检索结果-内蒙古大学图书馆

24th IEEE International Conference on Data Mining, ICDM 2024

作者： Zhou, Hang Yu, Wentao Wan, Sheng Tong, Yongxin Gu, Tianlong Gong, Chen School of Computer Science and Engineering Nanjing University of Science and Technology China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education China Jiangsu Key Laboratory of Image and Video Understanding for Social Security China SKLSDE Beihang University China Jinan University Engineering Research Center of Trustworthy AI Ministry of Education China

ISBN: (纸本)9798331506681

Accurate Traffic Flow Prediction (TFP) is crucial for enhancing the efficiency and safety of transportation systems, so it has attracted intensive researches by exploiting spatial-temporal dependencies within road networks. However, existing works only consider the case of centralized data collection with all traffic data observed, which may raise privacy concerns as each region of a city may have its own traffic administration department and the traffic data is not allowed to distribute. Therefore, this paper proposes to use Federated Learning (FL) to address this issue by allowing all clients (i.e., traffic administration departments in all regions in our problem) to collaboratively train TFP models without exchanging raw data, thereby offering a solution in maintaining data privacy. Nevertheless, most existing FL methods aim to learn a global model that performs well universally, so they cannot well handle the non-Independent and Identically Distributed (non-IID) traffic data naturally over different regions. To cope with this problem, this paper develops a new FL framework termed 'personalized Federated learning with Traffic Pattern Sharing' (FedTPS) to solve federated TFP problem. Our FedTPS critically exploits the underlying common traffic patterns (e.g., morning and evening rush hours) shared across different city regions and meanwhile maintaining the region-specific data characteristics in a personalized FL manner. Specifically, to extract the common traffic patterns, we decompose the traffic data in each client via using discrete wavelet transform, where the low-frequency components uncover the stable traffic dynamics of different regions and thus can be considered as the common traffic patterns. These common patterns are then shared among different clients through traffic pattern repositories on the server side to aid the global collaborative traffic flow modeling. Moreover, the model components capturing spatial-temporal dependencies in traffic data are r

关键词： Highway administration

来源：评论

学校读者我要写书评

暂无评论

CPL-CLIP: Compound Prompt Learning for Flexible-Modal Face Anti-Spoofing 18

CPL-CLIP: Compound Prompt Learning for Flexible-Modal Face A...

引用

18th IEEE International Joint Conference on Biometrics, IJCB 2024

作者： Zhang, Ying Zhu, Xiangyu Liu, Ajian Lin, Xun Wan, Jun Zhang, Jing Lei, Zhen Beihang University School of Computer Science and Engineering China Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation China University of Chinese Academy of Sciences School of Artificial Intelligence China Macau University of Science and Technology School of Computer Science and Engineering China Chinese Academy of Sciences Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation China

ISBN: (纸本)9798350364132

Face anti-spoofing (FAS) is pivotal in safeguarding the integrity of face recognition systems. Flexible-modal FAS utilizes multi-modal data and trains a unified model adaptable to any single-modal testing scenario. This innovation addresses the shortcomings of conventional multi-modal FAS approaches, which typically demand separate model training and deployment for each modality. However, existing flexible-modal FAS approaches activate specific network branches based on the modality of the tested sample. This not only increases the model's parameters but also necessitates the provision of the image's modality for testing, thereby constraining deployment flexibility. To address the issue, we present Compound Prompt Learning CLIP (CPL-CLIP), a novel method for flexible-modal FAS. This approach capitalizes on a learned textual prompt that is nearly independent of modality, thus bolstering class-based classification across arbitrary modalities. Specifically, our CPL-CLIP introduces a Dual-Branch Prompt (DBP), consisting of class and modal prompts that describe and guide classification, where each prompt is composed of learnable vectors and fixed templates. To further render the class prompt as modality-agnostic as possible, a Cosine Similarity Loss (CSL) is proposed to facilitate the maximal separation of the class prompt from the modality prompt. With only the class prompt utilized during testing, CPL-CLIP enables deployment in diverse modal testing scenarios without the necessity of the test image's modality to be known. Extensive experiments demonstrate CPL-CLIP's superiority over existing methods on several flexible-modal FAS benchmarks. © 2024 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

STARGATE: Spatial Transcriptomic Analysis with Recurrent and Graph Attention Techniques using Ensemble Learning

STARGATE: Spatial Transcriptomic Analysis with Recurrent and...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Li, Ning Badai, Jiayidaer Chen, Dengjie Xiao, Ming Zhang, Le Sichuan University College of Computer Science Chengdu610065 China Fujian A and F University College of Mechanical and Electrical Engineering Fuzhou350100 China Sichuan University College of Computer Science China University of Chinese Academy of Sciences Key Laboratory of Systems Health Science Zhejiang Province School of Life Science Hangzhou Institute for Advanced Study Chengdu610065 China

ISBN: (纸本)9798350386226

Previous research has identified hematoma as the primary cause of mortality and disability in intraventricular hemorrhage (IVH), yet neurologic outcomes post-IVH have not significantly improved following hematoma evacuation. Therefore, utilizing spatial transcriptomics sequencing technology to acquire and analyze IVH data is of significant importance for the early diagnosis and treatment of acute cerebral hemorrhage. However, existing spatial transcriptomics clustering algorithms often overlook local information, fail to integrate multimodal data, and suffer from performance instability. To address these issues, we developed a multimodal spatial transcriptomics clustering algorithm named STARGATE, which initially captures the global spatial topology and local long-sequence gene set features of cells by integrating Graph Convolutional Networks (GCNs) based on self-attention mechanisms and Long Short-Term Memory networks (LSTMs), subsequently fuses gene expression, tissue imagery, morphological, and spatial coordinate features using Gated Recurrent Units (GRUs), and finally enhances the accuracy and robustness of predictions through ensemble learning methods. Our key experimental results include: (1) In clustering experiments on our proprietary mouse IVH spatial transcriptomics dataset, the STARGATE model achieved Adjusted Rand Index (ARI), Normalized Mutual Information (NMI), and Fowlkes-Mallows Index (FMI) scores of 0.80, 0.84, and 0.82, respectively, all superior to classic algorithms such as stLearn and CCST. (2) In clustering experiments on the mouse IVH dataset, the STARGATE model reached an accuracy of 89.63%, with an excellent confusion matrix, demonstrating outstanding accuracy and stability. (3) In clustering experiments on the public dataset DLFPC, which is known for its high data complexity leading to generally lower clustering metrics, the STARGATE model's ARI, NMI, and FMI indicators still outperformed classic algorithms such as SpaGCN and Seurat. © 2024

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

NeSyKHG: Neuro-Symbolic Knowledge Hypergraphs 2

NeSyKHG: Neuro-Symbolic Knowledge Hypergraphs

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Bhuyan, Bikram Pratim Singh, Thipendra P. Tomar, Ravi Ramdane-Cherif, Amar LISV Laboratory University of Paris Saclay 10-12 Avenue of Europe Velizy78140 France School of Computer Science University of Petroleum and Energy Studies Dehradun248007 India School of Computer Science Engineering & Technology Bennett University Greater Noida201306 India Persistent Systems Pune411016 India

In the rapidly evolving landscape of artificial intelligence, there is an escalating demand for enhanced reasoning capabilities and robust representation of higher-order relationships. Despite their prowess in pattern identification and generalization, Neural networks often grapple with challenges linked to interpretability and the absence of explicit relational reasoning. Symbolic logic, on the other hand, excels in formal knowledge representation and inference yet remains limited in deriving knowledge directly from data. We introduce the Neuro-Symbolic Knowledge Hypergraphs (NeSyKHG) framework to bridge this gap. This innovative model synergistically merges the strengths of neural networks and symbolic logic, offering an optimized representation and reasoning system for higher-order relationships using knowledge hypergraphs. Our empirical evaluations on the Chinese Medical High-order Relational (CMHR) dataset revealed that NeSyKHG significantly outperforms several established baseline models. Specifically, when compared to models such as Hypergraph Neural Networks (HGNN), Hypergraph Convolutional Networks (HyperGCN), Logical Hypergraph Link Prediction (LHP), and Universal Graph Convolutional Networks (UniGCN), NeSyKHG achieved an F1-score of 0.845, an accuracy (ACC) of 0.947, and an area under the curve (AUC) of 0.965. These metrics underscore NeSyKHG's exceptional ability in higher-order relational learning and reasoning. © 2024 Elsevier B.V.. All rights reserved.

关键词： computer circuits

来源：评论

学校读者我要写书评

暂无评论

A Counterfactual Ultrasound Anti-Interference Self-Supervised Network for B-mode Ultrasound Tongue Extraction

A Counterfactual Ultrasound Anti-Interference Self-Supervise...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Jia, Yan Cheng, Yuqing Xu, Kele Dou, Yong Qiao, Peng He, Zhouyu National Key Laboratory of Parallel and Distributed Computing College of Computer Science and Technology National University of Defense Technology Changsha China College of Systems Engineering National University of Defense Technology Changsha China

ISBN: (纸本)9798350368741

B-mode ultrasound tongue imaging is a non-invasive and real-time method for visualizing vocal tract deformation. However, accurately extracting the tongue's surface contour remains a significant challenge due to the low signal-to-noise ratio (SNR) and prevalent speckle noise in ultrasound images. Traditional supervised learning models often require large labeled datasets, which are labor-intensive to produce and susceptible to noise interference. To address these limitations, we present a novel Counterfactual Ultrasound Anti-Interference Self-Supervised Network (CUAI-SSN), which integrates self-supervised learning (SSL) with counterfactual data augmentation, progressively disentangles confounding factors, ensuring that the model generalizes well across varied ultrasound conditions. Our approach leverages causal reasoning to decouple noise from relevant features, enabling the model to learn robust representations that focus on essential tongue structures. By generating counterfactual image-label pairs, our method introduces alternative, noise-independent scenarios that enhance model training. Furthermore, we introduce attention mechanisms to enhance the network's ability to capture fine-grained details even in noisy conditions. Extensive experiments on real ultrasound tongue images demonstrate that CUAI-SSN outperforms existing methods, setting a new benchmark for automated contour extraction in ultrasound tongue imaging. Our code is publicly available at https://***/inexhaustible419/CounterfactualultrasoundAI. © 2025 IEEE.

关键词： contour extraction counterfactual inference self-supervised learning speech production ultrasound image

来源：评论

学校读者我要写书评

暂无评论

Arbitrarily polarized bound states in the continuum with twisted photonic crystal slabs

引用

Light(science & Applications) 2023年第4期12卷 542-550页

作者： Haoye Qin Zengping Su Mengqi Liu Yixuan Zeng Man-Chung Tang Mengyao Li Yuzhi Shi Wei Huang Cheng-Wei Qiu Qinghua Song Tsinghua Shenzhen International Graduate School Tsinghua UniversityShenzhen 518055China Department of Electrical and Computer Engineering National University of SingaporeSingapore 117583Singapore Institute of Precision Optical Engineering School of Physics Science and EngineeringTongji UniversityShanghai 200092China Key Laboratory of Multifunctional Nanomaterials and Smart Systems Suzhou institute of Nano-Tech and Nano-Bionics(SINANO)Chinese Academy of Sciences(CAS)Suzhou 215123China

Arbitrary polarized vortex beam induced by polarization singularity offers a new platform for both classical optics and quantum entanglement *** states in the continuum(BICs)have been demonstrated to be associated with topological charge and vortex polarization singularities in momentum *** conventional symmetric photonic crystal slabs(PhCSs),BIC is enclosed by linearly polarized far fields with winding angle of 2π,which is unfavorable for high-capacity and multi-functionality integration-optics ***,we show that by breakingσz-symmetry of the PhCS,asymmetry in upward and downward directions and arbitrarily polarized BIC can be realized with a bilayer-twisted *** exhibits elliptical polarization states with constant ellipticity angle at every point in momentum space within the vicinity of *** topological nature of BIC reflects on the orientation angle of polarization state,with a topological charge of 1 for any value of ellipticity *** coverage of Poincarésphere(i.e.,-π/4≤X≤4 and-π/2≤ψ≤π/2)and higher-order Poincarésphere can be realized by tailoring the twist *** findings may open up new avenues for applications in structured light,quantum optics,and twistronics for photons.

关键词： Poincaré polarized twisted

来源：评论

学校读者我要写书评

暂无评论

IAACS: Image aesthetic assessment through color composition and space formation

引用

Virtual Reality & Intelligent Hardware 2023年第1期5卷 42-56页

作者： Bailin YANG Changrui ZHU Frederick WBLI Tianxiang WEI Xiaohui LIANG Qingxu WANG School of Computer and Information Engineering Zhejiang Gongshang UniversityHangzhou 310018China Department of Computer Science University of DurhamDH13LEUnited Kingdom College of Intelligence and Computing Tianjin UniversityTianjin 300072China State Key Laboratory of Virtual Reality Technology and Systems Beihang UniversityBeijing 100191China

Background Determining how an image is visually appealing is a complicated and subjective task. This motivates the use of a machine-learning model to evaluate image aesthetics automatically by matching the aesthetics of the general public. Although deep learning methods have successfully learned good visual features from images,correctly assessing the aesthetic quality of an image remains a challenge for deep learning. Methods To address this, we propose a novel multiview convolutional neural network to assess image aesthetics assessment through color composition and space formation(IAACS). Specifically, from different views of an image––including its key color components and their contributions, the image space formation, and the image itself––our network extracts the corresponding features through our proposed feature extraction module(FET) and the Image Net weight-based classification model. Result By fusing the extracted features, our network produces an accurate prediction score distribution for image aesthetics. The experimental results show that we have achieved superior performance.

关键词： Image aesthetic assessment Color composition Space formation Deep learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive neural network control of a 2-DOF helicopter system considering input constraints and global prescribed performance

引用

science China(Information sciences) 2024年第7期67卷 224-239页

作者： Zhijia ZHAO Jiale WU Zhijie LIU We HE C.L.Philip CHEN School of Mechanical and Electrical Engineering Guangzhou University School of Intelligence Science and Technology and Key Laboratory of Intelligent Bionic Unmanned Systems of Ministry of Education University of Science and Technology Beijing School of Computer Science and Engineering South China University of Technology Pazhou Lab

In this study, an adaptive neural network(NN) control is proposed for nonlinear two-degree-offreedom(2-DOF) helicopter systems considering the input constraints and global prescribed ***, radial basis function NN(RBFNN) is employed to estimate the unknown dynamics of the helicopter system. Second, a smooth nonaffine function is exploited to approximate and address nonlinear constraint functions. Subsequently, a new prescribed function is proposed, and an original constrained error is transformed into an equivalent unconstrained error using the error transformation and barrier function transformation methods. The analysis of the established Lyapunov function proves that the controlled system is globally uniformly bounded. Finally, the simulation and experimental results on a constructed Quanser's test platform verify the rationality and feasibility of the proposed control.

关键词： adaptive NN control 2-DOF helicopter global prescribed performance input constraints

来源：评论

学校读者我要写书评

暂无评论

Low-cost contact-free screen control based on machine vision 4

Low-cost contact-free screen control based on machine vision

引用

4th Optics Frontier Conference, OFS 2024

作者： Lin, Yangbing Wang, Teng Yan, Wei Peng, Xiao Zhang, Xinhai Department of Electrical and Electronic Engineering Southern University of Science and Technology Shenzhen518055 China College of Physics and Optoelectronic Engineering Key Laboratory of Optoelectronic Devices and Systems of Ministry of Education and Guangdong Province Shenzhen University Shenzhen518060 China School of Computer Science and Engineering South China University of Technology Guangzhou510641 China

ISBN: (纸本)9781510682269

Contact-free manipulation technology represents a novel approach that offers a fresh possibility for human-machine interaction, aiming to meet the evolving demands of this interface. In this paper, we introduce a contact-free planar display control technique based on imaging. In our research, we employ cameras as sensors and integrate infrared lasers with image processing techniques to detect and localize input signals. By establishing a coordinate mapping relationship between the operational plane and the display plane, we achieved contact-free control over the planar display. Our paper introduces two methods for establishing this coordinate mapping. The first involves constructing mapping functions between the rectified and transformed camera imagery and the display plane, thereby creating a point-to-point correspondence. The second method entails dividing both the camera imagery and the display plane into segments, establishing a one-to-one relationship between regions. We analyze the strengths and limitations of these two approaches. While the former boasts higher theoretical precision, it is more susceptible to equipment factors and exhibits slower response speeds. Conversely, the latter, despite its lower theoretical precision, offers faster response times. Through the setup of an experimental platform, we demonstrate the feasibility of our proposed. © 2024 SPIE.

关键词： Machine vision

来源：评论

学校读者我要写书评

暂无评论

Deep Learning in Medical Image Registration: Magic or Mirage?

arXiv

引用

arXiv 2024年

作者： Jena, Rohit Sethi, Deeksha Chaudhari, Pratik Gee, James C. Computer and Information Science Electrical and Systems Engineering Radiology Penn Image Computing and Science Laboratory United States

Classical optimization and learning-based methods are the two reigning paradigms in deformable image registration. While optimization-based methods boast generalizability across modalities and robust performance, learning-based methods promise peak performance, incorporating weak supervision and amortized optimization. However, the exact conditions for either paradigm to perform well over the other are shrouded and not explicitly outlined in the existing literature. In this paper, we make an explicit correspondence between the mutual information of the distribution of per-pixel intensity and labels, and the performance of classical registration methods. This strong correlation hints to the fact that architectural designs in learning-based methods is unlikely to affect this correlation, and therefore, the performance of learning-based methods. This hypothesis is thoroughly validated with state-of-the-art classical and learning-based methods. However, learning-based methods with weak supervision can perform high-fidelity intensity and label registration, which is not possible with classical methods. Next, we show that this high-fidelity feature learning does not translate to invariance to domain shift, and learning-based methods are sensitive to such changes in the data distribution. Finally, we propose a general recipe to choose the best paradigm for a given registration problem, based on these observations. © 2024, CC BY.

关键词： Contrastive Learning

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：