检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Wang, Hairong Wang, Tong Wang, Yiyan Chen, Fangping School of Computer Science and Engineering North Minzu University Yinchuan750021 China Key Laboratory of Image and Graphics Intelligent Processing of State Ethnic Affairs Commission North Minzu University Yinchuan750021 China

A B S T R A C TTo solve the visual semantic understanding bias and multimodal semantic bias in multimodal named entity recognition, the Confidence Learning Guides Label Fusion for Multimodal Named Entity Recognition (CLGLF) method is proposed. This method invokes the BLIP-2 pre-trained model to generate image captions, concatenates them with the input texts, and performs joint coding to achieve multimodal feature fusion. The candidate labels and text labels are obtained after decoding the multimodal representations and text representations. Based on using the KL divergence loss function to align the two groups of labels, the confidence score is calculated to evaluate the quality of the multimodal representation, and a confidence threshold is set to help screen out the biased candidate labels, the text labels in the corresponding positions are used to replace the biased candidate labels, to achieve the label fusion, and finally complete the multimodal named entity recognition. In order to verify the proposed method, experiments are carried out on the Twitter-2015 and Twitter-2017 multimodal datasets, and the experimental results are compared with 7 mainstream methods, such as MSB and UMT. The experimental results show the effectiveness of the CLGLF method. © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Extraction of Human Body Skeleton Based on Silhouette images

Extraction of Human Body Skeleton Based on Silhouette Images

引用

International Workshop on Education Technology and computer Science, ETCS

作者： Jianhao Ding Yigang Wang Lingyun Yu State Key Laboratory of CAD & CG University of Zhejiang Hangzhou China Institute of Computer graphics and Image Processing Hangzhou Dianzi University Hangzhou China Department of Mathematics and Computing Science University of Groningam Netherlands

ISBN: (纸本)9781424463886;9780769539874

Skeleton extraction is essential for general shape representation. A typical skeletonization algorithm should obtain the ability to preserve original object's topological and hierarchical properties. However, most of current methods are high memory cost, computationally intensive, and also require complex data structures. In this paper, we propose an efficient and accurate skeletonization method for the skeleton feature points extracted from human body based on silhouette images. First, the gradient of distance transform is used to detect critical points inside the foreground. Then, we converge and simplify critical points in order to generate the most important and elegant skeleton feature points. Finally, we present an algorithm which connects the skeleton feature points and estimates the position of skeleton joints.

关键词： Humans Skeleton Joints Iterative algorithms Euclidean distance Data mining Motion analysis image converters Shape Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Visual Semantic Enhancement for Multi-Modal Named Entity Recognition

SSRN

引用

SSRN 2024年

作者： Wang, Tong Wang, Hairong Xu, Xi Chen, Fangping School of Computer Science and Engineering North Minzu University Yinchuan750021 China Key Laboratory of Image and Graphics Intelligent Processing State Ethnic Affairs Commission North Minzu University Yinchuan750021 China

In recent years, a series of methods have been proposed to use image semantics to assist in extracting named entities. However, in these multi-modal named entity recognition methods, there are problems of visual semantic missing and weak semantic constraints in multi-modal representation. Therefore, a visual semantic enhancement for multi-modal named entity recognition (EVS-MNER) method is proposed. In this method, multiple visual features are used for collaborative representation to obtain more complete visual semantics. The semantic information in multiple visual features is integrated through the multi-modal features fusion module to generate visual semantic features, and the semantics are passed to the text features to obtain semantically enhanced multi-modal text representation. The visual entity classifier is used to decode visual semantic features, and the semantic consistency constraint of visual features is realized. The multi-task label decoder is called to mine the fine-grained semantics of the multi-modal text representation and text features, and the problem of semantic bias is solved by joint decoding, to further improve the accuracy of named entity recognition. On two multimodal entity recognition datasets of Twitter-2015 and Twitter-2017, the proposed method is compared with 10 methods such as PCEN and M3S. The experimental results show that the proposed method is effective. © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Content- and semantic-based progressive multimodal image retrieval

引用

ICIC Express Letters 2011年第1期5卷 201-206页

作者： Song, Haiyu Li, Xiongfei Wang, Pengjie Zhang, Xiaoli Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Jilin University Qianjin Avenue Changchun 130012 China Institute of Computer Graphics and Image Processing Dalian Nationalities University Economic and Technological Development Zone Liaohe Road Dalian 116600 China

image retrieval has been an active research topic due to its great importance in the field of image management, digital library and web searching. However, the performances of the existing approaches, including text-based or content-based image retrieval, are often unsatisfactory. Inspired by text-based image retrieval, we propose semantic-based approach, whose similarity computation is semantic relevance rather than word matching. In this paper, a novel approach of progressive image retrieval based on content and semantic is proposed. The proposed retrieval model overcomes the drawbacks of pure content-based and text-based image retrieval, which exploits the strengths of both semantic- and content-based methods, minimizing their weaknesses. Experiments demonstrate the effectiveness and efficiency of the proposed method for image retrieval. © 2011 ISSN.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

An Anisotropic Diffusion Filtering Implementation to Execute in Parallel Distributed Systems

An Anisotropic Diffusion Filtering Implementation to Execute...

引用

IEEE International Conference on Computational Science and Engineering Workshops (CSEWORKSHOPS)

作者： Antonio C. Sobieranski Leandro Coser M.A.R. Dantas Aldo v. Wangenheim Eros Comunello LAPIX-Image Processing and Graphic Computing Lab The Cyclops Group Federal University of Santa Catarina Brazil LaPeSD-Distributed Systems Research Laboratory Federal University of Santa Catarina Brazil Graduate Program Applied Computer Science Universidade do Vale do Itajaí Brazil

ISBN: (纸本)9780769532578

In this paper, we present a parallelization of a filtering algorithm related to non-linear anisotropic diffusion, used to enhance the performance of an application in a parallel distributed system. The anisotropic diffusion is a well-established technique for image enhancement by means of diffusivity functions, which act as border attenuators. However, it requires a high computational cost when a large amount of data is used. The proposed implementation was parallelized considering both point-to-point and collective communications, adopting the MPI paradigm. Results from both approaches indicate that the proposed algorithm has reached interesting levels of performance (81% and 93% of efficiency, respectively) when compared to the execution of one process in a single computer node. In addition, our results indicate an enhancement of around 21% utilizing the collective communication strategy when compared to point-to-point communication.

关键词： Filtering Magnetic separation Anisotropic magnetoresistance Ions Kernel Maximum likelihood detection Pixel

来源：评论

学校读者我要写书评

暂无评论

Portrait image segmentation based on improved grabcut algorithm 6th

Portrait image segmentation based on improved grabcut algori...

引用

6th International Conference on Swarm Intelligence, ICSI 2015 held in conjunction with the 2nd BRICS Congress on Computational Intelligence, CCI 2015

作者： Li, Shuai Zheng, Xiaohui Chen, Xianjun Zhan, Yongsong Key Laboratory of Cloud Computing and Complex System Guilin University of Electronic Technology Guilin Guangxi541004 China Guangxi Experiment Center of Information Science Guilin University of Electronic Technology Guilin Guangxi541004 China Key Laboratory of Intelligent Processing of Computer Image and Graphics Guilin University of Electronic Technology Guilin Guangxi541004 China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin Guangxi541004 China Information Engineering School Haikou College of Economics Haikou Hainan571127

ISBN: (纸本)9783319204680

Traditional computer portrait caricature system mainly take the method that exaggerate and deform real images directly, that lead the facial image background also been deformed when exaggerate facial image. If in pretreatment stage, we segmented the characters and background of the input image, and then do the subsequent processing, the problem may be solved. But for better portrait caricature effects, we need an excellent segmentation algorithm. So, we propose an improved Grabcut image segmentation algorithm and use it to extract the prospect character image for exaggeration and deformation. In practical application, we separate deform and exaggerate the foreground characters image with TPS method, then fuse it with the original or new background picture, get the final image. Application proves, the method solves the background deformation problem well, and improves the quality and rate of image segmentation, caricature synthesis effect reality and natural. © Springer International Publishing Switzerland 2015.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

An effective coaxiality measurement for twist drill based on line structured light sensor

arXiv

引用

arXiv 2021年

作者： Cheng, Ailing Ye, Jiaojiao Yang, Fei Lu, Shufang Gao, Fei The Laboratory of Graphics & Image Processing College of Computer Science and Technology Zhejiang University of Technology Zhejiang Province Hangzhou310023 China The Research Center of Intelligent Computing Software Zhejiang Lab. Zhejiang Province Hangzhou311121 China

Aiming at the accurate and effective coaxiality measurement for twist drill with irregular surface, an optical measurement mechanism is proposed in this paper. First, A high-precision rotation instrument based on four core units is designed, which can obtain the 3-D point cloud data of full angle for the twist drill. Second, in the data processing stage, an improved robust Gaussian mixture model is established for accurate and rapid blade back segmentation. To improve measurement efficiency, a rapid reconstruction method of the twist drill axis based on orthogonal synthesis is provided to locate the axial position of the maximum deviation from the benchmark by utilizing the extracted blade back data. Finally, by calculating the maximum radial Euclidean distance from the benchmark, the coaxiality error of the twist drill is obtained. Comparing with other measurement methods, experimental results show that our proposed method is effective with high precision of 3 um and high efficiency of less than 3 s/pc. The result demonstrate that the proposed method is effective, robust and automatic, it can be applied in many actual industrial scene. © 2021, CC BY.

关键词： Drills

来源：评论

学校读者我要写书评

暂无评论

Multi-Wavelength Narrow Linewidth Random Fiber Laser Based on Fiber Bragg Grating Fabry-Perot Filter

Multi-Wavelength Narrow Linewidth Random Fiber Laser Based o...

引用

International Conference on Information Science and Technology (ICIST)

作者： Sokliep Pheng Luo Xiaonan Zhongshuai Wang Yijie Zhu Zetao Jiang School of Information and Communication Guilin University of Electronic Technology Guilin China Guangxi Key Laboratory of Intelligent Processing of Computer Image and Graphics Guilin University of Electronic Technology Guilin China School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China

ISBN: (数字)9781728155586

ISBN: (纸本)9781728155593

Recently, multi-wavelength narrow linewidth random fiber laser has very interested for every researcher in this field, because of their useful advantages application, such as high-resolution spectroscopy and fiber optic sensing. In this paper, the standard single-mode fiber is used to form a half-opened cavity structure for generating the narrow linewidth random fiber laser and used the FBG-FP as a filter to form the narrow linewidth RFL into multi-wavelength. Firstly, we used the Rayleigh scattering that processed as well as in a standard single-mode fiber to provide random distribution feedback at the same time while using erbium-doped fiber (EDF) to provide the gain or amplification for achieving a broadband random laser output. Then, FBG-FP is added to the half-open cavity random laser structure. The multi-wavelength and narrow linewidth RFL can be achieved when the broadband RFL goes through the FBG-FP. In this paper we have generated the multi-wavelength narrow linewidth random fiber laser which has more than 10 wavelengths and the 3dB bandwidth is less than 0.01 nm and the mode separation of each wavelength is 0.04nm.

关键词： Fiber gratings Erbium-doped fiber lasers Optical fiber couplers Optical fiber amplifiers

来源：评论

学校读者我要写书评

暂无评论

Improved cross-media relevance model for automatic image annotation

引用

ICIC Express Letters, Part B: Applications 2012年第5期3卷 1231-1237页

作者： Song, Haiyu Li, Xiongfei Wang, Pengjie Bao, Cuizhu Liu, Yongkui Xu, Lu Institute of Computer Graphics and Image Processing Dalian Nationalities University No. 18 Liaohe Road Economic and Technological Development Zone-Dalian 116600 China Key Laboratory of Symbol Computation and Knowledge Engineering Ministry of Education Jilin University No. 2699 Qianjin Avenue Changchun 130012 China

Automatic image annotation has been an active research topic in the last decade due to its potentially large impact on image retrieval, object recognition and image understanding. Many approaches have been proposed for image annotation in recent years. The most influential annotation model is relevance model, whose representative algorithm is Cross-Media Relevance Model (CMRM). In this paper, to overcome the shortcomings of the original CMRM, we propose improved CMRM. In the improved CMRM, the annotation word distribution is estimated using binary probability, the significance of blob is discriminately depicted using TF-IDF (term frequency-inverse document frequency) schemes, and the similarity measurement of blob is based on blob and continuousvalued feature vector. The experimental results on the standard Corel5K dataset show that our proposed approach outperforms the original CMRM by about 111% and 73% in terms of F1 and N+ measures respectively. The improved CMRM can get better performance in specific domains such as cultural heritage and special necessities digitization for ethnic minorities. © 2012 ICIC International.

关键词： image retrieval

来源：评论

学校读者我要写书评

暂无评论

M3YOLOv5: Feature enhanced YOLOv5 model for mandibular fracture detection

引用

computers in Biology and Medicine 2024年 173卷 108291-108291页

作者： Zhou, Tao Wang, Hongwei Du, Yuhu Liu, Fengzhen Guo, Yujie Lu, Huiling School of Computer Science and Engineering North Minzu University Yinchuan750021 China School of Medical Information and Engineering Ningxia Medical University Yinchuan750004 China Key Laboratory of Image and Graphics Intelligent Processing of State Ethnic Affairs Commission North Minzu University Yinchuan750021 China

Background: It is very important to detect mandibular fracture region. However, the size of mandibular fracture region is different due to different anatomical positions, different sites and different degrees of force. It is difficult to locate and recognize fracture region accurately. Methods: To solve these problems, M3YOLOv5 model is proposed in this paper. Three feature enhancement strategies are designed, which improve the ability of model to locate and recognize mandibular fracture region. Firstly, Global-Local Feature Extraction Module (GLFEM) is designed. By effectively combining Convolutional Neural Network (CNN) and Transformer, the problem of insufficient global information extraction ability of CNN is complemented, and the positioning ability of the model to the fracture region is improved. Secondly, in order to improve the interaction ability of context information, Deep-Shallow Feature Interaction Module (DSFIM) is designed. In this module, the spatial information in the shallow feature layer is embedded to the deep feature layer by the spatial attention mechanism, and the semantic information in the deep feature layer is embedded to the shallow feature layer by the channel attention mechanism. The fracture region recognition ability of the model is improved. Finally, Multi-scale Multi receptive-field Feature Mixing Module (MMFMM) is designed. Deep separate convolution chains are used in this modal, which is composed by multiple layers of different scales and different dilation coefficients. This method provides richer receptive field for the model, and the ability to detect fracture region of different scales is improved. Results: The precision rate, mAP value, recall rate and F1 value of M3YOLOv5 model on mandibular fracture CT data set are 97.18%, 96.86%, 94.42% and 95.58% respectively. The experimental results show that there is better performance about M3YOLOv5 model than the mainstream detection models. Conclusion: The M3YOLOv5 model can effectiv

关键词： Fracture

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：