检索结果-内蒙古大学图书馆

DCT-DiffPose: A Lightweight Diffusion Model with Multi-Hypothesis for 3D Human Pose Estimation

IEEE Access 2025年 13卷 73319-73331页

作者： Zhong, Linzhan Chen, Fangni Zheng, Bolun Feng, Rui Zhang, Lei Wan, Jian Zhejiang University of Science and Technology The College of Information and Electronic Engineering Hangzhou310023 China The Zhejiang Key Laboratory of Biomedical Intelligent Computing Technology Hangzhou310023 China Hangzhou Dianzi University School of Automation Hangzhou310018 China

3D human pose estimation is a crucial task in computer vision with extensive applications, yet it remains challenging due to depth ambiguity and constraints on computational efficiency. In this paper, we propose DCT-DiffPose, a novel framework that integrates a diffusion model with Confidence and Consistency-based Multi-Hypothesis Aggregation (CCMA). Moreover, it incorporate the Discrete Cosine Transform (DCT) for frequency-domain feature extraction. Specifically, the diffusion model generates diverse and plausible hypotheses, and CCMA aggregates them based on confidence and consistency, effectively addressing depth ambiguity. Additionally, we incorporate DCT into the self-attention mechanism to transform input data into the frequency domain, thereby enhancing feature extraction while significantly reducing computational complexity. To validate DCT-DiffPose, we conducted extensive experiments on the Human3.6M and MPI-INF-3DHP datasets. Our method achieves a 19% lower Mean Per Joint Position Error (MPJPE) and a 55% reduction in FLOPs compared to D3DP. The results demonstrate its excellent trade-off between accuracy and complexity. © 2013 IEEE.

关键词： Discrete cosine transforms

来源：评论

学校读者我要写书评

暂无评论

GCINet: global convolution interaction network with a pre-trained reversible normalization method for long-term time series forecasting

引用

Neural computing and Applications 2025年第5期37卷 3227-3244页

作者： Fan, Jin Yang, Baoshun Sun, Danfeng Liu, Jie Chen, Qikai Wang, Zhipeng Wu, Jia Hangzhou Dianzi University Hangzhou China Key Laboratory of Intelligent Education Technology and Application of Zhejiang Province Zhejiang Normal University Hangzhou China School of Computing Macquarie University Sydney Australia

Long-term time series forecasting is crucial in various domains, such as weather forecasting and disease forecasting. With the rise of Transformer-based models, we have witnessed a significant improvement in long-term prediction accuracy, as these models use self-attention to capture long-term temporal features in the data during feature extraction. However, this approach has several drawbacks: Firstly, self-attention has quadratic complexity, and reducing its complexity often results in reduced prediction accuracy. Secondly, the distribution of time series data frequently changes over time, a phenomenon known as distribution shift, which is not taken into consideration in most Transformer-based models. This leads to decreased prediction accuracy as the distribution deviates from the one used for model training. Therefore, we have developed a new time series forecasting model, GCINet, which introduces a new mode of interaction based on a convolutional network. This captures both long-term and short-term temporal features while reducing complexity during feature extraction. Additionally, GCINet includes an Inverse Trained Normalization method to address distribution shift, bringing a fresh perspective to the design of time series forecasting models. Our experiments on long-term forecasting tasks demonstrate that GCINet outperforms other commonly used models. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Bilateral Pricing for Dynamic Association in Federated Edge Learning

引用

IEEE Transactions on Mobile computing 2025年第6期24卷 4684-4697页

作者： Pan, Bangqi Lu, Jianfeng Cao, Shuqin Liu, Jing Tian, Wenlong Li, Minglu Wuhan University of Science and Technology School of Computer Science and Technology Wuhan430065 China Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System China Dalian University of Technology Ministry of Education Key Laboratory of Social Computing and Cognitive Intelligence China University of South China School of Computer Science and Technology Hengyang421001 China Zhejiang Normal University School of Computer Science and Technology Jinhua321004 China

Devices and servers in Federated Edge Learning (FEL) are self-interested and resource-constrained, making it critical to design incentives to improve model performance. However, dynamic network conditions raise energy consumption, while data heterogeneity undermines device cooperation. Current research overlooks the interplay between system efficiency and device clustering, resulting in suboptimal updates. To address these challenges, we develop BENCH, a bilateral pricing mechanism consisting of three core rules aimed at incentivizing participation from both devices and servers. Specifically, we first design a reward allocation rule, based on the Rubinstein bargaining model, which dynamically allocates rewards. Theoretically, we derive a closed-form solution for this rule, demonstrating BENCH achieves Nash equilibrium. Secondly, we design a device partitioning rule that leverages modularity to group similar devices, facilitating personalized edge aggregation to accelerate local data adaptation. Thirdly, we design an edge matching rule that employs the Kuhn-Munkres algorithm to balance the load at edge servers, thus minimizing the congestion. Together, these three rules enable hierarchical optimization of pricing and associations, effectively mitigating the impact of dynamic costs and device heterogeneity. Extensive experiments demonstrate BENCH's effectiveness in increasing device participation by 28.81% and improving model performance by 2.66% compared to state-of-the-art baselines. © 2002-2012 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

GoPIM: GCN-Oriented Pipeline Optimization for PIM Accelerators 31

GoPIM: GCN-Oriented Pipeline Optimization for PIM Accelerato...

引用

31st IEEE International Symposium on High Performance Computer Architecture, HPCA 2025

作者： Yang, Siling He, Shuibing Wang, Wenjiong Yin, Yanlong Wu, Tong Chen, Weijian Zhang, Xuechen Sun, Xian-He Feng, Dan The State Key Laboratory of Blockchain and Data Security Zhejiang University China Zhejiang Lab China Institute of Blockchain and Data Security China Zhejiang Key Laboratory of Big Data Intelligent Computing China Washington State University Vancouver United States Illinois Institute of Technology United States Huazhong University of Science and Technology China Wuhan National Laboratory for Optoelectronics China

ISBN: (纸本)9798331506476

Graph convolutional networks (GCNs) are popular for a variety of graph learning tasks. ReRAM-based processing-in-memory (PIM) accelerators are promising to expedite GCN training owing to their in-situ computing capability. However, existing accelerators can be severely underutilized even with pipelines, due to the oversight of the skewed execution times of various GCN stages and the ignorance of skewed degrees of graph vertices. In this work, we propose GOPIM, a GCN-oriented pipeline optimization for PIM accelerators to expedite GCN training. First, GOPIM proposes an ML-based scheme that allocates crossbar resources to the most needed stages to streamline the overall pipeline. Second, GOPIM utilizes a selective vertex updating technique that evenly distributes vertices on crossbars by interleaved mapping. These techniques collectively reduce the overall execution time without losing much accuracy. We also provide a practical architecture design for GOPIM. Our experimental results show that, GoPIM achieves up to 191 × speedup and 16.1 × energy saving, compared to the state-of-the-art work. © 2025 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A Dual-Capture and Dual-Output 3D DNA Walker System Integrated with Ligases Enables Ultrasensitive Detection of Single-Nucleotide Polymorphisms

引用

Analytical Chemistry 2025年第17期97卷 9316-9325页

作者： Zhang, Yunshan Tan, Qianglong Yang, Fang Huang, Tuo Yu, Siyu Ye, Jing Zeng, Jianxian Feng, Xianzhong Zhang, Diming Key Laboratory of Soybean Molecular Design Breeding National Key Laboratory of Black Soils Conservation and Utilization Northeast Institute of Geography and Agroecology Chinese Academy of Sciences Changchun130102 China Research Center for Novel Computing Sensing and Intelligent Processing Zhejiang Laboratory Hangzhou311121 China Hangzhou Institute for Advanced Study University of Chinese Academy of Sciences Zhejiang Hangzhou310024 China School of Chemistry and Chemical Engineering Hunan University of Science and Technology Hunan Xiangtan411201 China

DNA walkers, as structurally and functionally programmable signal amplification tools, exhibit great potential for application in the field of biosensing. Traditional DNA walkers often rely on enzymes for operation, posing compatibility challenges, while the handful of existing enzyme-free DNA walkers demonstrate limited performance. To address this, we innovatively developed an efficient enzyme-free 3D DNA walker with dual capture and dual output capabilities. Coupled with ligase chain reaction (LCR), this system facilitates highly sensitive and specific detection of single nucleotide polymorphisms (SNPs). Specifically, LCR precisely identifies single-base mutations, effectively transmitting biological information. The 3D DNA walker system is based on entropy-driven circuit cycling reaction technology. In this system, LCR products serve as the driving strands for the DNA walker, independently binding to track strands and walking legs immobilized on gold nanoparticles, forming a unique dual signal capture mechanism. Each track strand carries two signal chains, significantly enhancing signal amplification efficiency. Benefiting from this novel enzyme-free 3D DNA walker strategy, our biosensing system exhibits exceptional sensitivity to mutant targets (MT), detecting MT at concentrations as low as 30.3 aM and distinguishing heterozygous samples with a 0.01% mutation frequency. Furthermore, this system has been successfully applied to genotyping and mutation abundance assessment of genomes from fresh soybean leaves, demonstrating its vast potential for practical applications. In summary, this research pioneers a novel enzyme-free 3D DNA walker with dual capture and dual output capabilities, and develops an ultrasensitive genotyping tool. This provides strong technical support for the advancement of genetic research. © 2025 American Chemical Society.

关键词： Nucleotides

来源：评论

学校读者我要写书评

暂无评论

Correlation Information Enhanced Graph Anomaly Detection via Hypergraph Transformation

引用

IEEE Transactions on Cybernetics 2025年第6期55卷 2865-2878页

作者： Huang, Changqin Gao, Chengling Li, Ming Li, Yongzhi Wang, Xizhe Jiang, Yunliang Huang, Xiaodi Zhejiang Key Laboratory of Intelligent Education Technology and Application Zhejiang Normal University Jinhua321004 China College of Education Zhejiang University Hangzhou310058 China Zhejiang Institute of Optoelectronics Jinhua321004 China China National Academy of Educational Sciences Beijing100088 China School of Information Engineering Huzhou University Huzhou313000 China School of Computing Mathematics and Engineering Charles Sturt University AlburyNSW2640 Australia

Graph anomaly detection (GAD) has attracted increasing interest due to its critical role in diverse real-world applications. Graph neural networks (GNNs) offer a promising avenue for GAD, leveraging their exceptional capacity to model complex graph structures and relationships. However, existing GNN-based models encounter challenges in addressing the GAD's fundamental issue - anomaly camouflage, where anomalies mimic normal instances, leading to indistinguishable features. In this article, we propose a novel approach, termed correlation information enhanced GAD (CIE-GAD). Specifically, drawing on the observation that the distribution of homophilic and heterophilic edges differs between abnormal and normal samples, we construct a hypergraph to learn the co-occurrence relationships among adjacent edges. By enhancing the extraction of sample correlation information, we effectively tackle feature similarity caused by anomaly camouflage, thereby enhancing the performance of GAD. Furthermore, we develop a spectral convolution mechanism based on node-level attention fusion, enabling the capture of multifrequency signals. This module performs adaptive fusion tailored to the unique frequency information requirements of each node, mitigating the local heterophily problem. Extensive experiments on various real-world GAD datasets demonstrate that the proposed CIE-GAD outperforms state-of-the-art methods. Notably, our approach achieves AUC-PR improvements of up to 3.47%, with an average gain of 1.5%, demonstrating its effectiveness in detecting anomalies in graph data. © 2025 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

SnapCFL: A Pre-clustering-based Clustered Federated Learning Framework for Data and System Heterogeneities

引用

IEEE Transactions on Mobile computing 2025年第6期24卷 5214-5228页

作者： Cheng, Yujun Zhang, Weiting Zhang, Zhewei Kang, Jiawen Xu, Qi Wang, Shengjin Niyato, Dusit Tsinghua University Department of Electronic Information Engineering Beijing100084 China Beijing Jiaotong University School of Electronic and Information Engineering Beijing100044 China Guangdong University of Technology School of Automation China Guangdong Key Laboratory of IoT Information Technology Guangzhou510006 China Zhejiang Lab Intelligent Computing Infrastructure Innovation Center Hangzhou311100 China Nanyang Technological University School of Computer Science and Engineering 639798 Singapore

Federated Learning (FL) has emerged as a promising framework to address data privacy concerns associated with mobile devices, in contrast to conventional Machine Learning (ML). However, traditional FL encounters significant challenges due to the heterogeneities among different clients. Clustered Federated Learning (CFL) has demonstrated effectiveness in mitigating the data heterogeneity challenge, which significantly limits a broader application of FL. Nevertheless, existing CFL approaches often tightly couple the clustering process with the main FL process, affecting the flexibility and performance of CFL. In this paper, we propose a pre-clustering-based CFL approach, named SnapCFL, which decouples the CFL process into pre-clustering and main FL stages, considering both the impact of heterogeneity on CFL accuracy and the framework's flexibility. The pre-clustering stage models the measurement of data similarity as a two-sample hypothesis testing problem to more accurately group clients and alleviate data heterogeneity. In the main FL stage, a constraint-based client selection method is employed to address the system heterogeneity problem. We conduct extensive experiments using popular datasets with various heterogeneity settings. The results demonstrate that SnapCFL achieves excellent performance in terms of accuracy and efficiency. Compared to five other state-of-the-art approaches, SnapCFL can improve model accuracy by 0.7%∼36.4%, and achieve the same level of accuracy with at least 0.08× the convergence time. © 2002-2012 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Multi-granularity feature intersection learning for visible-infrared person re-identification

引用

Complex & intelligent Systems 2025年第7期11卷 1-14页

作者： Chan, Sixian Wang, Jie Cui, Jiaao Hu, Jie Li, Zhuorong Mao, Jiafa College of Computer Science and Technology Zhejiang University of Technology Hangzhou China Key Laboratory of Intelligent Informatics for Safety & Emergency of Zhejiang Province Wenzhou University Wenzhou China School of Computer and Computing Science Hangzhou City University Hangzhou China

This paper proposes a multi-granularity feature intersection network (MGFINet) for visible-infrared person re-identification (VI-ReID). VI-ReID aims to retrieve images of the same pedestrian from different spectral cameras. The key challenge is to extract pedestrian descriptions with both inter-class discriminability and intra-class similarity. Previous methods ignore the potential loss of details during representation extraction and the presence of data bias in the metric function, limiting further improvements in retrieval performance. Meanwhile, the discrepancy regarding how to calculate the loss for representation learning and metric learning also affects the model’s training. To address the above issues, MGFINet consists of three components: a hierarchical part pooling method (HPP), a hierarchical part restriction method (HPC), and a feature intersection (FI) loss. HPP adopts a hierarchical framework to extract multi-granularity pedestrian representations, and it performs an inter-layer fusion operation to exploit the high-resolution information from shallow layers and the semantic representability from deep layers. Meanwhile, HPP employs part pooling with different step sizes to capture pedestrian details in each layer. Next, HPC spreads the identity loss across all layers to reduce the distance for gradient backpropagation and further optimize fine-grained features in shallow layers. Besides, FI loss combines representation and metric learning by incorporating hyperparameters of classifiers into metric learning, mitigating data bias and reducing the gap between the two learning processes. Finally, extensive experiments evaluated on two public datasets, SYSU-MM01 and RegDB demonstrate the effectiveness of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

: heterogeneous hypergraph attention network with counterfactual learning for multimodal sentiment analysis

引用

Complex & intelligent Systems 2025年第4期11卷 1-16页

作者： Huang, Changqin Lin, Zhenheng Huang, Qionghao Huang, Xiaodi Jiang, Fan Chen, Jili Zhejiang Key Laboratory of Intelligent Education Technology and Application Zhejiang Normal University Jinhua China School of Education Zhejiang Normal University Jinhua China School of Computer Science and Technology Zhejiang Normal University Jinhua China School of Computing Mathematics and Engineering Charles Sturt University Albury Australia

Multimodal sentiment analysis (MSA) has garnered significant attention for its immense potential in human-computer interaction. While cross-modality attention mechanisms are widely used in MSA to capture inter-modality interactions, existing methods are limited to pairwise interactions between two modalities. Additionally, these methods can not utilize the causal relationship to guide attention learning, making them susceptible to bias information. To address these limitations, we introduce a novel method called Heterogeneous Hypergraph Attention Network with Counterfactual Learning $$(\text {H}^2\text {CAN}).$$ The method constructs a heterogeneous hypergraph based on sentiment expression characteristics and employs Heterogeneous Hypergraph Attention Networks (HHGAT) to capture interactions beyond pairwise constraints. Furthermore, it mitigates the effects of bias through a Counterfactual Intervention Task (CIT). Our model comprises two main branches: hypergraph fusion and counterfactual fusion. The former uses HHGAT to capture inter-modality interactions, while the latter constructs a counterfactual world using Gaussian distribution and additional weighting for the biased modality. The CIT leverages causal inference to maximize the prediction discrepancy between the two branches, guiding attention learning in the hypergraph fusion branch. We utilize unimodal labels to help the model adaptively identify the biased modality, thereby enhancing the handling of bias information. Experiments on three mainstream datasets demonstrate that $$\text {H}^2\text {CAN}$$ sets a new benchmark.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MULTI-LABEL FEATURE SELECTION BASED ON BINARY HASHING LEARNING AND DYNAMIC GRAPH CONSTRAINTS

arXiv

引用

arXiv 2025年

作者： Guo, Cong Huang, Changqin Zhou, Wenhua Huang, Xiaodi Key Laboratory of Intelligent Education Technology and Application of Zhejiang Province Zhejiang Normal University Jinhua China School of Computing Mathematics and Engineering Charles Sturt University Albury Australia

Multi-label learning poses significant challenges in extracting reliable supervisory signals from the label space. Existing approaches often employ continuous pseudo-labels to replace binary labels, improving supervisory information representation. However, these methods can introduce noise from irrelevant labels and lead to unreliable graph structures. To overcome these limitations, this study introduces a novel multi-label feature selection method called Binary Hashing and Dynamic Graph Constraint (BHDG), the first method to integrate binary hashing into multi-label learning. BHDG utilizes low-dimensional binary hashing codes as pseudo-labels to reduce noise and improve representation robustness. A dynamically constrained sample projection space is constructed based on the graph structure of these binary pseudo-labels, enhancing the reliability of the dynamic graph. To further enhance pseudo-label quality, BHDG incorporates label graph constraints and inner product minimization within the sample space. Additionally, an l2,1-norm regularization term is added to the objective function to facilitate the feature selection process. The augmented Lagrangian multiplier (ALM) method is employed to optimize binary variables effectively. Comprehensive experiments on 10 benchmark datasets demonstrate that BHDG outperforms ten state-of-the-art methods across six evaluation metrics. BHDG achieves the highest overall performance ranking, surpassing the next-best method by an average of at least 2.7 ranks per metric, underscoring its effectiveness and robustness in multi-label feature selection. Copyright © 2025, The Authors. All rights reserved.

关键词： Graph theory

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：