检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Fu, Jun Zhou, Wei Jiang, Qiuping Liu, Hantao Zhai, Guangtao The CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China The School of Computer Science and Informatics Cardiff University CardiffCF24 4AG United Kingdom The School of Information Science and Engineering Ningbo University Ningbo315211 China The Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai200240 China

Recently, textual prompt tuning has shown inspirational performance in adapting Contrastive Language-image Pre-training (CLIP) models to natural image quality assessment. However, such uni-modal prompt learning method only tunes the language branch of CLIP models. This is not enough for adapting CLIP models to AI generated image quality assessment (AGIQA) since AGIs visually differ from natural images. In addition, the consistency between AGIs and user input text prompts, which correlates with the perceptual quality of AGIs, is not investigated to guide AGIQA. In this letter, we propose vision-language consistency guided multi-modal prompt learning for blind AGIQA, dubbed CLIP-AGIQA. Specifically, we introduce learnable textual and visual prompts in language and vision branches of CLIP models, respectively. Moreover, we design a text-to-image alignment quality prediction task, whose learned vision-language consistency knowledge is used to guide the optimization of the above multi-modal prompts. Experimental results on two public AGIQA datasets demonstrate that the proposed method outperforms state-of-the-art quality assessment models. The source code is available at https://***/JunFu1995/CLIP-AGIQA. © 2024, CC BY-NC-ND.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Emissivity Estimation and Application Based on Machine Learning Method

Hyperspectral Emissivity Estimation and Application Based on...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Xiujuan Li Hua Wu José Antonio Sobrino State Key Laboratory of Resources and Environmental Information System Institute of Geographic Sciences and Natural Resources Research Chinese Academy of Sciences Beijing China Global Change Unit Image Processing Laboratory University of Valencia Valencia Spain University of Chinese Academy of Sciences Beijing China School of Resources and Environment University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Land surface emissivity (LSE) can reflect the unique spectral characteristics of land surfaces, which holds significant research value and promising applications. However, due to the limitations of spaceborne hyperspectral thermal infrared (TIR) sensors, there is currently a lack of high spatial resolution LSE imagery. Therefore, this study proposes a methodology based on machine learning and mathematical statistical approaches to extend multispectral emissivity values to hyperspectral LSE spectrums. Furthermore, the Spectral Angle Mapper (SAM) method was used for target identification. The results indicated that the proposed method can estimate hyperspectral LSE curves in high accuracy. Moreover, the target ground class can be identified accurately by matching the spectral angle with the measured LSE curve. This has crucial implications for applications such as land cover classification, mineral identification, geological exploration and soil property research.

关键词： Training Accuracy Databases Land surface Estimation Machine learning Thermal sensors

来源：评论

学校读者我要写书评

暂无评论

Anti-jamming performance analysis of multi-OAM-mode vortex radar based on waveform diversity

Anti-jamming performance analysis of multi-OAM-mode vortex r...

引用

International Conference on Radar Systems (RADAR 2022)

作者： D. Hu L. Liu Y. Duan X. Jiang K. Lv H. Ma National Laboratory of Radar Signal Processing Xidian University Xi'an People's Republic of China Beijing Institute of Remote-sensing Equipment Science and Technology on Millimeter-wave Laboratory Beijing People's Republic of China

This paper exploits the electromagnetic vortex (EMV) radar system in anti-jamming applications of digital radio frequency memory (DRFM), considering the orthogonal-waveform-based uniform circular array (UCA) system specifically. Compared to conventional multiple-input-multiple-output (MIMO) system, the EMV radar has a novel dimension of EMV mode proportional to the orbital angular momentum (OAM), providing a new dimension for the orthogonal decomposition of the transmitted waveform, as well as a new dimension for distinguish the DRFM and a real target.

关键词： angular momentum antenna arrays digital radio jamming MIMO communication radar signal processing

来源：评论

学校读者我要写书评

暂无评论

Interactive Prototype Learning and Self-Learning for Few-Shot Medical image Segmentation

SSRN

引用

SSRN 2024年

作者： Song, Yuhui Xu, Chenchu Wang, Boyan Du, Xiuquan Chen, Jie Zhang, Yanping Li, Shuo School of Computer Science and Technology Anhui University Hefei230601 China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei230601 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230051 China Department of Computer Science and Technology Tsinghua University Beijing100084 China School of Engineering Case Western Reserve University Cleveland44106 United States

Few-shot learning alleviates the heavy dependence of medical image segmentation tasks on large-scale labeled data, but it shows a strong performance gap when dealing with new targets and new tasks compared with traditional deep learning. Existing few-shot medical image segmentation models mainly realize segmentation by learning the semantic class knowledge of a few known (support) samples and extending it to unknown (query) samples. However, the neglect of the differences between known and unknown samples leads to a certain deviation in the transfer of class knowledge, and the trained model tends to overfit the class knowledge of training classes, which greatly reduces the segmentation and generalization performance of few-shot model. In this work, we propose an interactive prototype learning and self-learning network to alleviate the above problems. Specifically, we propose an interactive prototype learning network to promote feature consistency between support images and query images to improve the accuracy of prototype metric learning. In addition, to avoid overfitting the training class knowledge and reduce the over-dependence of query segmentation on the class knowledge, we introduce a query features-guided self-learning network to achieve the finer segmentation of query images through its rich feature information. Our model obtained the competitive segmentation results on three multi-organ and multi-modal public datasets that show a substantial improvement in generalization ability. © 2024, The Authors. All rights reserved.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Multi-component High-Frequency Vibration Error Estimation and Compensation Approach for Multirotor UAV SAR

引用

IEEE Sensors Journal 2025年

作者： Han, Jiahao Tang, Shiyang Chen, Zhanye Guo, Ping Jiang, Chenghao Lian, Zhixin Zhang, Linrang Xidian University National Key Laboratory of Radar Signal Processing Xi’an 710071 China Southeast University State Key Laboratory of Millimeter Waves Nanjing 210096 China Southeast University Institute of Electromagnetic Space Nanjing 210096 China Xian University of Science and Technology College of Communication and Information Engineering Xian 710054 China

For multirotor unmanned aerial vehicle (UAV) synthetic aperture radar (SAR), the propeller rotation may lead to multi-component high-frequency vibration error (HFVE), seriously affecting imaging quality. To deal with this practical issue, a multi-component HFVE estimation and compensation approach is presented for multirotor UAV SAR, which can be implemented in three steps, i.e., vibration component extraction, vibration parameter estimation, and vibration error suppression. First, an improved ensemble empirical mode decomposition method is utilized to extract the vibration component of HFVE, ensuring the accuracy of component extraction. Then, based on the optimal solution of the correlation function, the parameters of the extracted vibration component are accurately determined to improve the accuracy of the constructed compensation function. Finally, all the vibration components are compensated in cyclic processing to achieve effective suppression of multi-component HFVE. Real data experimental results show that our approach outperforms the existing approach in terms of average impulse response width (0.21 m versus 0.25 m), peak sidelobe ratio (-25.26 dB versus -19.56 dB), and integration sidelobe ratio (-19.43 dB versus -6.54 dB), which verify the effectiveness of our approach. © 2001-2012 IEEE.

关键词： High-frequency vibration error (HFVE) multirotor unmanned aerial vehicle (UAV) synthetic aperture radar (SAR) vibration component extraction vibration parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Attention based Temporal convolutional network for Ф-OTDR event classification 19

Attention based Temporal convolutional network for Ф-OTDR e...

引用

19th International Conference on Optical Communications and Networks, ICOCN 2021

作者： Tian, Manling Dong, Hui Yu, Kuanglu Beijing Key Laboratory of Modern Information Science and Network Technology Beijing Jiaotong University Beijing100044 China Institute of Information Science Beijing Jiaotong University Beijing100044 China Signal Processing. RF & Optical Department Institute for Inforcomm Research A*Star Research Entities Singapore138632 Singapore

We designed a new attention based temporal convolutional network combined with bidirectional long short term memory model named ATCN-BiLSTM for Ф-OTDR event classification, achieving average classification accuracy o... 详细信息

ISBN: (纸本)9781665424462

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

From early biological models to CNNs: Do they look where humans look? 25

From early biological models to CNNs: Do they look where hum...

引用

25th International Conference on Pattern Recognition, ICPR 2020

作者： Cadoni, Marinella Iole Lagorio, Andrea Grosso, Enrico Jia Huei, Tan Chee Seng, Chan Computer Vision Laboratory University of Sassari Sassari Italy Center of Image and Signal Processing Department of Artificial Intelligence Faculty of Computer Science and Information Technology University of Malaya Malaysia

ISBN: (纸本)9781728188089

Early hierarchical computational visual models as well as recent deep neural networks have been inspired by the functioning of the primate visual cortex system. Although much effort has been made to dissect neural networks to visualize the features they learn at the individual units, the scope of the visualizations has been limited to a categorization of the features in terms of their semantic level. Considering the ability humans have to select high semantic level regions of a scene, the question whether neural networks can match this ability, and if similarity with humans attention is correlated with neural networks performance naturally arise. To address this question we propose a pipeline to select and compare sets of feature points that maximally activate individual networks units to human fixations. We extract features from a variety of neural networks, from early hierarchical models such as HMAX up to recent deep convolutional neural netwoks such as Densnet, to compare them to human fixations. Experiments over the ETD database show that human fixations correlate with CNNs features from deep layers significantly better than with random sets of points, while they do not with features extracted from the first layers of CNNs, nor with the HMAX features, which seem to have low semantic level compared with the features that respond to the automatically learned filters of CNNs. It also turns out that there is a correlation between CNN's human similarity and classification performance. © 2020 IEEE

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Single-Cell Clustering Algorithm Based on Structure Perturbation Non-Negative Matrix Factorization

A Single-Cell Clustering Algorithm Based on Structure Pertur...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Hanjing Jiang Meineng Wang Luping Zhang Yu-An Huang Yangyuan Li Yabing Huang Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China Institute of Artificial Intelligence School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China School of Computer Science and Technology China University of Mining and Technology Xuzhou China School of Mathematics and Computer Science Yichun University Yichun China School of Information Engineering East China University of Technology Nanchang China School of Computer Science Northwestern Polytechnical University Xi’an China Department of Pathology Renmin Hospital of Wuhan University Wuhan China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

The advent of single-cell RNA sequencing (scRNA-seq) has facilitated the acquisition of high-resolution data regarding cell heterogeneity across various tissues. A fundamental and critical step in the analysis of scRNA-seq data is cell type identification. An appropriate graph construction strategy can reflect the topological structure between cells and allows for detailed exploration of the relationships between cells and genes. Given the sparsity of scRNA-seq data and the pronounced noise generated by shallow sequencing, choosing an appropriate graph construction strategy has become a significant challenge. In this paper, we propose a single-cell clustering method, named Sc-PNNMF, based on structural perturbation of nonnegative matrix factorization. Sc-PNNMF employs a structural perturbation algorithm to optimize the gene expression matrix. The optimized matrix guides the matrix factorization process, effectively overcoming the impact of data sparsity and significant noise in gene expression data on the graph construction strategy. We compared the clustering abilities of Sc-PNNMF with five other methods on ten real datasets.

关键词： Sequential analysis Perturbation methods Clustering methods RNA Noise Clustering algorithms Sparse matrices Gene expression Unsupervised learning Periodic structures

来源：评论

学校读者我要写书评

暂无评论

Selection of Cancer Biomarkers from Microarray Gene Expression Data Utilizing the Bi-Objective Optimization Method

Selection of Cancer Biomarkers from Microarray Gene Expressi...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Hanjing Jiang Jianqing Lin Huachao Zhu Yabing Huang Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China Institute of Artificial Intelligence School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China School of Computer Science Wuhan University Wuhan China Department of Pathology Renmin Hospital of Wuhan University Wuhan China

Cancer-associated biomarker genes play an indispensable role in the intricate tapestry of cancer development and manifestation. The expression of biomarkers in different types of tumor cells has beneficial implications for shedding light on the development of various cancers, guiding clinical diagnosis, and treatment. Microarray technology enables the expression levels of thousands of genes in samples to be sequenced simultaneously. However, sparse and high-dimensional microarray data present a formidable challenge in identifying biomarker genes. This study presents EREF-NSGA2, a novel method for cancer biomarker selection from microarray data, employing a hybrid gene selection approach. Firstly, the combination of the wrapper and embedded gene selection methods is proposed to filter the microarray data, which efficiently decreases the search space of the algorithm. After that, the improved NSGA-II algorithm is used to search the genes subset obtained from the previous step to reach the optimal subset of cancer biomarker genes. The proposed EREF-NSGA2 is compared with other reported methods on six cancer benchmark gene expression datasets. A detailed biological analysis is performed to analyze the relationship between the selected genes and the cancer data sets they belong to. To summarize, EREF-NSGA2 proves its effectiveness in selecting a feature subset comprising the fewest genes while maintaining the highest classification accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Sequence-Scheduled and Query-Based MAC Protocol for Underwater Acoustic Networks with a Mobile Node

引用

Journal of Communications and Information Networks 2020年第2期5卷 150-159页

作者： Jing Huang Cheng Chi Wei Wang Haining Huang Institute of Acoustics Chinese Academy of SciencesBeijing 100190China Key Laboratory of Science and Technology on Advanced Underwater Acoustic Signal Processing Chinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China

Since mobile nodes such as autonomous underwater vehicles can effectively expand network coverage,underwater acoustic networks with mobile nodes have attracted more and more attention in recent *** ensure the timely access of a mobile node without disturbing the normal transmission of data packets from static nodes,a sequence-scheduled and query-based medium access control protocol is proposed in this *** underwater nodes with data packets to be transmitted reply with a control packet for channel reservation after receiving the broadcast control packet of the buoy,then the reserved nodes transmit their data packets as the order calculated by the *** develop a mechanism to adjust the transmission order of the control packets sent by the underwater nodes in the handshake phase to reduce the collision and guarantee the success rate of reservation,and a query is initiated when the reserved control packet of the mobile node is not received by the buoy in the handshake to respond to the data transmission request of the mobile node in *** show that the maximum nodal throughput of the proposed MAC protocol increases by at least 20%and the access delay of the mobile node decreases by about 90%,compared to the two reference ***,the average access probability of the mobile node in the proposed protocol is more than 90%.

关键词： sequence-scheduled query underwater acoustic networks mobile nodes MAC protocol

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：