledge

arXiv

引用

arXiv 2023年

作者： Liu, Yi Huang, Lianzhe Li, Shicheng Chen, Sishuo Zhou, Hao Meng, Fandong Zhou, Jie Sun, Xu National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China Pattern Recognition Center WeChat AI Tencent Inc. China Center for Data Science Peking University China

LLMs and AI chatbots have improved people\'s efficiency in various ***, the necessary knowledge for answering the question may be beyond themodels\' knowledge boundaries. To mitigate this issue, many researchers try tointroduce external knowledge, such as knowledge graphs and Internet contents,into LLMs for up-to-date information. However, the external information fromthe Internet may include counterfactual information that will confuse the modeland lead to an incorrect response. Thus there is a pressing need for LLMs topossess the ability to distinguish reliable information from externalknowledge. Therefore, to evaluate the ability of LLMs to discern thereliability of external knowledge, we create a benchmark from existingknowledge bases. Our benchmark consists of two tasks, Question Answering andText Generation, and for each task, we provide models with a context containingcounterfactual information. Evaluation results show that existing LLMs aresusceptible to interference from unreliable external knowledge withcounterfactual information, and simple intervention methods make limitedcontributions to the alleviation of this issue. © 2023, CC BY-NC-SA.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Learn What You Need in Personalized Federated Learning

arXiv

引用

arXiv 2024年

作者： Lv, Kexin Ye, Rui Huang, Xiaolin Yang, Jie Chen, Siheng Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China Shanghai Jiao Tong University Shanghai200240 China Shanghai Jiao Tong University Shanghai200240 China Shanghai AI Laboratory Shanghai200232 China

Personalized federated learning aims to address data heterogeneity across local clients in federated learning. However, current methods blindly incorporate either full model parameters or predefined partial parameters in personalized federated learning. They fail to customize the collaboration manner according to each local client's data characteristics, causing unpleasant aggregation results. To address this essential issue, we propose Learn2pFed, a novel algorithm-unrolling-based personalized federated learning framework, enabling each client to adaptively select which part of its local model parameters should participate in collaborative training. The key novelty of the proposed Learn2pFed is to optimize each local model parameter's degree of participant in collaboration as learnable parameters via algorithm unrolling methods. This approach brings two benefits: 1) mathmatically determining the participation degree of local model parameters in the federated collaboration, and 2) obtaining more stable and improved solutions. Extensive experiments on various tasks, including regression, forecasting, and image classification, demonstrate that Learn2pFed significantly outperforms previous personalized federated learning methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Parameter estimation

来源：评论

学校读者我要写书评

暂无评论

New logistics distribution route dispatching mode based on genetic algorithm-ant colony algorithm

引用

Computer Modelling and New Technologies 2014年第10期18卷 313-318页

作者： Yi, Fasheng Li, Xiaoling Yuan, Jimin School of Computer Science and Technology Chengdu University Chengdu China University Key Laboratory of Pattern Recognition and Intelligent information Processing Chengdu China The Department Computer Engineering Chengdu Aeronautic Vocational and Technical College Chengdu China

For multi-target route optimization with constraint conditions, the mathematical model for logistics distribution route optimization is built to accelerate response speed of logistics enterprises to customers, improve service quality, and strengthen the satisfaction of customers, and a new algorithm with the combination of genetic and ant colony algorithms is proposed to solve the selection issues of such logistics route. Initial pheromone is formed with genetic algorithm, based on which the optimal solution is rapidly sought with ant colony algorithm, and complementary advantages are achieved between above two algorithms. Application examples and simulations are available for calculation, and the results show that such algorithm is practical and effective to optimize logistics distribution route.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Bridging text and video: A universal multimodal transformer for video-audio scene-aware dialog

arXiv

引用

arXiv 2020年

作者： Li, Zekang Li, Zongjia Zhang, Jinchao Feng, Yang Niu, Cheng Zhou, Jie Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Pattern Recognition Center WeChat AI Tencent Inc China School of EECS Peking University University of Chinese Academy of Sciences

Audio-Visual Scene-Aware Dialog (AVSD) is a task to generate responses when chatting about a given video, which is organized as a track of the 8th Dialog System Technology Challenge (DSTC8). To solve the task, we propose a universal multimodal transformer and introduce the multitask learning method to learn joint representations among different modalities as well as generate informative and fluent responses. Our method extends the natural language generation pre-trained model to multimodal dialogue generation task. Our system achieves the best performance in both objective and subjective evaluations in the challenge. Copyright © 2020, The Authors. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Alignment, segmentation and 3-D reconstruction of serial sections based on automated algorithm

引用

AIP Conference Proceedings 2012年第1期1504卷 1287-1292页

作者： Weiguo Bian Shaojie Tang Qiong Xu Qin Lian Jin Wang Dichen Li State Key Lab for Manufacturing System Engineering Xi 'an Jiaotong University Xi 'an 710049 P.R.China and The First Affiliated Hospital Medical College Xi 'an Jiaotong University Xi 'an 710049 China School of Automation Xi'an University of Posts and Telecommunications Xi'an 710121 P.R.China and Institute of Image Processing & Pattern Recognition Xi'an Jiaotong University Xi'an 710049 China Institute of Image Processing & Pattern Recognition Xi'an Jiaotong University Xi'an 710049 China State Key Lab for Manufacturing System Engineering Xi 'an Jiaotong University Xi 'an 710049 China The Second Affiliated Hospital Medical College Xi'an Jiaotong University Xi'an Shaanxi 710121 China

A well-defined three-dimensional (3-D) reconstruction of bone-cartilage transitional structures is crucial for the osteochondral restoration. This paper presents an accurate, computationally efficient and fully-automated algorithm for the alignment and segmentation of two-dimensional (2-D) serial to construct the 3-D model of bone-cartilage transitional structures. Entire system includes the following five components: (1) image harvest, (2) image registration, (3) image segmentation, (4) 3-D reconstruction and visualization, and (5) evaluation. A computer program was developed in the environment of Matlab for the automatic alignment and segmentation of serial sections. Automatic alignment algorithm based on the position's cross-correlation of the anatomical characteristic feature points of two sequential sections. A method combining an automatic segmentation and an image threshold processing was applied to capture the regions and structures of interest. SEM micrograph and 3-D model reconstructed directly in digital microscope were used to evaluate the reliability and accuracy of this strategy. The morphology of 3-D model constructed by serial sections is consistent with the results of SEM micrograph and 3-D model of digital microscope.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Laser Measurement of 3D curved Glass Contour based on computer Vision

Research on Laser Measurement of 3D curved Glass Contour bas...

引用

International Conference on Information Science and Control Engineering (ICISCE)

作者： Peng Wang Jinmeng Wu Guilin Yan Shuo Bian Hubei Key Laboratory of Optical Information and Pattern Recognition Hubei Research Centre of Video Image and High Definition Projection Wuhan Institute of Technology Wuhan China School of Mechanical and Electrical Engineering School of Electrical and Information Engineering

In the mobile phone glass industry, curved glass is widely used. Whether the curved glass is measured with high efficiency and precision and whether the curved edge profile error can be evaluated directly affects the quality and service cycle of glass products. In view of the difficulty of accurate measurement and evaluation of 3D mobile phones curved glass profile, a visual measurement method of 3D mobile phones curved glass profile error based on laser scanning and shape template matching is proposed in this paper. Accurate measurement of mobile phone curved glass greatly improves the fit between curved glass and mobile phone and the efficiency of production. Therefore, this paper proposes a method for evaluating the contour degree of curved glass on mobile phones based on Open Cascade and OpenCV. This method uses the lasers and camera equipment to extract the profile outline of the curved glass, then extract the profile outline of the mobile phone curved glass model that has been drawn in 3D software. The extracted contour lines are matched by methods such as translation and rotation, and finally the distance between the corresponding points is calculated as the contour error. Experimental results show that the method is able to accurately measure the profile error and greatly reduce the measurement instability and have good robustness.

关键词： Computer vision Three-dimensional displays Shape Shape measurement Measurement uncertainty Measurement by laser beam Glass

来源：评论

学校读者我要写书评

暂无评论

RCFormer : Interactive image Segmentation via Reconstructing Click Vision Transformers

RCFormer : Interactive Image Segmentation via Reconstructing...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： PanPan Chen DaHan Wang JiaHua Wu Yun Wu YiFan He XuYao Zhang ShunZhi Zhu Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen University of Technology Xiamen China Xiamen Key Laboratory of Visual Perception Technology and Applications Reconova Technologies Co.Ltd Xiamen China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation of Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Click-based interactive image segmentation intends to segment an object from the background under user click guidance. Recently, Vision Transformer has made significant strides in interactive image segmentation. However, the previous studies 1) overlook the importance of different clicks in terms of their contribution to the segmentation results; and 2) suffer from inconsistency across different feature scales in the multi-scale structure. In this paper, we propose a new interactive segmentation framework, named RCFormer, with two novel components: reconstruct click patch embedding (RCPE) for encoding the importance of clicks, and multi-scale adaptive fusion (MSAF) for the adaptive fusion of feature maps across different scales. RCPE enhances the effectiveness of click interactions by spatially distinguishing the importance of clicks. MSAF adaptively fuses useful spatial information and filters the redundant feature at multi-scales. The experiments on several benchmarks show that our proposed approach achieves state-of-the-art performance. Notably, our method achieves 2.31 NoC@90 on the Berkeley dataset, improving by 8.6% over the previous best results.

关键词： image segmentation Computer vision Filters Fuses Neural networks Network architecture Transformers

来源：评论

学校读者我要写书评

暂无评论

Sparse Kernel Regression with Coefficient-based `q−regularization

引用

Journal of Machine Learning Research 2019年 20卷

作者： Shi, Lei Huang, Xiaolin Feng, Yunlong Suykens, Johan A.K. Shanghai Key Laboratory for Contemporary Applied Mathematics School of Mathematical Sciences Fudan University Shanghai China Institute of Image Processing and Pattern Recognition Institute of Medical Robotics Shanghai Jiao Tong University MOE Key Laboratory of System Control and Information Processing Shanghai China Department of Mathematics and Statistics State University of New York at Albany New York United States Department of Electrical Engineering ESAT-STADIUS KU Leuven Kasteelpark Arenberg 10 LeuvenB-3001 Belgium

In this paper, we consider the `q−regularized kernel regression with 0 q−penalty term over a linear span of features generated by a kernel function. We study the asymptotic behavior of the algorithm under the framework of learning theory. The contribution of this paper is two-fold. First, we derive a tight bound on the `2−empirical covering numbers of the related function space involved in the error analysis. Based on this result, we obtain the convergence rates for the `1−regularized kernel regression which is the best so far. Second, for the case 0 ©c 2019 Lei Shi, Xiaolin Huang, Yunlong Feng, and Johan A.K. Suykens.

关键词： Regression analysis

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：