检索结果-内蒙古大学图书馆

Multi-View Graph Embedding Learning for Image Co-Segmentation and Co-Localization

IEEE Transactions on Circuits and Systems for Video Technology 2024年第6期34卷 4942-4956页

作者： Huang, Aiping Li, Lijian Zhang, Le Niu, Yuzhen Zhao, Tiesong Lin, Chia-Wen Fuzhou University Fujian Key Laboratory for Intelligent Processing and Wireless Transmission of Media Information College of Physics and Information Engineering Fuzhou350108 China Fuzhou University Fujian Key Laboratory of Network Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou350108 China University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China Fuzhou University Fujian Key Laboratory for Intelligent Processing and Wireless Transmission of Media Information College of Physics and Information Engineering The Fujian Science and Technology Innovation Laboratory for Optoelectronic Information Fuzhou350108 China Institute of Communications Engineering National Tsing Hua University Department of Electrical Engineering Hsinchu30013 Taiwan

Image co-segmentation and co-localization exploit inter-image information to identify and extract foreground objects with a batch mode. However, they remain challenging when confronted with large object variations or complex backgrounds. This paper proposes a multi-view graph embedding (MV-Gem) learning scheme which integrates diversity, robustness and discernibility of object features to alleviate this phenomenon. To encourage the diversity, the deep co-information containing both low-layer general representations and high-layer semantic information is generated to form a multi-view feature pool for comprehensive co-object description. To enhance the robustness, a multi-view adaptive weighted learning is formulated to fuse the deep co-information for feature complementation. To ensure the discernibility, the graph embedding and sparse constraint are embedded into the fusion formulation for feature selection. The former aims to inherit important structures from multiple views, and the latter further selects important features to restrain irrelevant backgrounds. With these techniques, MV-Gem gradually recovers all co-objects through optimization iterations. Extensive experimental results on real-world datasets demonstrate that MV-Gem is capable of locating and delineating co-objects in an image group. © 1991-2012 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

UAV Visual Tracking Algorithm Based on Feature Fusion of the Attention Mechanism 5

UAV Visual Tracking Algorithm Based on Feature Fusion of the...

引用

5th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2022

作者： Ma, Sugang Zhang, Zixian Zhao, Zhixian Yang, Xiaobao Hou, Zhiqiang School of Computer Science and Technology Xi'an University of Posts and Telecommunications Shaanxi Xi'an China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an University of Posts and Telecommunications Shaanxi Xi'an China Xi'an Key Laboratory of Big Data and Intelligent Computing Xi'an University of Posts and Telecommunications Shaanxi Xi'an China

ISBN: (纸本)9781450396899

To enhance the expression ability of deep features and improve the tracking performance of the fully convolutional siamese network (SiamFC) in the UAV scene, we propose a UAV visual tracking algorithm based on feature fusion of the attention mechanism. By designing the local perception attention module and the global perception attention module to enhance the features extracted from the backbone network, a set of complementary local enhanced features and global enhanced features are obtained. And then, the tracking response map fused with the two features is then located, which effectively improves the tracking robustness of SiamFC in the UAV scene. The algorithm and nine other related algorithms such as SiamFC are tested on the DTB70 dataset. The experiments show that the algorithm has a good tracking performance and can adapt to the visual object tracking task in the UAV scene. © 2022 ACM.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

MULTI-GRANULARITY REPRESENTATION LEARNING FOR SKETCH-BASED DYNAMIC FACE IMAGE RETRIEVAL

arXiv

引用

arXiv 2023年

作者： Wang, Liang Dai, Dawei Fu, Shiyu Wang, Guoyin Key Laboratory of Big Data Intelligent Computing School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing China

In specific scenarios, face sketch can be used to identify a person. However, drawing a face sketch often requires exceptional skill and is time-consuming, limiting its widespread applications in actual scenarios. The new framework of sketch less face image retrieval (SLFIR)[1] attempts to overcome the barriers by providing a means for humans and machines to interact during the drawing process. Considering SLFIR problem, there is a large gap between a partial sketch with few strokes and any whole face photo, resulting in poor performance at the early stages. In this study, we propose a multigranularity (MG) representation learning (MGRL) method to address the SLFIR problem, in which we learn the representation of different granularity regions for a partial sketch, and then, by combining all MG regions of the sketches and images, the final distance was determined. In the experiments, our method outperformed state-of-the-art baselines in terms of early retrieval on two accessible datasets. Codes are available at https://***/ddw2AIGROUP2CQUPT/MGRL. Copyright © 2023, The Authors. All rights reserved.

关键词： Image retrieval

来源：评论

学校读者我要写书评

暂无评论

Burst-Sensitive Traffic Forecast Via Multi-Property Personalized Fusion in Federated Learning

引用

IEEE Transactions on Mobile computing 2025年第7期24卷 5598-5614页

作者： Xue, Jingjing Sun, Sheng Liu, Min Wang, Yuwei Meng, Xuying Wang, Jingyuan Zhang, JunBo Xu, Ke Chinese Academy of Sciences University of Chinese Academy of Sciences Institute of Computing Technology Beijing China Chinese Academy of Sciences Institute of Computing Technology Beijing China Beihang University School of Computer Science and Engineering China Beihang University MIIT Key Laboratory of Data Intelligence and Management Beijing China JD Technology JD iCity China JD Intelligent Cities Research China Tsinghua University Department of Computer Science and Technology Beijing China Zhongguancun Laboratory Beijing China

For distributed network traffic prediction with data localization and privacy protection, Federated Learning (FL) enables collaborative training without raw data exchange across Base Stations (BSs). Nevertheless, traffic across BSs exhibit inherently heterogeneous trend burst and smooth fluctuation properties, but existing FL methods model single-scale series from only one view, which cannot simultaneously capture diverse trend and fluctuation properties, especially distinct burst distributions. In this paper, we propose Personalized Federated Forecasting with Multi-property Self-fusion (P2FMS), which can represent multi-scale traffic properties from different views. With precise multi-property representations, a fusion-level prediction decision is learned for each client in a personalized manner to promptly sense traffic bursts and improve forecasting performance in non-IID settings. Specifically, P2FMS decomposes the traffic series into distinct time scales, based on which, we effectively extract closeness, period, and trend properties from different views. The closeness and period are embedded through global-view representations with spatial correlations, while non-stationary trends are individually fitted from the client-side view. Furthermore, a personalized combiner is designed to accurately quantify the proportion of general fluctuation raws (i.e., closeness and period) and specific trend property in predictions, which enables multi-property self-fusion for each client to accommodate heterogeneous traffic patterns and enhance prediction accuracy. Besides, an alternant training mechanism is introduced to optimize property representation and fusion modules with the convergence guarantee. Extensive experiments on real-world datasets show that P2FMS outperforms status quo methods in both prediction performance and convergence time. © 2002-2012 IEEE.

关键词： Weather forecasting

来源：评论

学校读者我要写书评

暂无评论

Travel Characteristics and Combination Choice Behavior Modeling of Passengers under the Influence of Epidemic Prevention Policies 24

Travel Characteristics and Combination Choice Behavior Model...

引用

24th COTA International Conference of Transportation Professionals: Resilient, intelligent, Connected, and Lowcarbon Multimodal Transportation, CICTP 2024

作者： Zhang, Yue Dong, Chunjiao Li, Penghui Dong, Qianru Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport School of Traffic and Transportation Beijing Jiaotong Univ. Beijing China State Key Laboratory of Intelligent Vehicle Safety Technology China Automotive Engineering Research Institute Co. Ltd. Chongqing China

ISBN: (数字)9780784485484

ISBN: (纸本)9780784485484

The intermodal travel characteristics and combination selection behaviors of passengers are key issues to providing reasonable, efficient, and safe solutions, ensuring the traffic order, and improving quality. With the Beijing Winter Olympics as a background, by combining the Stated Preference and Revealed Preference surveys, the research develops a decision-making behavior model based on nested logit to investigate the passenger travel choices. The impacts of individual attributes, epidemic prevention policies, and preferential measures on the choice of intermodal travel, as well as the combination of departure time and travel mode, are studied. The results show that cultural and creative products have a significant impact on the combined travel choices. The cultural and creative products and consumer vouchers have a significant impact on the choice of intermodal travel. The research results can provide insights into traffic organization and management policies during large-scale events. © ASCE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Recurrence Risk Prediction for Differentiated Thyroid Cancer Using Local Clustering Contrastive Learning

Deep Learning-Based Recurrence Risk Prediction for Different...

引用

Medical Artificial Intelligence (MedAI), IEEE International Conference on

作者： Junhao Zhu Pengbo Gao Feng Hu Hong Yu Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and Telecommunications Chongqing China Chongqing Key Laboratory of Computational Intelligence Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and Telecommunications Chongqing China

ISBN: (数字)9798350377613

ISBN: (纸本)9798350377620

Thyroid cancer incidence in women has risen sharply in China from 2000 to 2016. Differentiated thyroid cancer has a relatively low mortality rate but a higher recurrence rate. The American Thyroid Association (ATA) risk model, based on traditional clinical and pathological parameters, may not fully capture all factors affecting recurrence risk. Deep learning technology has shown potential in predicting recurrence in patients with well-differentiated thyroid cancer, but its application to heterogeneous tabular medical data remains challenging. We propose a local clustering contrastive learning method to address the challenges of applying deep learning to tabular medical data. This method divides features into random subsets, performs clustering within each subset, generates positive and negative sample pairs, and trains encoders and a decoder to maximize the InfoNCE output. The learned feature representation is used for downstream classification tasks. The proposed method was applied to a retrospective cohort of 383 patients diagnosed with thyroid cancer at a medical center. Experimental verification on this dataset and ten public tabular datasets demonstrated the effectiveness of the method in risk-stratifying patients with well-differentiated thyroid cancer. The proposed local clustering contrastive learning method effectively leverages the complexity of tabular medical data, enhancing the learned feature representation and enabling accurate recurrence risk prediction for well-differentiated thyroid cancer. This approach can assist doctors in making personalized treatment decisions, such as the necessity, dosage, and frequency of radioactive iodine treatment, ultimately improving patient care.

关键词： Deep learning Pathology Thyroid cancer Decision making Contrastive learning Predictive models data models Risk management Medical diagnostic imaging Thyroid

来源：评论

学校读者我要写书评

暂无评论

Diabetic retinopathy identification based on multi-sourcefree domain adaptation

引用

International Journal of Ophthalmology(English edition) 2024年第7期17卷 1193-1204页

作者： Guang-Hua Zhang Guang-Ping Zhuo Zhao-Xia Zhang Bin Sun Wei-Hua Yang Shao-Chong Zhang School of Big Data Intelligent Diagnosis&Treatment Industry Taiyuan UniversityTaiyuan 030032Shanxi ProvinceChina Shanxi Key Laboratory of Intelligent Optimization Computing and Blockchain Technology Taiyuan Normal UniversityTaiyuan 030619Shanxi ProvinceChina Shanxi Eye Hospital Taiyuan 030002Shanxi ProvinceChina College of Computer Science and Technology Taiyuan Normal UniversityTaiyuan 030619Shanxi ProvinceChina Shenzhen Eye Institute Shenzhen Eye HospitalJinan UniversityShenzhen 518040Guangdong ProvinceChina

AIM:To address the challenges of data labeling difficulties,data privacy,and necessary large amount of labeled data for deep learning methods in diabetic retinopathy(DR)identification,the aim of this study is to develop a source-free domain adaptation(SFDA)method for efficient and effective DR identification from unlabeled ***:A multi-SFDA method was proposed for DR *** method integrates multiple source models,which are trained from the same source domain,to generate synthetic pseudo labels for the unlabeled target ***,a softmax-consistence minimization term is utilized to minimize the intra-class distances between the source and target domains and maximize the inter-class *** is performed using three color fundus photograph datasets(APTOS2019,DDR,and EyePACS).RESULTS:The proposed model was evaluated and provided promising results with respectively 0.8917 and 0.9795 F1-scores on referable and normal/abnormal DR identification *** demonstrated effective DR identification through minimizing intra-class distances and maximizing inter-class distances between source and target ***:The multi-SFDA method provides an effective approach to overcome the challenges in DR *** method not only addresses difficulties in data labeling and privacy issues,but also reduces the need for large amounts of labeled data required by deep learning methods,making it a practical tool for early detection and preservation of vision in diabetic patients.

关键词： diabetic retinopathy multisource-free domain adaptation pseudo-label generation softmaxconsistence minimization

来源：评论

学校读者我要写书评

暂无评论

A Novel 3D Medical Image Segmentation Model Using Improved SAM

A Novel 3D Medical Image Segmentation Model Using Improved S...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Kuang, Yuansen Ma, Xitong Zhao, Jing Wang, Guangchen Zeng, Yijie Liu, Song Key Laboratory of Computing Power Network and Information Security Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China

ISBN: (纸本)9781665410205

3D medical image segmentation is an essential task in the medical image field, which aims to segment organs or tumours into different labels. A number of issues exist with the current 3D medical image segmentation task: existing models cannot simultaneously obtain the space correlation and depth correlation of 3D slices;previous models suffer from local detail loss of positional embedding in 3D images;previous approaches often have blurring of boundaries in segmenting 3D images. To solve these shortcomings, we propose a 3D medical image segmentation model named TPM-SAM. In our model, we design a twinchannel image encoder to simultaneously capture the space correlation and depth correlation of 3D slices through a multi-head attention mechanism and improved adapters. Furthermore, we design a prompt encoding generator, which divides the volumetric image into small blocks and better captures the local detail information. In addition, we introduce a multi-layer aggregation decoder by employing U-Net with multi-level skip connection to solve the blurring of boundaries in processing 3D images. Finally, we experimented and evaluated our model on KiTS21 and LiTS17 datasets to compare with other baseline models. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Deep Vision Guided Mobile Robot Dual Axis PID Dynamic Real Time Adjustment Following 5

Deep Vision Guided Mobile Robot Dual Axis PID Dynamic Real T...

引用

5th World Robot Conference Symposium on Advanced Robotics and Automation, WRC SARA 2023

作者： Li, Yang Yang, Guanci He, Ling Zhao, Le Zhao, Tianyi Sun, Haoran Guizhou University Key Laboratory of Advanced Manufacturing Technology of the Ministry of Education Guizhou Guiyang550025 China Guizhou University Key Laboratory of Advanced Manufacturing Technology of the Ministry of Education State Key Laboratory of Public Big Data Guizhou Provincial Key Laboratory of Internet+' Collaborative Intelligent Manufacturing Guizhou Guiyang550025 China

ISBN: (纸本)9798350307320

The real-time tracking of moving objects by social robots is crucial for ensuring object-oriented services. This paper presents a real-time following algorithm for mobile robots based on deep vision object detection. Firstly, using a binocular depth vision camera, real-time target information from a firstperson perspective is collected, and a lightweight deep learning model is employed to detect the relative position of the human body posture with respect to the social robot. Subsequently, to address the issue of unsmooth trajectory during the tracking process, a dual-axis PID algorithm is developed for cooperative control of the robot's speed and heading angle. Given the inherent randomness in human body movement, target loss can occur during tracking. To enhance the algorithm's robustness, a dynamic tracking mechanism is introduced. Finally, we implement a vision-driven two-wheel differential social robot following algorithm on the ROS system and validate it through three real-world experimental scenarios. The mean values of the target acquisition rate, tracked target position, and angle smoothness are found to be 0.81, 0.46, and 1.02, respectively. © 2023 IEEE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Plasmonic rhenium trioxide self-assembled microtubes for highly sensitive, stable and reproducible surface-enhanced Raman spectroscopy detection

引用

Chinese Chemical Letters 2023年第3期34卷 218-221页

作者： Jingbin Li Zhiwei Jiao Junfang Li Hua Bai Guangcheng Xi College of Sciences China Jiliang UniversityHangzhou 310018China Institute of Industrial and Consumer Product Safety Chinese Academy of Inspection and QuarantineBeijing 100176China Key Laboratory of Intelligent Manufacturing Quality Big Data Tracing and Analysis of Zhejiang Province China Jiliang UniversityHangzhou 310018China

Compared with noble metals, improving the sensitivity of semiconducting surface-enhanced Raman scattering(SERS) substrates is of great significance to their fundamental research and practical application of Raman spectroscopy. Herein, a simple chemical method is developed to synthesize a rhenium trioxide(ReO_(3)) microtubes assembled with highly crystalline nanoparticles. The ReO_(3) microtubes show a strong and well-defined surface plasmon resonance(SPR) behavior in visible region, which is rare for non-noble metals. As a low-cost SERS substrate, the plasmonic ReO_(3) microtubes exhibit a Raman enhancement factor of 8.9×10^(5) and a lowest detection limit of 1.0×10^(-9) mol/L for phenolic pollutants. Moreover, these ReO_(3) microtubule SERS substrates show excellent chemical stability and can resist the corrosion of strong acids and bases.

关键词： SERS ReO_(3) Surface plasmon resonance Microtubes Self assembly

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：