检索结果-内蒙古大学图书馆

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

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

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

Identification and Extraction of Circular Markers in 3D Reconstruction

Identification and Extraction of Circular Markers in 3D Reco...

引用

International Conference on Wireless Communications and Signal processing (WCSP)

作者： Yunfei Wang Hanyu Hong Jinmeng Wu Guangya Wang Shiyang Li Hubei Key Laboratory of Optical Information and Pattern Recognition Wuhan China Hubei Engineering Research Center of Video Image and HD Projection Wuhan China School of Electrical and Information Engineering Wuhan Institute of Technology Wuhan China

ISBN: (数字)9781728172361

ISBN: (纸本)9781728172378

This paper presents a method for the identification and location of circular markers in 3D reconstruction. The input image is processed with gray scale and gaussian filter to remove noise interference and improve the accuracy of edge detection. The size and direction of the gradient of the image were calculated to obtain the edge features of the circular marker, and the circle degree of the closed edge was judged, and the center of the marker was obtained by fitting the edge features with the ellipse of the least square method. Hu moment similarity of each marker was obtained, and the non-marker was deleted and the real marker was retained by similarity judgment. Experiments show that the algorithm has good robustness, high precision, can effectively reduce the probability of false detection, and has high accuracy in complex environments.

关键词： image edge detection Transforms Three-dimensional displays Fitting Feature extraction Cameras Least mean squares methods

来源：评论

学校读者我要写书评

暂无评论

A New Approach of Color image Quantization

引用

通讯和计算机（中英文版） 2005年第3期2卷 72-76页

作者： HU Xinrong WANG Tianzhen LI Dehua Institute for Pattern Recognition and Artificial Intelligence State Education Commission Laboratory for Image Processing and Intelligence Control HuaZhong Univ. of Science＆Technology WuHan 430074 China Dept. of Computer Science ＆Technology Wuhan Institute of Science＆Technology WuHan 430074 China Institute of linage Processing WuHan Univ. of Technology Wuhan 430070China

来源：评论

学校读者我要写书评

暂无评论

Analysis of Least Squares Regularized Regression in Reproducing Kernel Kreın Spaces

arXiv

引用

arXiv 2020年

作者： Liu, Fanghui Shi, Lei Huang, Xiaolin Yang, Jie Suykens, Johan A.K. Department of Electrical Engineering [ESAT-STADIUS KU Leuven LeuvenB-3001 Belgium Institute of Image Processing and Pattern Recognition Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China Shanghai Key Laboratory for Contemporary Applied Mathematics School of Mathematical Sciences Fudan University Shanghai China

In this paper, we study the asymptotical properties of least squares regularized regression with indefinite kernels in reproducing kernel Kreın spaces (RKKS). The classical approximation analysis cannot be directly applied to study its asymptotical behavior under the framework of learning theory as this problem is in essence non-convex and outputs stationary points. By introducing a bounded hyper-sphere constraint to such non-convex regularized risk minimization problem, we theoretically demonstrate that this problem has a globally optimal solution with a closed form on the sphere, which makes our approximation analysis feasible in RKKS. Accordingly, we modify traditional error decomposition techniques, prove convergence results for the introduced hypothesis error based on matrix perturbation theory, and derive learning rates of such regularized regression problem in RKKS. Under some conditions, the derived learning rates in RKKS are the same as that in reproducing kernel Hilbert spaces (RKHS), which is actually the first work on approximation analysis of regularized learning algorithms in RKKS. Copyright © 2020, The Authors. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

SliceProp: A Slice-Wise Bidirectional Propagation Model for Interactive 3D Medical image Segmentation

SliceProp: A Slice-Wise Bidirectional Propagation Model for ...

引用

Medical Artificial Intelligence (MedAI), IEEE International Conference on

作者： Xin Xu Wenjing Lu Jiahao Lei Peng Qiu Hong-Bin Shen Yang Yang Department of Computer Science and Engineering Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China Department of Vascular Surgery Shanghai Ninth People's Hospital Shanghai Jiao Tong University School of Medicine Institute of Image Processing and Pattern Recognition and Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Jiao Tong University Shanghai China

Interactive medical image segmentation methods have become increasingly popular in recent years. These methods combine manual labeling and automatic segmentation, reducing the workload of annotation while maintaining high accuracy. However, most current interactive segmentation frameworks are limited to 2D image data, and are not suitable for 3D image data due to the large size and high complexity of 3D data, as well as the challenges posed by information asymmetry and sparse annotation. In this paper, we propose SliceProp, an interactive segmentation framework that implements slice-wise Label Bidirectional Propagation (LBP) for 3D medical image segmentation. SliceProp extends the interactive 2D image segmentation algorithm to 3D image segmentation, and can handle 3D data with large size and high complexity. Moreover, equipped with a Backtracking Feedback Check (BFC) module, SliceProp effectively addresses the issues of information asymmetry and spatial sparse annotation in 3D medical image segmentation. Additionally, we adopt an uncertainty-based criterion to pri-oritize the slices to be refined interactively, which enhances the efficiency of the interaction process by enabling the model to focus on the regions with the most unreliable predictions. SliceProp is evaluated on two datasets and achieves promising results compared to state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dim Small Targets Detection Based on Dualband Infrared image Fusion

Dim Small Targets Detection Based on Dualband Infrared Image...

引用

IEEE International Conference on Industrial Technology (ICIT)

作者： Yu-Qiu Sun Jin-Wen Tian Jian Liu State Education Commission Key Laboratory for Image Processing and Intelligent Control Institute for Pattern Recongnition and Artificial Intelliegence Huazhong University of Science and Technology Wuhan China School of Information and Mathematics Yangtze University Jingzhou China State Education Commission Key Laboratory for Image Processing and Intelligent Control Department of Electronic Information and Enginery Huazhong University of Science and Technology Wuhan China

To infrared images, the contrast of target and background is low, dim small targets have no concrete shapes and their textures cannot be reliable predicted. The paper puts forward a novel algorithm to fuse mid-wave and long-wave infrared images and detect targets. Firstly, the source images are decomposed by wavelet transformation. In usual, targets in infrared images are man-made, and their fractal dimension is different comparing with natural background. In wavelet transformation domain high-frequency part, we calculate local fractal dimension and set up fusion rule to merge corresponding sub-images of two matching source images. In low-frequency, we extract local maximum gray level to fuse them. Then reconstruct image by wavelet inverse transformation and obtain fused result image. In fusion results, the contrast between targets and background has obvious changes. And targets can be detected using contrast thresholding. The experimental results show that the method using fractal dimension to fuse dualband infrared images, and then detect targets is superior to use mid-wave or long -wave infrared images detect targets alone.

关键词： Object detection Dual band Infrared imaging Infrared detectors image fusion Fuses Fractals Concrete Shape Wavelet domain

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：