检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Wan, Jun Lin, Chi Wen, Longyin Li, Yunan Miao, Qiguang Escalera, Sergio Anbarjafari, Gholamreza Guyon, Isabelle Guo, Guodong Li, Stan Z. National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China JD Finance Mountain ViewCA United States University of Southern California Los AngelesCA90089-0911 United States School of Computer Science and Technology Xidian University & Xi'an Key Laboratory of Big Data and Intelligent Vision 2nd South Taibai Road Xi'an710071 China Universitat de Barcelona Computer Vision Center Spain iCV Lab Institute of Technology University of Tartu Estonia Faculty of Engineering Hasan Kalyoncu University Gaziantep Turkey Institute of Digital Technologies Loughborough University London United Kingdom ChaLearn United States University Paris-Saclay France institute of Deep Learning Baidu Research National Engineering Laboratory for Deep Learning Technology and Application China

The ChaLearn large-scale gesture recognition challenge has been run twice in two workshops in conjunction with the International Conference on Pattern Recognition (ICPR) 2016 and International Conference on Computer Vision (ICCV) 2017, attracting more than 200 teams around the world. This challenge has two tracks, focusing on isolated and continuous gesture recognition, respectively. This paper describes the creation of both benchmark datasets and analyzes the advances in large-scale gesture recognition based on these two datasets. We discuss the challenges of collecting large-scale ground-truth annotations of gesture recognition, and provide a detailed analysis of the current state-of-the-art methods for large-scale isolated and continuous gesture recognition based on RGB-D video sequences. In addition to recognition rate and mean jaccard index (MJI) as evaluation metrics used in our previous challenges, we also introduce the corrected segmentation rate (CSR) metric to evaluate the performance of temporal segmentation for continuous gesture recognition. Furthermore, we propose a bidirectional long short-term memory (Bi-LSTM) baseline method, determining the video division points based on the skeleton points extracted by convolutional pose machine (CPM). Experiments demonstrate that the proposed Bi-LSTM outperforms the state-of-the-art methods with an absolute improvement of 8.1% (from 0.8917 to 0.9639) of CSR. Copyright © 2019, The Authors. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Domain-Aware SE network for Sketch-Based Image Retrieval with Multiplicative Euclidean Margin Softmax

arXiv

引用

arXiv 2018年

作者： Lu, Peng Yang, Wenming Huang, Gao Guo, Guodong Lin, Hangyu Fu, Yanwei Shenzhen International Graduate School Tsinghua University Shenzhen China Shenzhen International Graduate School Department of Electronic Engineering Tsinghua University Shenzhen China Department of Automation Tsinghua University Beijing China IDL Baidu Research National Engineering Lab for Deep Learning Technology and Application Beijing China School of Data Science Fudan University Shanghai China

This paper proposes a novel approach for Sketch-Based Image Retrieval (SBIR), for which the key is to bridge the gap between sketches and photos in terms of the data representation. Inspired by channel-wise attention explored in recent years, we present a Domain-Aware Squeeze-and-Excitation (DASE) network, which seamlessly incorporates the prior knowledge of sample sketch or photo into SE module and make the SE module capable of emphasizing appropriate channels according to domain signal. Accordingly, the proposed network can switch its mode to achieve a better domain feature with lower intra-class discrepancy. Moreover, while previous works simply focus on minimizing intra-class distance and maximizing inter-class distance, we introduce a loss function, named Multiplicative Euclidean Margin Softmax (MEMS), which introduce multiplicative Euclidean margin into feature space and ensure that the maximum intra-class distance is smaller than the minimum inter-class distance. This facilitates learning a highly discriminative feature space and ensures a more accurate image retrieval result. Extensive experiments are conducted on two widely used SBIR benchmark datasets. Our approach achieves better results on both datasets, surpassing the state-of-the-art methods by a large margin. Copyright © 2018, The Authors. All rights reserved.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Aggregation Signature for Small Object Tracking

arXiv

引用

arXiv 2019年

作者： Liu, Chunlei Ding, Wenrui Yang, Jinyu Murino, Vittorio Zhang, Baochang Han, Jungong Guo, Guodong School of Electrical and Information Engineering Beihang University Beijing China Unmanned System Research Institute Beihang University Beijing China School of Computer Science University of Birmingham British United Kingdom University of Verona Verona Italy Pattern Analysis and Computer Vision department Istituto Italiano di Tecnologia Genoa Italy School of Automation Science and Electrical Engineering Beihang University Beijing China Shenzhen Academy of Aerospace Technology Shenzhen China WMG Data Science Group University of Warwick CoventryCV4 7AL United Kingdom Institute of Deep Learning Baidu Research and National Engineering Laboratory for Deep Learning Technology and Application

—Small object tracking becomes an increasingly important task, which however has been largely unexplored in computer vision. The great challenges stem from the facts that: 1) small objects show extreme vague and variable appearances, and 2) they tend to be lost easier as compared to normal-sized ones due to the shaking of lens. In this paper, we propose a novel aggregation signature suitable for small object tracking, especially aiming for the challenge of sudden and large drift. We make three-fold contributions in this work. First, technically, we propose a new descriptor, named aggregation signature, based on saliency, able to represent highly distinctive features for small objects. Second, theoretically, we prove that the proposed signature matches the foreground object more accurately with a high probability. Third, experimentally, the aggregation signature achieves a high performance on multiple datasets, outperforming the state-of-the-art methods by large margins. Moreover, we contribute with two newly collected benchmark datasets, i.e., small90 and small112, for visually small object tracking. The datasets will be available in https://***/bczhangbczhang/. Copyright © 2019, The Authors. All rights reserved.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Experimental and Numerical Study on the Compressive Behaviour of Cfrp-Confined Columns with Recycled Waste Concrete

SSRN

引用

SSRN 2024年

作者： Xu, Y. Wang, Xin Dong, Jiangfeng Guan, Zhongwei Wang, Qingyuan Key Laboratory of C & PC Structures Ministry of Education National and Local Unified Engineering Research Center for Basalt Fiber Production and Application Technology Southeast University Nanjing211189 China MOE Key Laboratory of Deep Earth Science and Engineering School of Architecture and Environment Sichuan University Chengdu610065 China Sichuan Provincial Engineering Research Center of City Solid Waste Energy and Building Materials Conversion and Utilization Technology Chengdu University Chengdu610106 China Advanced Materials Research Centre TII Abu Dhabi United Arab Emirates

This study investigates how externally wrapping CFRP enhances the mechanical and structural performance of recycled concrete structures, aiming to optimize the use of recycled aggregate concrete in civil engineering. Here, an experimental and numerical study is undertaken on the axial compressive behaviour of 30 RAC columns and 15 BFRC columns confined by CFRP sheets. The study focuses on effects of RCA replacement ratio, cross-sectional shape, CFRP wrapping form and BF addition on the compressive properties of specimens. The results show that the increase of RCA replacement ratio leads to the decrease of the ultimate hoop strain by 15.2~47.8%. The partial and full wrapping of CFRP, as well as the number of layers, significantly affect the bearing capacity and axial deformation capacity of column specimens. The partial and full wrappings of CFRP provide the enhancements of the ultimate bearing capacity by 80~153% and 119~206%, and the ultimate axial displacement by 49~113% and 15~75%, respectively. Also, single-layer and double-layer CFRP confinements offer the corresponding enhancements by 80~150% and 124~206%, and 15~50% and 27~113%, respectively. Moreover, with a uniform confinement, the enhancement rate on the ultimate strain and bearing capacity of the circular column specimens is higher than the square column counterparts. The addition of BF can further improve the axial compression performance of the core RAC column well, also inhibit the confinement of CFRP. In addition, the ultimate bearing capacity model and the finite element model of RAC confined by CFRP are established, which are validated against the experimental results with good correlation. © 2024, The Authors. All rights reserved.

关键词： Bearing capacity

来源：评论

学校读者我要写书评

暂无评论

Transformer-based Annotation Bias-aware Medical Image Segmentation

arXiv

引用

arXiv 2023年

作者： Liao, Zehui Xie, Yutong Hu, Shishuai Xia, Yong National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an710072 China Australian Institute for Machine Learning The University of Adelaide AdelaideSA Australia Ningbo Institute of Northwestern Polytechnical University Ningbo315048 China Research and Development Institute Northwestern Polytechnical University in Shenzhen Shenzhen518057 China

Manual medical image segmentation is subjective and suffers from annotator-related bias, which can be mimicked or amplified by deep learning methods. Recently, researchers have suggested that such bias is the combination of the annotator preference and stochastic error, which are modeled by convolution blocks located after decoder and pixel-wise independent Gaussian distribution, respectively. It is unlikely that convolution blocks can effectively model the varying degrees of preference at the full resolution level. Additionally, the independent pixel-wise Gaussian distribution disregards pixel correlations, leading to a discontinuous boundary. This paper proposes a Transformer-based Annotation Bias-aware (TAB) medical image segmentation model, which tackles the annotator-related bias via modeling annotator preference and stochastic errors. TAB employs the Transformer with learnable queries to extract the different preference-focused features. This enables TAB to produce segmentation with various preferences simultaneously using a single segmentation head. Moreover, TAB takes the multivariant normal distribution assumption that models pixel correlations, and learns the annotation distribution to disentangle the stochastic error. We evaluated our TAB on an OD/OC segmentation benchmark annotated by six annotators. Our results suggest that TAB outperforms existing medical image segmentation models which take into account the annotator-related bias. © 2023, CC BY-NC-ND.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

ACQUISITION REFORM AND BEST PRODUCT PROCUREMENT - AN engineering VIEW

引用

NAVAL ENGINEERS JOURNAL 1994年第6期106卷 41-57页

作者： FISHER, DA SKOLNICK, A He has been involved with several weapon system developments. Among these were the Trident II fire control and navigation systems the BSY-I Anti-Submarine Warfare System and the Navy standard computers (UYK44 and EMSP). He served as manager of the Digital Circuits Engineering Branch and was then appointed as manager of the Automatic Test Equipment (ATE) Technology Division. As manager of the ATE Technology Division he was responsible for the SP-23 Fire Control System Support Project the SP-24 Navigation Project and the Fleet Progressive Maintenance Program (2M/ATE). This Division was responsible for selection and application of electronic product technology and for developing fleet test and repair techniques. He holds a B.S. in Electrical Engineering from the University of Evansville and is currently pursuing a Masters of Public Administration at Indiana University-Purdue University Indianapolis. Dr. Alfred Skolnick:retired from the Navy in 1983 with the rank of captain. He is president of System Science Consultants (SSC) specializing in strategic planning technical program definition technology assessment and engineering analyses on selected matters of national interest. Dr. Skolnick taught mathematics and management sciences at University of Virginia and Marymount University. He is adjunct faculty at Northern Virginia Community College. From 1985 to 1989 he was president of the American Society of Naval Engineers. In the Navy he served at Applied Physics Laboratory/The Johns Hopkins University then aboard USSBoston(CAG-1) and played leading roles in several weapon system developments inertial navigation (Polaris) deep submergence (DSRV) and advanced ship designs (SES). He later was director Combat System Integration Naval Sea Systems Command and head Combat Projects Naval Ship Engineering Center. In 1975 he became a major project manager and led the Navy's High Energy Lasers Program in 1981 he was assigned all Navy Directed Energy Weapons development efforts. He was vice president advanced tech

The military services are being moved in the direction of performance-based specifications and standards. They are being steered against dictating ''how to'' produce an item since such action forecloses on the ability to gain access to components or technology that may have a commercial equivalent. Why should the engineering community embrace the new approach? Aside from the obvious weight of it being approved policy, therefore currently mandated, it warrants examination because it is the correct approach at this time when applied to appropriate products. Military specifications and standards are to be displaced then, by acceptable alternative contractor design solutions. Industry bidders will be allowed to propose the particular design details, permitting procurement flexibility by contractually citing only system level or interface requirements, both physical and functional. Hopefully, this can broaden the industrial base and increase competition with reduced costs to follow. Conceptually, the approach appears both performance-sensible and cost-attractive (there are, of course, consequent risks) but how does implementation proceed? Is it possible to pursue the goals envisioned along paths that are not in themselves experimental? Can the American postulate, minimal loss of life and limb to U.S. military people, continue to be honored? Experience and track record elsewhere imply encouraging possibilities in select situations-useful prospects are identified and discussed in practical terms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to "Effect of konjac glucomannan with different viscosity on the quality of surimi wheat dough and noodles" [Int. J. Biol. Macromol. 221 (2022) 1228-1237]

引用

International journal of biological macromolecules 2024年第PT 1期271卷 132607页

作者： Geng Cao Xueting Chen Nan Wang Jie Tian Shuang Song Xinyu Wu Lei Wang Chengrong Wen Collaborative Innovation Center of Seafood Deep Processing National Engineering Research Center of Seafood National & Local Joint Engineering Laboratory for Marine Bioactive Polysaccharide Development and Application School of Food Science and Technology Dalian Polytechnic University Dalian 116034 China. School of Chemistry and Food Science Yulin Normal University Yulin 573000 China. Collaborative Innovation Center of Seafood Deep Processing National Engineering Research Center of Seafood National & Local Joint Engineering Laboratory for Marine Bioactive Polysaccharide Development and Application School of Food Science and Technology Dalian Polytechnic University Dalian 116034 China. Electronic address: wencr2014@***.

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to "Effect of ultrasound-assisted resting on the quality of surimi-wheat dough and noodles" [Ultrason. Sonochem. 94 (2023) 106322]

引用

Ultrasonics sonochemistry 2024年 107卷 106921页

作者： Geng Cao Xueting Chen Bingbing Hu Zuoqian Yang Man Wang Shuang Song Lei Wang Chengrong Wen Collaborative Innovation Center of Seafood Deep Processing National Engineering Research Center of Seafood National & Local Joint Engineering Laboratory for Marine Bioactive Polysaccharide Development and Application School of Food Science and Technology Dalian Polytechnic University Dalian 116034 China. School of Chemistry and Food Science Yulin Normal University Yulin 573000 China. Collaborative Innovation Center of Seafood Deep Processing National Engineering Research Center of Seafood National & Local Joint Engineering Laboratory for Marine Bioactive Polysaccharide Development and Application School of Food Science and Technology Dalian Polytechnic University Dalian 116034 China. Electronic address: wencr2014@***.

来源：评论

学校读者我要写书评

暂无评论

Impact of pulsation frequency and pressure amplitude on the evolution of coal pore structures during gas fracturing

引用

Fuel 2020年 268卷

作者： Yingke Liu Xiaojiang Wen Mingjun Jiang Zhihong He Jianhong Kang Feng Gao Fubao Zhou Mingyao Wei Xiangzhong Liu Key Laboratory of Gas and Fire Control for Coal Mines (Ministry of Education) China University of Mining & Technology Xuzhou Jiangsu 221116 China Jiangsu Key Laboratory of Fire Safety in Urban Underground Space (China University of Mining and Technology) Xuzhou Jiangsu 221116 China Faculty of Safety Engineering China University of Mining & Technology Xuzhou Jiangsu 221116 China Xishan Coal Electricity Group Co. Ltd Taiyuan Shanxi 030024 China State Key Laboratory for Geomechanics & Deep Underground Engineering China University of Mining & Technology Xuzhou Jiangsu Province 221116 China National and Local Joint Engineering Laboratory of Internet Application Technology on Mine IoT Perception Mine Research Center China University of Mining and Technology Xuzhou Jiangsu 221116 China

Pulse gas fracturing (PGF) is a method of injecting high-pressure gas into coal cyclically to stimulate the coalbed methane reservoir. However, the evolution of coal pore structure during pulse gas fracturing is still unclear, especially when the injection pressure is lower than the breakdown pressure of coal. In this paper, 11 groups of PGF experiments with the injection pressure amplitude no more than 8 MPa were carried out on coal. Furthermore, the pore size distribution and the crack morphology of coal samples before and after PGF were observed. The experimental results show that pulse gas fracturing with relatively lower injection pressure increases the total pore volume and the permeability exponentially. Moreover, with the increase of pulsation frequency or of injection pressure amplitude, the volume of macropores and its proportion in total pore volume rise significantly, and the increasing rate gradually grows. However, the mesopore volume and its proportion in the total pore volume go up with the increase of pulsation frequency, but remain basically unchanged with the rise of injection pressure amplitude. Besides, the volume of micropores and transition pores slightly fluctuates. In addition, PGF hardly generate wide main fractures in the coal body, and instead mainly causes the tip of pores to propagate and induces substantial micro-cracks. The accumulation of irreversible deformation such as plastic deformation of pores and propagation of micro-cracks is the fundamental cause why the total pore volume and the permeability of coal grow continuously. The research results lay a foundation for understanding the fracturing effect of PGF.

关键词： Pulse gas fracturing Pore size distribution Pulsation frequency Injection pressure amplitude Coal

来源：评论

学校读者我要写书评

暂无评论

Sketch-based Medical Image Retrieval

arXiv

引用

arXiv 2023年

作者： Kobayashi, Kazuma Gu, Lin Hataya, Ryuichiro Mizuno, Takaaki Miyake, Mototaka Watanabe, Hirokazu Takahashi, Masamichi Takamizawa, Yasuyuki Yoshida, Yukihiro Nakamura, Satoshi Kouno, Nobuji Bolatkan, Amina Kurose, Yusuke Harada, Tatsuya Hamamoto, Ryuji Division of Medical AI Research and Development National Cancer Center Research Institute 5-1-1 Tsukiji Chuo-ku Tokyo104-0045 Japan Cancer Translational Research Team RIKEN Center for Advanced Intelligence Project 1-4-1 Nihonbashi Chuo-ku Tokyo103-0027 Japan Machine Intelligence for Medical Engineering Team RIKEN Center for Advanced Intelligence Project 1-4-1 Nihonbashi Chuo-ku Tokyo103-0027 Japan Research Center for Advanced Science and Technology The University of Tokyo 4-6-1 Komaba Meguro-ku Tokyo153-8904 Japan Medical Data Deep Learning Team Advanced Data Science Project RIKEN Information R&D and Strategy Headquarters 1-4-1 Nihonbashi Chuo-ku Tokyo103-0027 Japan Department of Experimental Therapeutics National Cancer Center Hospital 5-1-1 Tsukiji Chuo-ku Tokyo104-0045 Japan Department of Diagnostic Radiology National Cancer Center Hospital 5-1-1 Tsukiji Chuo-ku Tokyo104-0045 Japan Department of Neurosurgery and Neuro-Oncology National Cancer Center Hospital 5-1-1 Tsukiji Chuo-ku Tokyo104-0045 Japan Department of Colorectal Surgery National Cancer Center Hospital 5-1-1 Tsukiji Chuo-ku Tokyo104-0045 Japan Department of Thoracic Surgery National Cancer Center Hospital 5-1-1 Tsukiji Chuo-ku Tokyo104-0045 Japan Radiation Safety and Quality Assurance Division National Cancer Center Hospital 5-1-1 Tsukiji Chuo-ku Tokyo104-0045 Japan Division of Research and Development for Boron Neutron Capture Therapy National Cancer Center Exploratory Oncology Research & Clinical Trial Center 5-1-1 Tsukiji Chuo-ku Tokyo104-0045 Japan Medical Physics Laboratory Division of Health Science Graduate School of Medicine Osaka University Yamadaoka 1-7 Osaka Suita-shi565-0871 Japan Department of Surgery Kyoto University Graduate School of Medicine 54 Shogoin Kawahara-cho Sakyo-ku Kyoto606-8507 Japan

The amount of medical images stored in hospitals is increasing faster than ever;however, utilizing the accumulated medical images has been limited. This is because existing content-based medical image retrieval (CBMIR) systems usually require example images to construct query vectors;nevertheless, example images cannot always be prepared. Besides, there can be images with rare characteristics that make it difficult to find similar example images, which we call isolated samples. Here, we introduce a novel sketch-based medical image retrieval (SBMIR) system that enables users to find images of interest without example images. The key idea lies in feature decomposition of medical images, whereby the entire feature of a medical image can be decomposed into and reconstructed from normal and abnormal features. By extending this idea, our SBMIR system provides an easy-to-use two-step graphical user interface: users first select a template image to specify a normal feature and then draw a semantic sketch of the disease on the template image to represent an abnormal feature. Subsequently, it integrates the two kinds of input to construct a query vector and retrieves reference images with the closest reference vectors. Using two datasets, ten healthcare professionals with various clinical backgrounds participated in the user test for evaluation. As a result, our SBMIR system enabled users to overcome previous challenges, including image retrieval based on fine-grained image characteristics, image retrieval without example images, and image retrieval for isolated samples. Our SBMIR system achieves flexible medical image retrieval on demand, thereby expanding the utility of medical image databases. Copyright © 2023, The Authors. All rights reserved.

关键词： Search engines

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：