检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

17 篇 会议
13 篇 期刊文献

馆藏范围

30 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

21 篇 工学
- 17 篇 计算机科学与技术...
- 14 篇 软件工程
- 7 篇 信息与通信工程
- 5 篇 控制科学与工程
- 2 篇 机械工程
- 2 篇 电气工程
- 2 篇 生物工程
- 1 篇 光学工程
- 1 篇 电子科学与技术（可...
- 1 篇 建筑学
- 1 篇 土木工程
- 1 篇 交通运输工程
- 1 篇 生物医学工程（可授...
10 篇 理学
- 7 篇 数学
- 3 篇 物理学
- 2 篇 生物学
- 2 篇 统计学（可授理学、...
5 篇 管理学
- 5 篇 图书情报与档案管...
- 1 篇 管理科学与工程(可...

主题

5 篇 semantics
3 篇 feature extracti...
3 篇 feature selectio...
2 篇 text categorizat...
2 篇 deep learning
2 篇 graph neural net...
2 篇 image classifica...
2 篇 data models
2 篇 training
2 篇 clothing
1 篇 plant disease id...
1 篇 prediction model...
1 篇 disentangled rep...
1 篇 deep neural netw...
1 篇 indexes
1 篇 reliability engi...
1 篇 human parsing
1 篇 time factors
1 篇 recommender syst...
1 篇 variational tech...

机构

16 篇 guangxi key lab ...
7 篇 school of comput...
4 篇 college of mathe...
3 篇 school of comput...
3 篇 department of co...
2 篇 guangxi key labo...
2 篇 guangxi key labo...
2 篇 nanning normal u...
2 篇 school of system...
2 篇 department of da...
2 篇 communication in...
2 篇 nanning normal u...
2 篇 guangxi academy ...
1 篇 school of comput...
1 篇 digital media ar...
1 篇 zhidayuan ai lab...
1 篇 the school of of...
1 篇 school of mahari...
1 篇 college of compu...
1 篇 the school of co...

作者

10 篇 huang faliang
4 篇 qin xiao
3 篇 faliang huang
3 篇 zhao jie
3 篇 xiao qin
3 篇 wang jiahai
2 篇 zhao jianbo
2 篇 yang xiaochen
2 篇 liu yang
2 篇 liao jianping
2 篇 zhang guangyu
2 篇 huang enbo
2 篇 peng yuzhong
2 篇 bi yingzhou
2 篇 lei peng
2 篇 xiaochen yang
2 篇 jinyong zhang
2 篇 zhang yuan
2 篇 wang wenji
2 篇 ling yun

语言

26 篇 英文
3 篇 其他
2 篇 中文

检索条件"机构=Guangxi Key Laboratory of Human-Computer Interaction and Intelligent Decision Making"

共 30 条记录，以下是1-10 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

BGNN-TC: BERT GNN Based Text Classification Algorithm 1

BGNN-TC: BERT GNN Based Text Classification Algorithm

引用

1st IEEE International Conference on Data Intelligence and Innovative Application, DIIA 2024

作者： Zhao, Jianbo Qin, Xiao Peng, Lei Zhang, Jinyong Wang, Wenji Zheng, Hongchun Nanning Normal University Guangxi Key Laboratory of Human-Computer Interaction and Intelligent Decision Making Nanning China

ISBN: (纸本)9798331504434

The traditional Text-Level-GNN effectively captures the structural information of texts but fails to fully extract the semantic information of words during text-level composition. To address this limitation, we employ BERT to initialize the word nodes within text-level graphs, constructing a graph network that integrates both spatial structure and semantic information. Based on BERT optimization, we proposes a BGNN-TC based text classification algorithm to enhance the performance of existing methods, particularly on long-text classification tasks. This approach leverages the strengths of large-scale pre-trained models and text-level graph neural networks. We perform text category prediction using both BERT+GNN and BERT models based on word features from text-level compositions and train the model with a mixed loss of the two prediction results. Experiments on the R8, R52, and Ohsumed datasets demonstrate that the proposed method achieves outstanding performance in handling long texts, effectively extracting both semantic and structural information. The results highlight the robustness and generalization capabilities of the model. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Implementation of Person Re-Identification Algorithm Based on Huawei Mindspore and Pytorch Hybrid Architecture 1

Implementation of Person Re-Identification Algorithm Based o...

引用

1st IEEE International Conference on Data Intelligence and Innovative Application, DIIA 2024

作者： Deng, Chao Yang, Xiaochen Qin, Xiao Peng, Lei Zhang, Jinyong Wang, Wenji Qian, Quanmei Zhao, Jianbo Nanning Normal University Guangxi Key Laboratory of Human-Computer Interaction and Intelligent Decision Nanning China

ISBN: (纸本)9798331504434

Based on Huawei's Mindspore and Pytorch hybrid architecture, this paper carries out localization operation of the current mainstream pedestrian re-recognition algorithm - AGW model, and makes it successfully run correctly on the domestic hardware platform. In this paper, the construction mode of Mindspore map and the technical characteristics of Mindspore branch structure in the process of localization of pedestrian rerecognition model are deeply analyzed, and the difficulties of localization of AGW model are explored. The effects of the implementation of data processing logic in different frameworks on the running performance of AGW localization model are studied. Develop a cross-framework parameter mapping module to map the parameters in Pytorch to the Mindspore framework in order to maintain the performance of the localized AGW model. Finally, the visualization module proposed in this paper can track the feature map changes in the domestic AGW model. In this paper, the domestic AGW model was tested on SYSU-MM01 and RegDB data sets, and its performance in RANK1 index and mAP index reached more than 80% of the original model. The experimental results show that the localized AGW model based on Huawei's Mindspore and Pytorch hybrid architecture runs successfully and correctly on the localized platform. © 2024 IEEE.

关键词： hybrid architecture localization Mindspore pedestrian re-recognition Pytorch

来源：评论

学校读者我要写书评

暂无评论

Fine-Grained Image Classification Model M-ResNet50 Based On Small Collar Dataset 1

Fine-Grained Image Classification Model M-ResNet50 Based On ...

引用

1st IEEE International Conference on Data Intelligence and Innovative Application, DIIA 2024

作者： Yang, Xiaochen Qin, Xiao Meng, Baiqi Li, Xiaolian Ya, Shanshan Nanning Normal University Guangxi Key Laboratory of Human-Computer Interaction and Intelligent Decision Nanning China

ISBN: (纸本)9798331504434

Within this manuscript, a refined model, MResNet50, which builds upon the ECA-ResNet50 framework, is suggested for the nuanced classification of collar images, complemented by the introduction of the MC-Loss function. Because the collars' inter-class differences are concentrated in a small area of the image, traditional classification networks are difficult to distinguish effectively. The M-ResNet50 model significantly improves classification performance by focusing on discriminative and discriminative regions. Experimental results on the Collar-6 private dataset show that M-ResNet50 not only outperforms several classical and novel classification models, but also has better separability of extracted features. In addition, MResNet50's experiments on the public dataset DeepFashion also verified its effectiveness in the field of clothing image classification, indicating that the model is not only suitable for collar image classification, but also can be extended to a wider range of clothing image classification tasks. © 2024 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

FasterPlateNet: A Faster Deep Neural Network for License Plate Detection and Recognition 1st

FasterPlateNet: A Faster Deep Neural Network for License Pla...

引用

1st International Conference on Applied Intelligence, ICAI 2023

作者： Huang, Lei Huang, De Shuang Chen, Yuan Yuan Peng, Yu Zhong Wang, Chao Liao, Jianping Guangxi Key Laboratory of Human-Computer Interaction and Intelligent Decision-Making School of Computer and Information Engineering Nanning Normal University Guangxi Nanning530100 China Guangxi Academy of Sciences Guangxi Nanning530007 China School of Electronic and Information Engineering Tongji University Shanghai201804 China

ISBN: (纸本)9789819709021

License plate recognition is an important technology for vehicle management. However, the existing methods based on traditional image processing or deep learning have limitations in accuracy and efficiency. In this paper, we propose a novel method for license plate detection and recognition, called FasterPlateNet. FasterPlateNet consists of two stages: detection localization and character recognition. In the detection localization stage, it employs a backbone network with stacked C3_Faster modules and a one-stage object detection algorithm with a multi-scale feature fusion pyramid to extract multi-scale features of the license plate, and enhances the resolution and global feature dependency of the feature map by using the content-aware feature reassembly (CARAFE) algorithm and the exposed visual center (EVC) module. In the character recognition stage, it adopts a character recognition network with a convolutional neural network and a connectionist temporal classification loss function, which can directly output the character sequence from the license plate image without character segmentation. The experimental results on the CPPD dataset and its subsets demonstrate that our method achieves 98.8% and 98.5% accuracy in detection localization and recognition respectively. This method has great potential and value in practical applications. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

BGNN-TC: BERT GNN Based Text Classification Algorithm

BGNN-TC: BERT GNN Based Text Classification Algorithm

引用

Data Intelligence and Innovative Application (DIIA), IEEE International Conference on

作者： Jianbo Zhao Xiao Qin Lei Peng Jinyong Zhang Wenji Wang Hongchun Zheng Guangxi Key Laboratory of Human-Computer Interaction and Intelligent Decision Making Nanning Normal University Nanning China

ISBN: (数字)9798331504434

ISBN: (纸本)9798331504441

关键词： Training Text categorization Semantics Predictive models Semisupervised learning Prediction algorithms Graph neural networks Classification algorithms Data mining Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

RePCMA-YOLOv8n: A Lightweight Traffic Sign Detection Model 2nd

RePCMA-YOLOv8n: A Lightweight Traffic Sign Detection Model

引用

2nd International Conference on Applied Intelligence, ICAI 2024

作者： Huang, Lei Cai, Hongguo Peng, Yuzhong Liao, Jianping Guangxi Key Laboratory of Human-Computer Interaction and Intelligent Decision-Making School of Computer and Information Engineering Nanning Normal University Guangxi Nanning530100 China Guangxi Academy of Sciences Guangxi Nanning530007 China

ISBN: (纸本)9789819619030

This paper addresses the challenges of mobile traffic sign detection in dynamic environments by proposing a lightweight model, RePCMA-YOLOv8n, to enhance feature extraction efficiency and detection performance. The RePCMA module integrates Partial Convolution (PConv), re-parameterization strategies, and multi-scale attention mechanisms (EMA), effectively reducing redundancy in feature extraction to lower the number of parameters and floating-point operations, thereby improving overall model performance. Specifically, to tackle the common issue of varying target sizes in traffic sign detection, this study introduces the Normalized Wasserstein Distance (NWD) as an optimization loss function, significantly enhancing the model’s detection accuracy for targets of different sizes. The model demonstrates exceptional adaptability across various scenarios. Experimental results show that on the LISA dataset, the algorithm achieved an mAP50 of 97.9%, and its outstanding performance was further validated on seven other public datasets using mAP50 and mAP50-90 metrics. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Fine-Grained Image Classification Model M-ResNet50 Based On Small Collar Dataset

Fine-Grained Image Classification Model M-ResNet50 Based On ...

引用

Data Intelligence and Innovative Application (DIIA), IEEE International Conference on

作者： Xiaochen Yang Xiao Qin Baiqi Meng Xiaolian Li Shanshan Ya Guangxi Key Laboratory of Human-Computer Interaction and Intelligent Decision Nanning Normal University Nanning China

ISBN: (数字)9798331504434

ISBN: (纸本)9798331504441

关键词： Measurement Clothing Focusing Feature extraction Image classification

来源：评论

学校读者我要写书评

暂无评论

Implementation of Person Re-Identification Algorithm Based on Huawei Mindspore and Pytorch Hybrid Architecture

Implementation of Person Re-Identification Algorithm Based o...

引用

Data Intelligence and Innovative Application (DIIA), IEEE International Conference on

作者： Chao Deng Xiaochen Yang Xiao Qin Lei Peng Jinyong Zhang Wenji Wang Quanmei Qian Jianbo Zhao Guangxi Key Laboratory of Human-Computer Interaction and Intelligent Decision Nanning Normal University Nanning China

ISBN: (数字)9798331504434

ISBN: (纸本)9798331504441

关键词： Location awareness Training Analytical models Pedestrians Data models Hardware Indexes Time factors Logic Identification of persons

来源：评论

学校读者我要写书评

暂无评论

Chinese Text Classification Method Based on Double Pre-Processed Graph Aggregation Network 1

Chinese Text Classification Method Based on Double Pre-Proce...

引用

1st IEEE International Conference on Data Intelligence and Innovative Application, DIIA 2024

作者： He, Yixian Jiang, Jianhui Chen, Dingjia Tang, Molan Chen, Biquan Chen, Weiqing School of System and Computer Engineering North China Electric Power University Beijing China Guangxi Key Lab of Human-machine Interaction and Intelligent Decision Guangxi Academy Sciences Nanning China Communication Industry Service Co. Ltd. Guangxi Zhuang Autonomous Region Nanning China Vocational College Guangxi Technology and Business Nanning China

ISBN: (纸本)9798331504434

To address the problem of insufficient node feature recognition and shallow network layers in Chinese text classification, this paper proposes a Chinese text classification method called Dual Preprocessing Graph Information Aggregation Network (DPGIAN). This method solves the problem of insufficient initial feature recognition of nodes and the inability of edge weights to highlight the weight ratio between keywords through a dual preprocessing strategy of node preprocessing and edge weight preprocessing;At the same time, a deeper graph information aggregation feature extraction method was used to solve the problem of excessive feature smoothing when obtaining deep semantic features in graph structured networks, improving the accuracy of Chinese text classification. By conducting experiments on multiple Chinese text classification datasets and comparing the experimental results with multiple mainstream text classification methods on the same dataset, our method outperforms the current mainstream text classification methods on the same dataset. Multiple ablation comparison experiments were also conducted to further verify the effectiveness of our method. © 2024 IEEE.

关键词： Chinese text classification Deep Learning Graph Network Node preprocessing Pre-processing of edge rights

来源：评论

学校读者我要写书评

暂无评论

DRDM: A Disentangled Representations Diffusion Model for Synthesizing Realistic Person Images

DRDM: A Disentangled Representations Diffusion Model for Syn...

引用

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

作者： Huang, Enbo Zhang, Yuan Huang, Faliang Zhang, Guangyu Liu, Yang Guangxi Key Lab of Human-machine Interaction and Intelligent Decision Nanning Normal University Nanning China School of Computer and Information Engineering Nanning Normal University Nanning China College of Mathematics and Informatics South China Agricultural University Guangzhou China School of Computer Science and Engineering Sun Yat-sen University Guangzhou China

ISBN: (纸本)9798350368741

Person image synthesis with controllable body poses and appearances is an essential task owing to the practical needs in the context of virtual try-on, image editing and video production. However, existing methods face significant challenges with details missing, limbs distortion and the garment style deviation. To address these issues, we propose a Disentangled Representations Diffusion Model (DRDM) to generate photo-realistic images from source portraits in specific desired poses and appearances. First, a pose encoder is responsible for encoding pose features into a high-dimensional space to guide the generation of person images. Second, a body-part subspace decoupling block (BSDB) disentangles features from the different body parts of a source figure and feeds them to the various layers of the noise prediction block, thereby supplying the network with rich disentangled features for generating a realistic target image. Moreover, during inference, we develop a parsing map-based disentangled classifier-free guided sampling method, which amplifies the conditional signals of texture and pose. Extensive experimental results on the Deepfashion dataset demonstrate the effectiveness of our approach in achieving pose transfer and appearance control. The associated project can be found at https://***/lovemusiceb/DRDM. © 2025 IEEE.

关键词： Diffusion Model Disentangled Representation human Parsing Person image synthesis

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共3页 << < 1 2 3 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：