检索结果-内蒙古大学图书馆

Identity and Modality Attributes Driven Multimodal Fusion Networks for Emotion Recognition in Conversations

IEEE Transactions on Multimedia 2025年

作者： Shi, Wuzhen Chen, Xuping Yao, Biyun Wen, Yang Sheng, Bin Shenzhen University Guangdong Province Engineering Laboratory for Digital Creative Technology Guangdong Provincial Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Shenzhen518060 China Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai China

Emotion recognition in conversations (ERC) is a crucial aspect of human-computer interaction and plays an important role in various domains, including healthcare, entertainment, and education. Since the conversation data in the form of multimodal sequences is well suited to be constructed into graphs, the methods based on graph convolutional network (GCN) show incomparable advantages. However, existing methods attempt to model the highly uncertain emotional relationships between different speakers, which is not an easy task and may even introduce interference information. Therefore, we propose an identity and modality attributes driven multimodality fusion network (dubbed IMDNet) for emotion recognition in conversations. Specifically, we construct a speaker-centric graph that only connects nodes of the same speaker within modalities to each other, reducing the interference between the emotions of different speakers. We also introduce the attribute embedding mechanism, which facilitates the correct calculation of correlations between nodes for better multimodal feature fusion. Considering that the emotional correlation between utterances will decrease over time, we present an utterance distance attention to make the fusion network pay more attention to the adjacent utterances. Furthermore, we explore the solution to the data imbalance problem suitable for conversation scenarios. Given the presence of possible anomalous samples in the dataset, we opt for the BoundaryFocalLoss. Experiments on the IEMOCAP and MELD datasets show that our IMDNet outperforms the state-of-the-art methods. © 1999-2012 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Towards Label-Efficient Deep Learning for Myopic Maculopathy Classification 1

引用

Myopic Maculopathy Analysis Challenge, MMAC 2023, which was a part of the 26th International Conference on Medical Image Computing and computer Assisted Intervention, MICCAI 2023

作者： Hou, Junlin Xu, Jilan Xiao, Fan Zhang, Bo Xu, Yiqian Zhang, Yuejie Zou, Haidong Feng, Rui School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai China Academy for Engineering and Technology Fudan University Shanghai China Department of Ophthalmology Shanghai General Hospital School of Medicine Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9783031548574

ISBN: (纸本)9783031548567

Myopic Maculopathy is the leading cause of legal blindness in patients with pathologic myopia. Automated myopic maculopathy diagnosis is of vital importance to early treatment and progression slowdown. However, the scarcity of labeled fundus images with myopic maculopathy makes it challenging to improve diagnostic performance via deep learning models. In this paper, we construct a label-efficient deep learning framework for myopic maculopathy classification. In specific, we exploit two categories of pre-training methods, i.e., vision-language pre-training and self-supervised visual representation learning, to alleviate the overfitting problem caused by the limited number of training images. Moreover, we adopt a semi-supervised learning technique, namely pseudo labeling, to leverage a large number of unlabeled fundus images from external datasets. We also investigate the impact of other key components in model training for better performance, including backbone architecture, input resolution, and loss function. Our method is evaluated in the MICCAI 2023 Myopic Maculopathy Analysis Challenge (MMAC). Among 17 participating teams, our ensembled model ranked 1st on the leaderboard with an average score of 0.8752. The code will be publicly available at https://***/FDU-VTS/MMAC. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Ensemble Deep Learning Approaches for Myopic Maculopathy Plus Lesions Segmentation 1

引用

Myopic Maculopathy Analysis Challenge, MMAC 2023, which was a part of the 26th International Conference on Medical Image Computing and computer Assisted Intervention, MICCAI 2023

作者： Xiao, Fan Hou, Junlin Xu, Jilan Xu, Yiqian Zhang, Bo Zhang, Yuejie Zou, Haidong Feng, Rui Academy for Engineering and Technology Fudan University Shanghai China School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai China Department of Ophthalmology Shanghai General Hospital School of Medicine Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9783031548574

ISBN: (纸本)9783031548567

Myopia is a leading cause of visual impairment and blindness in several countries. Effective diagnosis and intervention are crucial, typically relying on manual image analysis by ophthalmologists, which is time-consuming and experience-dependent. In this work, we introduce an ensemble of deep learning techniques for myopic maculopathy plus lesions segmentation. Specifically, we utilize UNet, UNet++, and DeeplabV3+ to segment three lesions with strong data augmentation. Our ensembled model has proved to be effective in the MICCAI 2023 Myopic Maculopathy Analysis Challenge (MMAC). This dataset covers classification, segmentation, and spherical equivalent prediction, fostering automated analysis research. Extensive experiments on the MMAC dataset reveal the superior performance of our proposed approach, which ranked 1st on the challenge leaderboard. This work addresses a critical need for accurate and efficient myopic maculopathy diagnosis and intervention. The code will be publicly available at https://***/FDU-VTS/MMAC. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Learning the continuous-time optimal decision law from discrete-time rewards

引用

National Science Open 2024年第5期3卷 130-147页

作者： Ci Chen Lihua Xie Kan Xie Frank Leroy Lewis Yilu Liu Shengli Xie School of Automation Guangdong University of TechnologyGuangdong Key Laboratory of IoT Information TechnologyGuangzhou 510006China Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of EducationGuangzhou 510006China School of Electrical and Electronic Engineering Nanyang Technological UniversitySingapore 639798Singapore 111 Center for Intelligent Batch Manufacturing Based on IoT Technology Guangzhou 510006China UTA Research Institute the University of Texas at ArlingtonFort Worth 76118USA Department of Electrical Engineering and Computer Science University of TennesseeKnoxville 37996USA Oak Ridge National Laboratory Oak Ridge 37830USA Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou 510006China

The concept of reward is fundamental in reinforcement learning with a wide range of applications in natural and social *** an interpretable reward for decision-making that largely shapes the system's behavior has always been a challenge in reinforcement *** this work,we explore a discrete-time reward for reinforcement learning in continuous time and action spaces that represent many phenomena captured by applying physical *** find that the discrete-time reward leads to the extraction of the unique continuous-time decision law and improved computational efficiency by dropping the integrator operator that appears in classical results with integral *** apply this finding to solve output-feedback design problems in power *** results reveal that our approach removes an intermediate stage of identifying dynamical *** work suggests that the discrete-time reward is efficient in search of the desired decision law,which provides a computational tool to understand and modify the behavior of large-scale engineering systems using the optimal learned decision.

关键词： continuous-time state and action decision law learning discrete-time reward dynamical systems reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Generating superposed terahertz perfect vortices via a spin-multiplexed all-dielectric metasurface

引用

Photonics Research 2023年第3期11卷 431-441页

作者： FAN HUANG QUAN XU WANYING LIU TONG WU JIANQIANG GU JIAGUANG HAN WEILI ZHANG Center for Terahertz Waves and College of Precision Instrument and Optoelectronics Engineering Tianjin University and Key Laboratory of Optoelectronics Information and Technology(Ministry of Education)Tianjin 300072China Guangxi Key Laboratory of Optoelectronic Information Processing School of Optoelectronic EngineeringGuilin University of Electronic TechnologyGuilin 541004China School of Electrical and Computer Engineering Oklahoma State UniversityStllwaterOklahoma 74078USA

Perfect optical vortices(POVs),characterized as a ring radius independent of topological charge(TC),possess extensive application in particle manipulation and optical *** present,the complex and bulky optical device for generating POVs has been miniaturized by leveraging the metasurface,and either spindependent or spin-independent POV conversions have been further ***,it is still challenging to generate superposed POVs for incidences with orthogonal circular ***,a spinmultiplexed all-dielectric metasurface method for generating superposed POVs in the terahertz frequency range is proposed and *** using the multiple meta-atom comprised structure as the basic unit,the complex amplitude of two superposed POVs is modulated,decoupled,and subsequently encoded to left-and righthanded circular polarization ***,two kinds of metasurfaces are fabricated and characterized to validate this controlling *** is demonstrated that the measured intensity and phase distributions match well with the calculation of the Rayleigh–Sommerfeld diffraction integral,and the radius of superposed POVs is independent of *** work provides promising opportunities for developing ultracompact terahertz functional devices applied to complex structured light generation and terahertz communication,and exploring sophisticated spin angular momentum and orbital angular momentum interactions like the photonic spin-Hall effect.

关键词： dielectric radius generating

来源：评论

学校读者我要写书评

暂无评论

Contrast enhancement of optical videoscope images

引用

Iran Journal of computer Science 2023年第3期6卷 261-275页

作者： Ammar, Reda Aboshosha, Sahar El-Hag, Noha A. Saifeldeen, Reda El-Shafai, Walid El-Banby, Ghada M. Ashiba, Huda I. Khalaf, Ashraf A. M. Elazm, Atef Abou El-Rabaie, El-Sayed M. Abd El-Samie, Fathi E. El-Safrawey, Amir Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf 32952 Egypt Department of Electronics and Electrical Comm. Faculty of Engineering Minia University Minya Egypt Department of Management of Information Systems Higher Institute of Commercial Science El-Mahala El-Kobra Egypt Department of Industrial Electronics and Control Engineering Faculty of Electronic Engineering Menoufia University Menouf 32952 Egypt Department of Electronics and Electrical Communications Engineering Bilbis Higher Institute of Engineering Sharqia Bilbis Egypt Security Engineering Laboratory Computer Science Department Prince Sultan University Riyadh 11586 Saudi Arabia Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh 11671 Saudi Arabia

The videoscope (VS) images have poor quality and low contrast. Hence, in this paper, three proposed frameworks to improve the quality of VS images are presented. The first framework depends on contrast-limited adaptive histogram equalization (CLAHE) with adaptive gamma correction. The second framework depends on homomorphic processing. The third framework is based on the homomorphic enhancement with histogram equalization. The first one is superior from the entropy perspective, while the third one is superior from the contrast perspective. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2023.

关键词： Fuzzy enhancement Histogram equalization Homomorphic enhancement Spectral entropy

来源：评论

学校读者我要写书评

暂无评论

Self-Decoupled Square Patch Antenna Arrays by Exciting and Using Mixed Electric/Magnetic Coupling Between Adjacent Radiators

引用

Chinese Journal of Electronics 2025年第2期34卷 483-494页

作者： Liu Qianwen Zhu Lei Lu Wenjun College of Telecommunications and Information Engineering Nanjing University of Posts and Telecommunications Nanjing 210003 China Department of Electrical and Computer Engineering Faculty of Science and Technology University of Macau Macau 999078 China Jiangsu Key Laboratory of Wireless Communications Nanjing University of Posts and Telecommunications Nanjing 210003 China

This article presents and develops a simple decoupling method for the planar square patch antenna arrays by virtue of mixed electric and magnetic coupling property. Since the resonant modes of TM10 and TM01 are a pair of degenerate modes in the square patch radiator which are intrinsically orthogonal, a superposed mode of them can be generated to possess consistent field distributions along all the four sides of the patch by adjusting the feeding position. By employing such superposed mode, the mutual coupling between two horizontally adjacent patch elements will become identical to that between two vertical ones, indicating an expected possibility that the complex 2-D decoupling problem in a large-scale antenna patch array can be effectively facilitated and simplified to a 1-D one. Subsequently, metallic pins and connecting strip are properly loaded in each square patch resonator, such that appropriate electric and magnetic coupling strengths can be readily achieved and thus the mutual coupling can get highly decreased. A 1 × 2 antenna array with an edge-to-edge separation of 1 mm, which corresponding to 0.0117λ0, is firstly discussed, simulated, and fabricated. The measured results show that the isolation can be highly improved from 4 dB to 17 dB across the entire passband. In final, 1 × 3, 2 × 2, and 4 × 4 antenna array prototypes are constructed and studied for verification of the expansibility and feasibility of the proposed decoupling method to both linear and 2-D antenna arrays.

关键词： Large-scale antenna array Mutual coupling Mixed electric and magnetic coupling effect Self-decoupling Square patch antenna

来源：评论

学校读者我要写书评

暂无评论

Mixture Gaussian Distribution-Based Collaborative Reinforcement Learning for 3D UAV Localization Optimization Against Jamming Attacks

Mixture Gaussian Distribution-Based Collaborative Reinforcem...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Zhu, Yujiao Chen, Mingzhe Wang, Sihua Liu, Yuchen Li, Gaolei Yin, Changchuan Quek, Tony Q.S. Beijing University of Posts and Telecommunications Beijing Laboratory of Advanced Information Network Beijing100876 China Singapore University of Technology and Design 487372 Singapore University of Miami Department of Electrical and Computer Engineering Institute for Data Science and Computing Coral GablesFL33146 United States North Carolina State University Department of Computer Science RaleighNC27695 United States Shanghai Jiao Tong University School of Electronic Information and Electrical Engineering Shanghai200240 China

ISBN: (纸本)9798350351255

In this paper, the optimization of unmanned aerial vehicle (UAV) localization under jamming attacks is studied. In the considered network, a base station (BS) collaborates with an active UAV to localize a target UAV. During this positioning process, a jamming UAV transmits discontinuous signals to passive UAVs to interfere the distance information measurement. To localize the target UAV under jamming attacks, the BS jointly use two localization methods: 1) generative adversarial network (GAN)-based positioning method and 2) time difference of arrival (TDOA)-based positioning method. Since GAN-based positioning method cannot defense in a strong jamming signal while TDOA-based positioning method may consume more energy and sacrifice localization accuracy, the BS must select an appropriate positioning method (GAN-based or TDOA-based methods) and four distance measurement information of passive UAVs to estimate the position of the target UAV. This problem is formulated as an optimization problem whose goal is to minimize the positioning error between the estimated and the ground truth positions of the target UAV while considering jamming attacks and the trajectory of passive UAVs. To solve this problem, we propose a mixture Gaussian distribution model-based collaborative reinforcement learning (RL) method which enables the active UAV to determine its transmit power and trajectory, and enables the BS to select the most appropriate subsets of distance measurement information and the optimal positioning method according to the movement of passive UAVs and the unknown jamming attack pattern of the jamming UAV. Simulation results show the proposed method can reduce the positioning error of the target UAV by up to 36.5% compared to the method that does not consider the GAN-based positioning method. © 2024 IEEE.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Learning good state and action representations for Markov decision process via tensor decomposition

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2023年第1期24卷 5157-5209页

作者： Chengzhuo Ni Yaqi Duan Munther Dahleh Mengdi Wang Anru R. Zhang Department of Electrical & Computer Engineering Princeton University Laboratory for Information & Decision Systems Massachusetts Institute of Technology Electrical Engineering & Computer Science Department Massachusetts Institute of Technology Department of Biostatistics & Bioinformatics Duke University

The transition kernel of a continuous-state-action Markov decision process (MDP) admits a natural tensor structure. This paper proposes a tensor-inspired unsupervised learning method to identify meaningful low-dimensional state and action representations from empirical trajectories. The method exploits the MDP's tensor structure by kernelization, importance sampling and low-Tucker-rank approximation. This method can be further used to cluster states and actions respectively and find the best discrete MDP abstraction. We provide sharp statistical error bounds for tensor concentration and the preservation of diffusion distance after embedding. We further prove that the learned state/action abstractions provide accurate approximations to latent block structures if they exist, enabling function approximation in downstream tasks such as policy evaluation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RIS as a Network Resource: User Multiplexing and Pricing Algorithms 3

RIS as a Network Resource: User Multiplexing and Pricing Alg...

引用

3rd International Conference on 6G Networking, 6GNet 2024

作者： Papadopoulos, Alexandros Lalas, Antonios Votis, Konstantinos Schmid, Stefan Katsalis, Kostas Liaskos, Christos University of Ioannina Department of Computer Science and Engineering Ioannina Greece Information Technologies Institute CERTH Thessaloniki Greece Aristotle University of Thessaloniki Thessaloniki Greece TU Berlin and Fraunhofer SIT Berlin Germany Aristotle University of Thessaloniki Department of Electrical and Computer Engineering Thessaloniki Greece DOCOMO Communications Laboratory GmbH Munich Germany FORTH Ioannina Greece

ISBN: (纸本)9798350378597

Reconfigurable Intelligent Surfaces (RIS) have the ability to actively control wave propagation through space, enabling the creation of Programmable Wireless Environments (PWEs). This capability allows for the uti-lization and control of previously unexploited resources. However, there is a notable gap in allocating these resources to network users in a way that aligns with the pricing policies of telecommunications stakeholders. This paper considers RIS elements as network resources and describes a pricing policy that links the PWE efficiency of individual users to an optimal method for sharing RIS elements. A specialized policy tailored to this purpose, is designed with a focus on robustness, ensuring its applicability across various RIS functionalities and frequency bands. Its computational efficiency further underscores its viability for deployment in practical scenarios. © 2024 IEEE.

关键词： Costs

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：