检索结果-内蒙古大学图书馆

FMR-GNet: Forward Mix-Hop Spatial-Temporal Residual Graph Network for 3D Pose Estimation

Chinese Journal of Electronics 2024年第6期33卷 1346-1359页

作者： Honghong YANG Hongxi LIU Yumei ZHANG Xiaojun WU Key Laboratory of Modern Teaching Technology Ministry of Education Shaanxi Normal University Key Laboratory of Intelligent Computing and Service Technology for Folk Song Ministry of Culture and Tourism School of Computer Science Shaanxi Normal University

Graph convolutional networks that leverage spatial-temporal information from skeletal data have emerged as a popular approach for 3D human pose estimation. However, comprehensively modeling consistent spatialtemporal dependencies among the body joints remains a challenging task. Current approaches are limited by performing graph convolutions solely on immediate neighbors, deploying separate spatial or temporal modules, and utilizing single-pass feedforward architectures. To solve these limitations, we propose a forward multi-scale residual graph convolutional network(FMR-GNet) for 3D pose estimation from monocular video. First, we introduce a mix-hop spatialtemporal attention graph convolution layer that effectively aggregates neighboring features with learnable weights over large receptive fields. The attention mechanism enables dynamically computing edge weights at each layer. Second,we devise a cross-domain spatial-temporal residual module to fuse multi-scale spatial-temporal convolutional features through residual connections, explicitly modeling interdependencies across spatial and temporal domains. Third, we integrate a forward dense connection block to propagate spatial-temporal representations across network layers, enabling high-level semantic skeleton information to enrich lower-level features. Comprehensive experiments conducted on two challenging 3D human pose estimation benchmarks, namely Human3.6M and MPI-INF-3DHP, demonstrate that the proposed FMR-GNet achieves superior performance, surpassing the most state-of-the-art methods.

关键词： Location awareness Three-dimensional displays Correlation Graph convolutional networks Fuses Aggregates Pose estimation Semantics Benchmark testing Skeleton

来源：评论

学校读者我要写书评

暂无评论

Review of GAN-Based Research on Chinese Character Font Generation

引用

Chinese Journal of Electronics 2024年第3期33卷 584-600页

作者： Xuanhong WANG Cong LI Zengguo SUN Luying HUI Xi'an University of Posts and Telecommunications School of Computer Science Shaanxi Normal University Key Laboratory of Intelligent Computing and Service Technology for Folk Song Ministry of Culture and Tourism

With the rapid development of deep learning,generative adversarial network(GAN) has become a research hotspot in the field of computer *** has a wide range of applications in image *** by GAN,a series of models of Chinese character font generation have been proposed in recent *** this paper,the latest research progress of Chinese character font generation is analyzed and *** and its development history are ***-based methods for Chinese character font generation are clarified as well as their improvements,based on whether the specific elements of Chinese characters are *** public datasets used for font generation are summarized in detail,and various application scenarios of font generation are *** evaluation metrics of font generation are systematically summarized from both qualitative and quantitative *** paper contributes to the in-depth research on Chinese character font generation and has a positive effect on the inheritance and development of Chinese culture with Chinese characters as its carrier.

关键词： Generative adversarial network Font generation Image-to-image translation Deep learning

来源：评论

学校读者我要写书评

暂无评论

Practical Prescribed Time Tracking Control With Bounded Time-Varying Gain Under Non-Vanishing Uncertainties

引用

IEEE/CAA Journal of Automatica Sinica 2024年第1期11卷 219-230页

作者： Dahui Luo Yujuan Wang Yongduan Song the Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of EducationChongqing UniversityChongqing 400044 the School of Automation Chongqing UniversityChongqing 400044 the Star Institute for Intelligent Systems Chongqing 400044 IEEE

This paper investigates the prescribed-time control(PTC) problem for a class of strict-feedback systems subject to non-vanishing uncertainties. The coexistence of mismatched uncertainties and non-vanishing disturbances makes PTC synthesis nontrivial. In this work, a control method that does not involve infinite time-varying gain is proposed, leading to a practical and global prescribed time tracking control solution for the strict-feedback systems, in spite of both the mismatched and nonvanishing uncertainties. Different from methods based on control switching to avoid the issue of infinite control gain that involves control discontinuity at the switching point, in our method a softening unit is exclusively included to ensure the continuity of the control action. Furthermore, in contrast to most existing prescribed-time control works where the control scheme is only valid on a finite time interval, in this work, the proposed control scheme is valid on the entire time interval. In addition, the prior information on the upper or lower bound of gi is not in need,enlarging the applicability of the proposed method. Both the theoretical analysis and numerical simulation confirm the effectiveness of the proposed control algorithm.

关键词： Adaptive control prescribed time control(PTC) strict-feedback systems tracking control

来源：评论

学校读者我要写书评

暂无评论

TFSWA-UNet: Temporal-Frequency and Shifted Window Attention Based UNet for Music Source Separation

TFSWA-UNet: Temporal-Frequency and Shifted Window Attention ...

引用

2024 International Conference on Culture-Oriented Science and Technology, CoST 2024

作者： Yao, Zhenyu Su, Yuping Yang, Honghong Wu, Xiaojun Zhang, Yumei Shaanxi Normal University Key Laboratory of Intelligent Computing and Service Technology for Folk Song Ministry of Culture and Tourism School of Computer Science Xi'an China Key Laboratory of Modern Teaching Technology Ministry of Education Xi'an China Key Laboratory of Intelligent Computing and Service Technology for Folk Song Ministry of Culture and Tourism Xi'an China

ISBN: (纸本)9798350380347

The performance of music source separation (MSS) has been greatly improved in recent years due to the rapid development of various neural network architectures. Spectrogram features are widely used in MSS tasks which consists of both time and frequency information. However, the time and frequency correlations and the local patterns of spectrogram have not been fully explored. In this paper, we propose a novel U-Net architecture named TFSWA-UNet in which a temporal-frequency and shifted window attention (TFSWA) based block is designed as bottleneck block. In the proposed TFSWA block, time sequence attention (TSA) block and frequency sequence attention (FSA) block are used to capture the global correlation of music spectrogram features within time and frequency sequences respectively. To further capture the local correlations of spectrogram features, shifted window attention based Swin transformer is also introduced into the TFSWA module, which computes self-attention within local non-overlapping windows and capture correlations from both temporal and frequency dimensions. Experiment results on MUSDB18 dataset indicate that the proposed TFSWA-UNet model outperforms the state-of-the-art MSS methods with SDR of 9.16dB on vocals. © 2024 IEEE.

关键词： Spectrographs

来源：评论

学校读者我要写书评

暂无评论

CGNet: Classification-Guided Multi-Task Interactive Network for Hyperspectral and Multispectral Image Fusion

CGNet: Classification-Guided Multi-Task Interactive Network ...

引用

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

作者： Lv, Guohua Xu, Yanlong Gao, Yongbiao Zhao, Guixin Wang, Guotao Sun, Xiangcheng Jinan China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China Shandong Key Laboratory of Ubiquitous Intelligent Computing Jinan China Ministry of Education China Beihang University Beijing China

ISBN: (纸本)9798350368741

The goal of fusing hyperspectral images (HSI) and multispectral images (MSI) is to generate high-resolution hyperspectral images for downstream tasks. However, most existing methods overlook the specific requirements of these tasks, leading to a gap between the fusion process and its subsequent applications due to insufficient guidance from downstream tasks. To address this issue, we propose a classification-guided multitask interactive network (CGNet) that integrates both fusion and classification tasks into a unified framework, with two branches producing the fused image and classification results, respectively. In the fusion branch, we design a multi-level residual refinement module to efficiently integrate spatial and spectral information. Additionally, an attention-based multi-scale fusion module, incorporating both spatial and channel attention, is carefully crafted to enhance representation learning. In the classification branch, both 2-D and 3-D convolutions are employed to improve classification performance. Moreover, an information interaction module is proposed to guide the fusion task based on classification outcomes. Extensive experiments demonstrate that our method outperforms state-of-the-art approaches on the Pavia Centre and Pavia University datasets. © 2025 IEEE.

关键词： Feature interaction Hyperspectral classification Hyperspectral image Image fusion

来源：评论

学校读者我要写书评

暂无评论

A Grouping Strategy-Based Progressive Fusion Network for Hyperspectral Image Super-Resolution

A Grouping Strategy-Based Progressive Fusion Network for Hyp...

引用

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

作者： Lv, Guohua Zhang, Baodong Gao, Yongbiao Zhao, Guixin Wang, Guotao Wang, Juncan Jinan China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China Shandong Key Laboratory of Ubiquitous Intelligent Computing Jinan China Ministry of Education China Beihang University Beijing China

ISBN: (纸本)9798350368741

Hyperspectral super-resolution involves combining low-resolution hyperspectral images with high-resolution multispectral images to produce a high-resolution hyperspectral image. Recently, although many methods for hyperspectral image super-resolution have been proposed, they often fail to fully utilize the high similarity among adjacent bands to enhance fusion performance. Therefore, we propose a grouping strategy-based progressive fusion network (GPFNet) for hyperspectral super-resolution. The core of GPFNet is the grouping strategy fusion block (GPF block), in which grouping-based spatial-spectral information fusion and spatial information refinement are performed. We design the spatial-spectral information fusion module (SSIFM) based on grouped convolutions to capture the feature differences from adjacent bands. To refine spatial details, we develop the spatial information enhancement module (SpaEM), which leverages the hierarchical features extracted by the multi-scale feature extraction module (MIEM). Additionally, a progressive fusion strategy, which involves using multiple upsampled hyperspectral images and downsampled multispectral images, further preserves spectral integrity and spatial details. Extensive experiments show that GPFNet outperforms state-of-the-art methods both qualitatively and quantitatively. © 2025 IEEE.

关键词： group convolution Hyperspectral image image fusion super-resolution

来源：评论

学校读者我要写书评

暂无评论

A Chinese Font Generation Method based on Dynamic Convolution Improved Generative Adversarial Network

A Chinese Font Generation Method based on Dynamic Convolutio...

引用

2024 International Conference on Culture-Oriented Science and Technology, CoST 2024

作者： Guo, Xuefei Zhao, Li Wu, Xiaojun Yang, Honghong Man, Yufang Shaanxi Normal University School of Computer Science Xi'an China Key Laboratory of Intelligent Computing and Service Technology for Folk Song Ministry of Culture and Tourism Xi'an China Ministry of Education Key Laboratory of Modern Teaching Technology Xi'an China

ISBN: (纸本)9798350380347

Font generation is a challenging research topic in the field of computer vision, aiming to apply the style from a reference image to a source character image. The core task of font generation is to generate images, especially complex character images, that closely resemble the style of the reference font while maintaining the original glyph structure. This paper proposes a novel font generation method based on the generation adversarial network (GAN). Firstly, a new unsupervised end-to-end Chinese font generation network is designed. Then, a Convolution-Transformer (CNNTrans) module is devised to extract style features from global and local with attention constraint. Finally, a dynamic convolutional skip connection module (DCSC) is proposed to dynamically fuse font content and style according the importance of content and style features in different positions. Experimental results demonstrate that the proposed font generation method can generate higher quality styled fonts compared to other methods. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A Dataset for Generating Chinese Landscape Painting

A Dataset for Generating Chinese Landscape Painting

引用

2023 International Conference on Culture-Oriented Science and Technology, CoST 2023

作者： Sun, Zengguo Li, Haoyue Wu, Xiaojun Zhang, Yumei Guo, Rong Wang, Biyu Dong, Liren Key Laboratory of Intelligent Computing and Service Technology for Folk Song Ministry of Culture and Tourism Xi'an China School of Computer Science Shaanxi Normal University Xi'an China

ISBN: (纸本)9798350357998

A dataset was constructed for intelligent generation of Chinese landscape paintings based on deep learning, which provides the scientific assistance for inheriting the traditional Chinese culture. This dataset is originated from the two of top ten paintings in ancient China, i.e., 'Dwelling in the Fuchun Mountains' with ink wash style and 'A Thousand Li of Rivers and Mountains' with style of blue and green. This dataset contains landscape paintings and their corresponding sketches, as well as photos of natural landscapes. The samples of landscape paintings are achieved with the size of 256× 256 due to the technique of image preprocessing, the samples of sketches are generated by the canny edge detector, and the samples of landscape photos are formed by image flipping. The above samples of landscape paintings, sketches, and photos make the dataset more flexible for the generation of landscape paintings. Based on this dataset, landscape paintings can be generated from sketches and photos respectively, and landscape paintings can be transferred from one style to another. The experimental results demonstrate the suitability of the dataset for the field of landscape painting generation. The constructed dataset will be publicly available to the community. © 2023 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Facial StO2-based Stress Recognition using Automatic Graph Generation and Dual-Stream GNN

Facial StO2-based Stress Recognition using Automatic Graph G...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Jia, Yingjuan Wang, Hanpu Liu, Xinyu Chen, Tong Southwest University College of Electronic and Information Engineering 400715 China Southwest University Chongqing Key Laboratory of Generic Technology and System of Service Robots China Southwest University Institute of Legal Psychology and Intelligent Computing 400715 China

ISBN: (纸本)9798350386226

The recognition of stress responses in health, resilience, and psychopathology holds significant scientific importance. The biological information carried by the facial tissue oxygen saturation (StO2) is a useful indicator for stress recognition. Although graph-based methods have achieved state-of-the-art (SOTA), there is room for improvement. This study proposes an automatic graph generation method for facial StO2, replacing manual methods and enhancing the information of graphs. To further enhance the capability of graphs' representation, a dimensionality reduction strategy for nodes is proposed. The strategy is implemented based on an novel objective function that can increase the inter-class distance and reduce the intra-class distance. After obtaining highly representative graphs, a dual-stream network integrating GAT and GCN is designed to extract stress-related features from the graphs, ultimately achieving the SOTA recognition accuracy. © 2024 IEEE.

关键词： Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

KF-TMIAF: An Efficient key-Frames-Based Temporal Modeling of Images and AU Features structure for Masked Facial Expression Recognition

KF-TMIAF: An Efficient Key-Frames-Based Temporal Modeling of...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Gu, Huijie Wang, Hanpu He, Shiwei Li, Mengyan Zhou, Jianmeng Chen, Tong Southwest University College of Electronic and Information Engineering Chongqing400715 China Swu Chongqing Key Laboratory of Generic Technology and System of Service Robots China Southwest University Institute of Legal Psychology and Intelligent Computing Chongqing400715 China

ISBN: (纸本)9798350386226

Masked Facial Expression refers to facial expression that people deliberately make which do not correspond to their true emotions. The purpose of masked facial expression is to conceal one's genuine feelings. Precisely identifying masked facial expression aids in revealing the genuine emotions, and finds applications in diagnosis of mental illness. However, the masked facial expression sequences have redundant information, temporal modeling is difficult, and the expressive ability of AU features needs to be improved. To solve the existing problems, we first propose a key frame Selection and Data Augmentation (KS-DA) method to obtain the key frame in the sequence. In addition, we propose a Global Feature Relation Block (GFR) to aggregate global information and combine it with Temporal Convolutional Networks (TCN) to better realize temporal modeling. Finally, we propose an Adaptive Weight Generation Module (Ada-WGM) to form different weights from adaptation, allowing for better extraction of the temporal changes in AU features. Finally, the experiments have shown that the proposed method has improved the mixed expression classification task (36 task) by 15.23% and the experienced emotions classification task (6E task) by 17.77%, respectively, and obtain sort results. © 2024 IEEE.

关键词： Convolutional neural networks

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：