检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Deng, Kaijun Zheng, Dezhi Xie, Jindong Wang, Jinbao Xie, Weicheng Shen, Linlin Song, Siyang Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China Department of Computer Science University of Exeter United Kingdom

Accurately synthesizing talking face videos and capturing fine facial features for individuals with long hair presents a significant challenge. To tackle these challenges in existing methods, we propose a decomposed per-embedding Gaussian fields (DEGSTalk), a 3D Gaussian Splatting (3DGS)-based talking face synthesis method for generating realistic talking faces with long hairs. Our DEGSTalk employs Deformable Pre-Embedding Gaussian Fields, which dynamically adjust pre-embedding Gaussian primitives using implicit expression coefficients. This enables precise capture of dynamic facial regions and subtle expressions. Additionally, we propose a Dynamic Hair-Preserving Portrait Rendering technique to enhance the realism of long hair motions in the synthesized videos. Results show that DEGSTalk achieves improved realism and synthesis quality compared to existing approaches, particularly in handling complex facial dynamics and hair preservation. Our code will be publicly available at https://***/CVI-SZU/DEGSTalk. Copyright © 2024, The Authors. All rights reserved.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Report-Guided Cross-Modal Representation Learning for Predicting EGFR Mutations by Whole Slide image

Report-Guided Cross-Modal Representation Learning for Predic...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Qiao, Qi Shi, Jun Jiang, Zhiguo Wang, Wei Wu, Haibo Zheng, Yushan Hefei University of Technology School of Computer Science and Information Engineering Hefei230601 China Hefei University of Technology School of Software Hefei230601 China Beihang University Image Processing Center School of Astronautics Beijing102206 China University of Science and Technology of China Division of Life Sciences and Medicine Department of Pathology First Affiliated Hospital of Ustc Hefei230036 China University of Science and Technology of China Intelligent Pathology Institute Division of Life Sciences and Medicine Hefei230036 China Beihang University School of Engineering Medicine Beijing Advanced Innovation Center for Biomedical Engineering Beijing100191 China

ISBN: (纸本)9798350386226

Traditional PCR/NGS-based multigene panel testing is time-consuming and costly. Predicting EGFR mutations directly from H&E stained whole slide images (WSIs) can alleviate these limitations. Furthermore, histopathological reports contain valuable textual information that correlates with tissue areas in WSIs. However, recent research mainly analyses EGFR mutation status only from a single modality, ignoring rich information contained in reports. In this paper, we propose a report-guided cross-modal representation learning method for predicting EGFR mutations by WSIs. Specifically, we reconstruct report-level embeddings through exploring intrinsic relationships between diagnostic words in histopathological reports and tissue areas in WSIs. Finally, reconstructed histopathological report embedding and aggregated WSI embedding are fused for final prediction. More importantly, molecular testing report is also introduced as prior supervision information at the training stage to guarantee semantic consistency of fused feature and molecular report embedding. We evaluate our method on the TCGA-EGFR public benchmark dataset and an in-house clinical dataset (USTC-EGFR). Experimental results demonstrate that our method outperforms existing approaches in EGFR mutation prediction, highlighting the benefits of cross-modal learning in enhancing feature representational ability. The code is available at https://***/HFUT-miaLab/RCRL. © 2024 IEEE.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Memristor-Based Circuit of Sequential Associative Memory with Memory Interactions and Stimulus Similarity Effect

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Xiong, Dongdong Wang, Xiaoping Jiang, Yiming Yang, Chao Jiang, Man Lai, Jingang Zeng, Zhigang Huazhong University of Science and Technology School of Artificial Intelligence and Automation Wuhan430074 China Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan430074 China Hubei Key Laboratory of Braininspired Intelligent Systems Wuhan430074 China Huazhong University of Science and Technology Institute of Artificial Intelligence School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan430074 China Guangxi University of Science and Technology School of Computer Science and Technology Liuzhou545006 China Huazhong University of Science and Technology Department of Physiology School of Basic Medicine and Tongji Medical College Wuhan430030 China

Most proposed memristor-based circuits of associative memory consider various mechanisms in only one associative memory. Few works on circuit design of sequential associative memory have been reported. In this paper, a memristor-based circuit of sequential associative memory with memory interactions and stimulus similarity effect is designed. Two associative memories, the prior associative memory (PAM) and the later associative memory (LAM), are formed successively. The PAM modifies the rate of the formation of the LAM, and the LAM, in turn, affects the strength of the PAM, which are two interactions in sequential associative memory, called transfer and retroaction. In addition, the magnitudes of transfer and retroaction are determined by the similarity of the conditioned stimuli. The above functions are realized by the ring input processing module, memory module, transfer module and retroaction module. It has been identified in circuit analysis that the proposed circuit is power efficient and has good robustness. Furthermore, the proposed circuit has promising applications for fire rescue robots. © 2016 IEEE.

关键词： Associative storage

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Classification of Data Streams by BIRCH Ensemble and Local Structure Mapping

引用

Journal of computer Science & technology 2020年第2期35卷 295-304页

作者： Yi-Min Wen Shuai Liu Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin 541004China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic TechnologyGuilin 541004China School of Computer Science and Information Security Guilin University of Electronic TechnologyGuilin 541004China

Many researchers have applied clustering to handle semi-supervised classification of data streams with concept ***,the generalization ability for each specific concept cannot be steadily improved,and the concept drift detection method without considering the local structural information of data cannot accurately detect concept *** paper proposes to solve these problems by BIRCH(Balanced Iterative Reducing and Clustering Using Hierarchies)ensemble and local structure *** local structure mapping strategy is utilized to compute local similarity around each sample and combined with semi-supervised Bayesian method to perform concept *** a recurrent concept is detected,a historical BIRCH ensemble classifier is selected to be incrementally updated;otherwise a new BIRCH ensemble classifier is constructed and added into the classifier *** extensive experiments on several synthetic and real datasets demonstrate the advantage of the proposed algorithm.

关键词： semi-supervised classification clustering data stream concept drift

来源：评论

学校读者我要写书评

暂无评论

GEM: Context-Aware Gaze EstiMation with Visual Search Behavior Matching for Chest Radiograph

arXiv

引用

arXiv 2024年

作者： Liu, Shaonan Chen, Wenting Liu, Jie Luo, Xiaoling Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University China Department of Electrical Engineering City University of Hong Kong Hong Kong AI Research Center for Medical Image Analysis and Diagnosis Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

Gaze estimation is pivotal in human scene comprehension tasks, particularly in medical diagnostic analysis. Eye-tracking technology facilitates the recording of physicians’ ocular movements during image interpretation, thereby elucidating their visual attention patterns and information-processing strategies. In this paper, we initially define the context-aware gaze estimation problem in medical radiology report settings. To understand the attention allocation and cognitive behavior of radiologists during the medical image interpretation process, we propose a context-aware Gaze EstiMation (GEM) network that utilizes eye gaze data collected from radiologists to simulate their visual search behavior patterns throughout the image interpretation process. It consists of a context-awareness module, visual behavior graph construction, and visual behavior matching. Within the context-awareness module, we achieve intricate multimodal registration by establishing connections between medical reports and images. Subsequently, for a more accurate simulation of genuine visual search behavior patterns, we introduce a visual behavior graph structure, capturing such behavior through high-order relationships (edges) between gaze points (nodes). To maintain the authenticity of visual behavior, we devise a visual behavior-matching approach, adjusting the high-order relationships between them by matching the graph constructed from real and estimated gaze points. Extensive experiments on four publicly available datasets demonstrate the superiority of GEM over existing methods and its strong generalizability, which also provides a new direction for the effective utilization of diverse modalities in medical image interpretation and enhances the interpretability of models in the field of medical imaging. https://***/Tiger-SN/GEM. Copyright © 2024, The Authors. All rights reserved.

关键词： Eye movements

来源：评论

学校读者我要写书评

暂无评论

Efficient Fault Detection in Nonlinear Industrial Process: A Reduced Kernel PCA-Based Spectral Clustering Approach

Efficient Fault Detection in Nonlinear Industrial Process: A...

引用

Artificial Intelligence, Applications, Innovation and Ethics (AI2E), International Conference for

作者： Khadija Attouri Majdi Mansouri Mansour Hajji Kais Bouzrara Laboratory of Advanced Materials and Nanotechnologies Higher Institute of Applied Sciences and Technology of Kasserine Kairouan University Tunisia Department of Electrical and Computer Engineering College of Engineering Sultan Qaboos University Muscat Oman Research Laboratory of Automation Signal Processing and Image National Engineering School of Monastir Tunisia

ISBN: (数字)9798331513733

ISBN: (纸本)9798331513740

The challenges posed by nonlinearities in industrial systems necessitate innovative techniques that outperform the limitations of traditional methods such as principal component analysis (PCA). While Kernel Principal Component Analysis (KPCA) offers a robust solution to handle nonlinear data, its computational requirements are a significant issue, especially for large-sized datasets. In this work, we propose a novel technique, namely, reduced kernel principal component analysis-based spectral clustering (RKPCA SpC ), to monitor and detect faults in the benchmark Tennessee Eastman process. The suggested approach addresses the complexity associated with KPCA by reducing data size during the model training phase. This reduction involves retaining only the principal components, preserving informative features, and selecting pertinent samples without compromising the original data's content. The efficacy of the proposed method is evaluated through key performance metrics, including false alarm rate (FAR), missed detection rate (MDR), detection time delay (DTD), and computation time (CT). Additionally, gained execution time (GET), gained storage space (GSP), and loss function (LF) are considered, providing a comprehensive assessment of the developed paradigms' effectiveness. The results demonstrate the promising capabilities of our proposed scheme.

关键词： Training Measurement Technological innovation Fault detection Delay effects Computational modeling Complexity theory Kernel Monitoring Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Modeling Inter-Intra Heterogeneity for Graph Federated Learning

arXiv

引用

arXiv 2024年

作者： Yu, Wentao Chen, Shuo Tong, Yongxin Gu, Tianlong Gong, Chen School of Computer Science and Engineering Nanjing University of Science and Technology China Center for Advanced Intelligence Project RIKEN Japan State Key Laboratory of Complex & Critical Software Environment Beihang University China Jinan University China Department of Automation Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

Heterogeneity is a fundamental and challenging issue in federated learning, especially for the graph data due to the complex relationships among the graph nodes. To deal with the heterogeneity, lots of existing methods perform the weighted federation based on their calculated similarities between pairwise clients (i.e., subgraphs). However, their inter-subgraph similarities estimated with the outputs of local models are less reliable, because the final outputs of local models may not comprehensively represent the real distribution of subgraph data. In addition, they ignore the critical intra-heterogeneity which usually exists within each subgraph itself. To address these issues, we propose a novel Federated learning method by integrally modeling the Inter-Intra Heterogeneity (FedIIH). For the inter-subgraph relationship, we propose a novel hierarchical variational model to infer the whole distribution of subgraph data in a multi-level form, so that we can accurately characterize the inter-subgraph similarities with the global perspective. For the intra-heterogeneity, we disentangle the subgraph into multiple latent factors and partition the model parameters into multiple parts, where each part corresponds to a single latent factor. Our FedIIH not only properly computes the distribution similarities between subgraphs, but also learns disentangled representations that are robust to irrelevant factors within subgraphs, so that it successfully considers the inter- and intra- heterogeneity simultaneously. Extensive experiments on six homophilic and five heterophilic graph datasets in both non-overlapping and overlapping settings demonstrate the effectiveness of our method when compared with nine state-of-the-art methods. Specifically, FedIIH averagely outperforms the second-best method by a large margin of 5.79% on all heterophilic datasets. Code is available at https://***/blgpb/FedIIH. Copyright © 2024, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

VAction: A Lightweight and Integrated VR Training System for Authentic Film-Shooting Experience 25

VAction: A Lightweight and Integrated VR Training System for...

引用

Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems

作者： Shaocong Wang Che Qu Minjing Yu Chao Zhou Yuntao Wang Yu-Hui Wen Yuanchun Shi Yong-Jin Liu Department of Computer Science and Technology Tsinghua University Beijing China Film & TV Technology Department Beijing Film Academy Beijing Beijing China College of Intelligence and Computing Tianjin University Tianjin China Human Computer Interaction Technology and Intelligent Information Processing Laboratory Institute of Software Chinese Acadamy of Sciences Beijing China School of Computer Science and Technology Beijing Jiaotong University Beijing China Department of Computer science and Technology Tsinghua University Beijing China Computer Science and Technology Tsinghua University Beijing Beijing China

ISBN: (纸本)9798400713941

The film industry exerts significant economic and cultural influence, and its rapid development is contingent upon the expertise of industry professionals, underscoring the critical importance of film-shooting education. However, this process typically necessitates multiple practice in complex professional venues using expensive equipment, presenting a significant obstacle for ordinary learners who struggle to access such training environments. Despite VR technology has already shown its potential in education, existing research has not addressed the crucial learning component of replicating the shooting process. Moreover, the limited functionality of traditional controllers hinder the fulfillment of the educational requirements. Therefore, we developed VAction VR system, combining high-fidelity virtual environments with a custom-designed controller to simulate the real-world camera operation experience. The system's lightweight design ensures cost-effective and efficient deployment. Experiment results demonstrated that VAction significantly outperforms traditional methods in both practice effectiveness and user experience, indicating its potential and usefulness in film-shooting education. © 2025 Copyright held by the owner/author(s).

关键词： Film Production Education

来源：评论

学校读者我要写书评

暂无评论

Constraining Depth Map Geometry for Multi-View Stereo: A Dual-Depth Approach with Saddle-shaped Depth Cells

Constraining Depth Map Geometry for Multi-View Stereo: A Dua...

引用

International Conference on computer Vision (ICCV)

作者： Xinyi Ye Weiyue Zhao Tianqi Liu Zihao Huang Zhiguo Cao Xin Li Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Department of Computer Science University of Albany Albany NY

Learning-based multi-view stereo (MVS) methods deal with predicting accurate depth maps to achieve an accurate and complete 3D representation. Despite the excellent performance, existing methods ignore the fact that a suitable depth geometry is also critical in MVS. In this paper, we demonstrate that different depth geometries have significant performance gaps, even using the same depth prediction error. Therefore, we introduce an ideal depth geometry composed of Saddle-Shaped Cells, whose predicted depth map oscillates upward and downward around the ground-truth surface, rather than maintaining a continuous and smooth depth plane. To achieve it, we develop a coarse-to-fine framework called Dual-MVSNet (DMVSNet), which can produce an oscillating depth plane. Technically, we predict two depth values for each pixel (Dual-Depth), and propose a novel loss function and a checkerboard-shaped selecting strategy to constrain the predicted depth geometry. Compared to existing methods, DMVSNet achieves a high rank on the DTU benchmark and obtains the top performance on challenging scenes of Tanks and Temples, demonstrating its strong performance and generalization ability. Our method also points to a new research direction for considering depth geometry in MVS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Short-Term Photovoltaic Power Forecasting-Based Kernel Ridge Regression

Short-Term Photovoltaic Power Forecasting-Based Kernel Ridge...

引用

Artificial Intelligence, Applications, Innovation and Ethics (AI2E), International Conference for

作者： Manel Marweni Majdi Mansouri Mansour Hajji Mohamed Faouzi Mimouni Research Laboratory of Automation Signal Processing and Image National Engineering School of Monastir Tunisia Department of Electrical and Computer Engineering College of Engineering Sultan Qaboos University Muscat Oman Laboratory of Advanced Materials and Nanotechnologies Higher Institute of Applied Sciences and Technology of Kasserine Kairouan University Kasserine Tunisia

ISBN: (数字)9798331513733

ISBN: (纸本)9798331513740

The modern energy landscape is undergoing a seismic change from traditional, finite energy sources and toward cleaner, renewable alternatives. The restrictions faced by traditional sources, which are not only finite but increasingly shrink in the face of burgeoning global energy demands driven by population increase and industrial expansion, are driving this change. Although promising, renewable energy poses complications, particularly the reliance on climatic conditions. An important aspect of addressing these difficulties is effective energy management within distribution systems, which includes forecasting and optimization phases. This research focuses on forecasting using an advanced machine learning (ML) approach. Accurately forecasting renewable energy generation over time is critical for improving energy management. This technique is evaluated using a variety of performance indicators, including Mean Error (ME), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and the Coefficient of Determination (R 2 ). Empirical studies support the method's usefulness, demonstrating noteworthy performance with low error rates.

关键词： Photovoltaic systems Renewable energy sources Technological innovation Accuracy Machine learning Predictive models Forecasting Kernel Energy management Optimization

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：