检索结果-内蒙古大学图书馆

Gifts from Gallery: Advancing Image Retrieval via Unsupervised Asymmetric Feature Fusion

IEEE Transactions on Multimedia 2025年

作者： Zhou, Wengang Wu, Hui Wang, Min Li, Houqiang University of Science and Technology of China CAS Key Laboratory of Technology in Geospatial Information Processing and Application System Department of Electronic Engineering and Information Science Hefei230027 China Hefei Comprehensive National Science Center Institute of Artificial Intelligence Hefei230030 China

Asymmetric retrieval systems, characterized by the deployment of models with varying capacities on platforms with differing computational and storage resources, pose a challenge in balancing retrieval efficiency and accuracy. The recent introduction of the Asymmetric Feature Fusion (AFF) paradigm has shown promise by enhancing existing asymmetric retrieval systems through feature fusion on the gallery side. However, its reliance on extensive human-annotated data hinders practical applicability. To this end, we introduce an innovative unsupervised training method tailored for AFF. Leveraging multiple gallery models as feature extractors, our approach exploits similarities among images encoded by these models as pseudolabels. For each gallery model, we calculate its adaptive weight through an in-depth exploration of contextual relationships among ranking list images in its embedding spaces. Subsequently, these weights are utilized to effectively fuse the image similarities encoded by different gallery models into a more robust one. The fused image similarities provide powerful pseudo-supervision for training AFF. Our unsupervised training approach enhances the generality and utility of AFF in real-world scenarios, particularly when labeled data is limited or expensive to obtain. Exhaustive experiments on various landmark retrieval datasets demonstrate the superiority of our method. © 1999-2012 IEEE.

关键词： Multimedia systems

来源：评论

学校读者我要写书评

暂无评论

ExpTopo: Explicit Topological Modeling for Bronchus Segmentation

ExpTopo: Explicit Topological Modeling for Bronchus Segmenta...

引用

IEEE International Symposium on Biomedical Imaging

作者： Mingyue Zhao Xiaolan Qiu S.Kevin Zhou Division of Life Sciences and Medicine School of Biomedical Engineering University of Science and Technology of China (USTC) China Center for Medical Imaging Robotics Analytic Computing & Learning (MIRACLE) Suzhou Institute for Advance Research USTC China Suzhou Key Laboratory of Microwave Imaging Processing and Application Technology Suzhou Aerospace Information Research Institute China Key Laboratory of Precision and Intelligent Chemistry University of Science and Technology of China (USTC) China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology China

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Airway extraction is paramount in the early diagnosis and treatment of respiratory diseases. As a tree-like structure, both topological-aware learning and voxel-wise classification are equally crucial for the airway. However, existing methods demonstrate insufficient topological learning, emphasizing only the supervision of individual key topological points. Consequently, this paper proposes a Explicit Topological Modeling (ExpTopo) approach to aid airway segmentation. It explicitly introduces topological metric space learning based on semantic segmentation, enhancing the model's structural perception by implementing global skeleton-level sparse topological learning (STL) and local voxel-level dense topological perception (DTP). Extensive experimental results demonstrate that the algorithm achieves competitive performance at both the topological and voxel levels. Code will be available in https://***/MorineZ/ExpTopo.

关键词： Codes Atmospheric modeling Semantic segmentation Pulmonary diseases Biological system modeling Extraterrestrial measurements Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Bell State Preparation Based on Switching Between Quantum system Models

引用

Journal of systems Science & Complexity 2017年第2期30卷 347-356页

作者： ZHOU Juan KUANG Sen CONG Shuang Department of Automation University of Science and Technology of ChinaHefei 230027China CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science

For the preparation of any target Bell state under continuous quantum measurement, this paper proposes a method which achieves the control objective by switching between two different models or by switching between two control channels under one model. Proper control Hamiltonians are selected for the two system models, a switching strategy between the two models is designed, and the stability of the whole switching system is proved in theory. For a given target Bell state, the effectiveness of the proposed switching control strategy between different models is illustrated through simulation experiments.

关键词： Bell state model switching quantum systems switching strategy.

来源：评论

学校读者我要写书评

暂无评论

A New Approach to Airborne High Resolution SAR Motion Compensation for Large Trajectory Deviations

引用

电子学报(英文版) 2012年第4期21卷 764-769页

作者： MENG Dadi HU Donghui DING Chibiao Key Laboratory of Technology in Geospatial Information Processing and Application System Chinese Academy of Sciences Beijing 100190 China Institute of Electronics Chinese Academy of Sciences Beijing 100190 China

The Two-step algorithm (TSA) is widely used for trajectory deviation compensation of airborne Synthetic aperture radar (SAR), by which most of the mo- tion errors are compensated before Range curve migration compensation (RCMC) and the residual after the RCMC. We found that the RCMC in the presence of the residual motion errors results in additional range shift errors hard to be compensated for. Based on theoretical investiga- tions, this shortage of TSA is reported and a new compen- sation scheme which greatly alleviates the RCMC induced errors is proposed. Besides, range resampling considering the residual motion errors is very convinent, which, how- ever, is boresome in TSA. The new method is effective to compensate the high resolution SAR systems for large tra- jectory deviations, which is hard to be achieved by TSA because of the uncompensated errors. Results on the sim- ulated data are provided to demonstrate the effectiveness of the new method.

关键词：机载合成孔径雷达高分辨率SAR 运动补偿弹道偏差运动误差 TSA 偏差补偿误差范围 Synthetic aperture radar (SAR), Motion compensation, Space variant.

来源：评论

学校读者我要写书评

暂无评论

Sampled-data Observer Design for a Class of Stochastic Nonlinear systems Based on the Approximate Discrete-time Models

引用

IEEE/CAA Journal of Automatica Sinica 2017年第3期4卷 507-511页

作者： Xinxin Fu Yu Kang Pengfei Li Department of Automation University of Science and Technology of China State Key Laboratory of Fire Science Department of AutomationInstitute of Advanced TechnologyUniversity of Science and Technology of China Key Laboratory of Technology in GeoSpatial Information Processing and Application System Chinese Academy of Sciences IEEE

In this paper,we studied the approximate sampleddata observer design for a class of stochastic nonlinear ***-Maruyama approximation was investigated in this paper because it is the basis of other higher precision numerical methods,and it preserves important structures of the nonlinear ***,the form of Euler-Maruyama model is simple and easy to be *** results provide a reference for sampled-data observer design method for such stochastic nonlinear systems,and may be useful to many practical control applications,such as tracking control in mechanical *** the effectiveness of the approach is demonstrated by a simulation example.

关键词： Approximation model exponentially bounded sampled-data observer stochastic nonlinear

来源：评论

学校读者我要写书评

暂无评论

RFID Cardinality Estimation Method for Intelligent Warehouse 35

RFID Cardinality Estimation Method for Intelligent Warehouse

引用

第35届中国控制会议

作者： SHEN Jingjing TAN Xiaobin WU Fan YAN Pei CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China

ISBN: (纸本)9781509009107

With the rapid development of RFID technologies,RFID has been introduced into applications such as supply chain management,inventory control,sampling inspection,3-D positioning and object ***,the reader accesses all the tags in its interrogation region while some applications may only need to identify the tags in a specified area which is smaller than the reader's interrogation *** paper concerns the essential problem of estimating cardinality of tags in the specified *** key novelty of our solution builds on an estimation synopsis that can capture key counting information by moving the reader as well as a simple *** the help of this data structure,a BS can be obtained which only contains the target *** computing the number of 1 in the BS,we can easily get cardinality |E| of the tags in the specified *** conduct extensive experiments to examine this design and the results shows that our solution achieves high *** it not requires any modification of tags and can be implemented with only one reader and some passive RFID tags,the proposed method is easy to deploy in a practical system.

关键词： Cardinality estimation RFID tags algorithm design

来源：评论

学校读者我要写书评

暂无评论

Planar near-field to far-field transformation for massive MIMO systems 34

Planar near-field to far-field transformation for massive MI...

引用

第三十四届中国控制会议

作者： HAN Xiangzi TAN Xiaobin WU Fan CAS Key laboratory of Technology in Geo-spatial Information Processing and Application System School of Information Science and Technology University of Science and Technology of China

ISBN: (纸本)9781467374439

The massive or large scaled multiple input multiple output(MIMO) systems have gained huge consideration due to high achievable data rates, reliable system performance and advantaged energy efficiency for future wireless networks. For such systems, we should have a keen knowledge of the channel model, the ways of configuration, spectral efficiency and so on. The obtaining of the far-field pattern in the massive MIMO system from measurements made in the near-field has attracted widespread attention recently. In this article, two basic techniques for accomplishing this have been proposed. In the first technique, the NTFF(near-field to far-field) transformation is based on the equivalence principle. While in the second technique, it is based on the plane wave spectrum(PWS) expansion. Both of the methods have their own advantages for the massive MIMO systems. One can drastically reduce the computation time and the other can make enormous reduction in the storage consumption. Experimental results show that the two transformation techniques are proved to be feasible and they are consistent with each other.

关键词： massive MIMO,NTFF transformation,the equivalence principle,PWS expansion

来源：评论

学校读者我要写书评

暂无评论

Rapid face image retrieval with pose-based local features and multi-reference re-ranking

引用

Journal of Computational information systems 2013年第1期9卷 223-230页

作者： Zhen, Haiyang Zeng, Lingzi Zhang, Rong Yin, Dong Department of Electronic Eng. and Information Science University of Science and Technology of China Hefei 230027 China Key Laboratory of Geospatial Information Processing and Application System Technology Chinese Academy of Sciences Beijing 100190 China

The performance of state-of-art image retrieval systems using Bag-of-Words representation and textual retrieval methods degrades quickly when applied to face images because their local features can not suffer variations of illumination, pose and expression of human face. Moreover, most discriminative facial features are typically high-dimensional and global, and not suitable for rapid retrieval. Motivated by the observation that local features and global features are complementary, we propose a rapid face image retrieval approach using both local and global features in this paper. To ensure the high speed of retrieval, an inverted index is built by quantizing pose-based local features specially designed for face images on component level. Candidate images with low precision and high recall can be obtained using inverted index of visual words in the retrieval stage. Global facial features and multi-reference method are used to obtain a final retrieval list with high precision. Experiments on a 160k face dataset downloaded from the internet show our approach can achieve a high precision and a high speed. © 2013 Binary information Press.

关键词： Indexing (of information)

来源：评论

学校读者我要写书评

暂无评论

Geometry-aware image completion via multiple examples 22

Geometry-aware image completion via multiple examples

引用

22nd Pacific Conference on Computer Graphics and applications, PG 2014

作者： Wang, Guihang Chen, Xuejin Hu, Siyu CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China China

ISBN: (纸本)9783905674736

When browsing through photographs taken during a trip, it can be a distressing discovery to find many other bystanders captured within the frame. A visually compelling snapshot preserves the desired subject in the foreground, and eliminates irrelevant persons or objects. In this paper, we present a new image completion algorithm that retains the geometric consistency of the scene using Internet photo collections. Our key insight allows us to successfully fill the missing regions with content derived from related images with distinct features, or from visible parts of the input image with repetitive textures. The final composition for the missing regions is guided by a confidence map combining the two types of example images. We validate our algorithm on a variety of scenes which are challenging for state-of-the-art completion techniques. The completion results successfully preserve the geometry consistency for complex structures in a wide range of depths. © The Eurographics Association 2014.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Human Machine Joint Decision Making in Distorted Surveillance Scenario 2

Human Machine Joint Decision Making in Distorted Surveillanc...

引用

2nd China Symposium on Cognitive Computing and Hybrid Intelligence, CCHI 2019

作者： Liu, Sen Zhao, Shuxin Pang, Yingxue Chen, Zhibo CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

ISBN: (纸本)9781728140919

There is plenty of human-machine joint decision-making scenarios in the real world applications, such as driving assistant, suspect identification, medical diagnosis, etc. Existing algorithms propose that machine should give a rejection option when having a high risk or uncertainty score so that the input can be passed to human to make the decision. This is an interesting algorithmic model of human-machine collaboration, but implicitly assumes that humans are more trustworthy than machines. Such an assumption ignores the bias and inconsistency of human, especially in scenarios where machines have superior recognition ability than humans. In this work, we investigate the human-machine joint decision-making problem in distorted surveillance videos, where machines experimentally prove to be comparable to human beings in tolerance to distortion, sometimes even stronger. We propose a new human-machine joint decision-making framework by considering both the confidences of machine and human. To obtain the confidence of human, we build a real-life human decision-making database and propose a deep neural network to estimate human's confidence. Then, confidence alignment method and decision rule are proposed to further output the final decision. Experiments demonstrate that the proposed framework can make less human intervention and more accurate decisions in several human-machine joint decision-making scenarios. © 2019 IEEE.

关键词： Deep neural networks

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：