检索结果-内蒙古大学图书馆

4th International Conference on Electronic Information Engineering and Computer Science, EIECS 2024

作者： Duan, Xiaodong Yuan, Yonghui Shen, Jiaqi Chen, Bo Wang, Yuangang Dalian Minzu University Seac Key Laboratory of Big Data Applied Technology Dalian China

ISBN: (纸本)9798331531409

Virtual liver has become a emerging tendency in the fields of new-media and social network. In the process of building bright individuality image for virtual liver, how to generate more vivid speech is still a challenging problem, especially for stylization and diversity. In this paper, we take First Impression V1 dataset as training data. Meanwhile, multiple models including DeepFace, InsightFace, and FaceNet are utilized to achieve the mapping relations between liver's attributes and the speeches in videos. These attributes consist of facial appearance, emotion, body mass index, age, gender, and big-five personality traits. Afterwards, we propose a novel speech synthesis method of virtual liver by hybridizing multi-scale channel attention module and conditional p-variational autoencoder. Through application of the proposed model, we can obtain diverse synthesized speech with various settings of individual's attributes. Moreover, we also investigate in different attributes' influence on synthesized speech. © 2024 IEEE.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Skeleton-Based Action Recognition Using Graph Convolutional Network with Pose Correction and Channel Topology Refinement

引用

Computers, Materials & Continua 2025年第4期83卷 701-718页

作者： Yuxin Gao Xiaodong Duan Qiguo Dai School of Engineering Guangzhou College of Technology and BusinessFoshan528138China School of Computer Science and Engineering Dalian Minzu UniversityDalian116000China SEAC key Laboratory of Big Data Applied Technology Dalian Minzu UniversityDalian116000China

Graph convolutional network(GCN)as an essential tool in human action recognition tasks have achieved excellent performance in previous ***,most current skeleton-based action recognition using GCN methods use a shared topology,which cannot flexibly adapt to the diverse correlations between joints under different motion *** video-shooting angle or the occlusion of the body parts may bring about errors when extracting the human pose coordinates with estimation *** this work,we propose a novel graph convolutional learning framework,called PCCTR-GCN,which integrates pose correction and channel topology refinement for skeleton-based human action ***,a pose correction module(PCM)is introduced,which corrects the pose coordinates of the input network to reduce the error in pose feature ***,channel topology refinement graph convolution(CTR-GC)is employed,which can dynamically learn the topology features and aggregate joint features in different channel dimensions so as to enhance the performance of graph convolution networks in feature ***,considering that the joint stream and bone stream of skeleton data and their dynamic information are also important for distinguishing different actions,we employ a multi-stream data fusion approach to improve the network’s recognition *** evaluate the model using top-1 and top-5 classification *** the benchmark datasets iMiGUE and Kinetics,the top-1 classification accuracy reaches 55.08%and 36.5%,respectively,while the top-5 classification accuracy reaches 89.98%and 59.2%,*** the NTU dataset,for the two benchmark RGB+Dsettings(X-Sub and X-View),the classification accuracy achieves 89.7%and 95.4%,respectively.

关键词： Pose correction multi-stream fusion GCN action recognition

来源：评论

学校读者我要写书评

暂无评论

Research on cross-modal hashing method based on diffusion mode 8

Research on cross-modal hashing method based on diffusion mo...

引用

8th International Conference on Electronic technology and Information Science, ICETIS 2023

作者： Li, Wenjiao Zhong, Zirui SEAC key Laboratory of Big Data Applied Technology Dalian Minzu University Dalian116000 China

ISBN: (纸本)9781510666535

For achieving fast and flexible retrieval across heterogeneous modalities, unsupervised is more flexible and easy to use than supervised methods, of which the unsupervised method GAN is the most popular. However, GAN has been suffering from the problems of lack of diversity in generated samples, debugging difficulties and training instability. A cross-modal hashing method based on a diffusion model is proposed in the paper. Specifically: (1) For the first time, the diffusion model is applied to the field of cross-modal retrieval, targeting three modalities for mutual retrieval. (2) The combination of adversarial network GAN and diffusion model improves the sample quality and sample diversity, and ameliorates the problems of complex GAN debugging and unstable training. The effectiveness of the proposed method is demonstrated through experiments on three datasets and comparison with state-of-the-art methods. © 2023 SPIE.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

EMPA-YOLO:A Lightweight Real-time Weed Detection Method Suitable for Natural

EMPA-YOLO:A Lightweight Real-time Weed Detection Method Suit...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Wang, Yuzhe Chen, Jiahao Duan, Xiaodong Li, Zhuohui College of Mechanical and Electronic Engineering Dalian China College of Computer Science and Engineering Dalian China Seac Key Laboratory of Big Data Applied Technology Dalian China

ISBN: (纸本)9781665410205

Weed detection is crucial for the healthy growth of crops, yet existing detection models struggle to perform high-accuracy real-time detection of weeds in natural environments on edge computing devices. This paper introduces EMPA-YOLO, a model designed for rapid, accurate, real-time weed detection on low-performance edge computing devices. It incorporates an efficient multi-scale convolutional structure, C3EMSC, and a lightweight, adaptive weight subsampling layer, LAWDS, into YOLOv5s. Additionally, a logical distillation algorithm, AlignSoftTarget, is proposed for knowledge distillation. Validation on a mixed dataset of crops and weeds showed that EMPA-YOLO improved mAP50 by 11.2%, reduced parameter count by 4.8M, decreased computational load by 8.7GFLOPs, and increased inference frame rate by 58% compared to the original YOLOv5s algorithm. When compared to YOLOv3, YOLOv5s, YOLOv6, YOLOv8s, and RT-DETR, inference speed improved by 89.2%, 60.8%, 77.5%, 76.5%, and 94.7%, respectively, with mean accuracy enhancements of 7.3%, 11.2%, 16.7%, 0.9%, and 1.2%. Real-world testing on edge computing devices met real-time detection requirements, proving its efficacy and practicality in weed detection. © 2024 IEEE.

关键词： edge computing knowledge distillation lightweight model model compress ion YOLO

来源：评论

学校读者我要写书评

暂无评论

Multimodal Apparent Personality Traits Analysis of Short Video using Swin Transformer and Bi-directional Long Short-Term Memory Network 4

Multimodal Apparent Personality Traits Analysis of Short Vid...

引用

4th International Conference on Frontiers technology of Information and Computer, ICFTIC 2022

作者： Duan, Xiaodong Zhan, Qingguo Zhan, Shaohui Yu, Yingying Chang, Luning Wang, Yuangang Minzu University Seac Key Laboratory of Big Data Applied Technology Dalian Key Lab of Digital Technology for National Culture Dalian Dalian China

ISBN: (纸本)9798350321951

Due to potential applications in online education, human resources and personalized recommendation, apparent personality analysis has become a meaningful task in the field of computer vision and multimedia. According to characteristics of short video in time length, idea density and individual expression, we take full advantage of clues in visual and audio aspects to propose a novel framework of apparent personality analysis. From the viewpoint of visual modality, Swin- Transformer and Bi-directional Long Short-Term Memory (BiLSTM) network are introduced to discovery feature representation for personality assessment. Meanwhile, usual features including chromaticity characteristics, root mean square energy, spectrum, zero crossing rate, and MFCC are extracted to describe personality from the perspective of audio modality. Finally, feature leaned from visual and audio modalities are fused to make personality analysis that can be viewed as solving regression problem. For the purpose of evaluating the proposed algorithm's performance, we conduct comparative analysis between our approach and other methods on First Impression V1 and Short Video Vlogger Personality datasets. The experimental results show that our method is competitive in prediction accuracy. © 2022 IEEE.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

Multimodal Apparent Personality Analysis based on ConvNeXt-GRU and Random Forest

Multimodal Apparent Personality Analysis based on ConvNeXt-G...

引用

Machine Learning and Intelligent Systems Engineering (MLISE), International Conference on

作者： Xiaodong Duan Jiaqi Shen Yonghui Yuan Feng Yang Yuangang Wang SEAC Key Laboratory of Big Data Applied Technology Dalian Minzu University Dalian China

ISBN: (数字)9798350375077

ISBN: (纸本)9798350375084

With the integrative development of computer science and psychology, apparent personality analysis has gradually become a new research hotspot. In this study, we aim to extract key information from large-scale video data and build an end-to-end deep learning model to explore the latent personality traits of vloggers in short videos. To fully utilize the spatiotemporal information existing in audio and visual modalities of short videos, we propose a multimodal apparent personality analysis method that integrates neural network and random forest. In visual modality analysis, we improve the ConvNeXt network by introducing the ECA attention mechanism and propose a new network structure unit named ECblock in order to obtain features closely relating to personality traits. Considering the temporal characteristics of short video, we combine the improved ConvNeXt with gated recurrent units for making personality traits assessment. For the audio modality, we manually extract voice features using librosa tool and employ random forest model for feature prediction under the help of grid search. Finally, according to decision fusion strategy, the latent information learned from visual and audio modalities are fused to implement apparent personality analysis. The results of comparative experiment on ChaLearn First Impressions V2 dataset show that our proposed method achieves competitive performance in terms of prediction accuracy.

关键词： Visualization Analytical models Psychology Predictive models Feature extraction Brain modeling Robustness

来源：评论

学校读者我要写书评

暂无评论

A Component-Aware Chinese Font Generation Method Based on Multi-Scale Features 5

A Component-Aware Chinese Font Generation Method Based on Mu...

引用

5th International Conference on Artificial Intelligence and Computer Engineering, ICAICE 2024

作者： Guo, Xiaoqi Wang, Cunrui Zhan, Guodong Zhou, Juxiang Dalian Minzu University Seac Key Laboratory of Big Data Applied Technology Dalian China Dalian Minzu University Dalian Chinese Font Design Technology Innovation Center Dalian China Yunnan Normal University Foundation of Key Laboratory of Education Informatization for Nationalities Kunming China

ISBN: (纸本)9798331528911

AI-assisted generation technology for Chinese characters can significantly improve the efficiency of font library development for designers. However, existing algorithms still encounter errors in glyph strokes and structures, even when incorporating stroke semantics or font component information. This paper deepens the utilization of structural and positional features of Chinese character components by capturing the characteristics of these components at different scales, constraining their positional relationships, and enhancing the stability and consistency of glyph structures. By leveraging the cross-scale features associated with Chinese character components, the coherence of glyphs across various spatial and hierarchical levels is reinforced, improving the expression of local features. This study conducts ablation experiments on a dataset comprising 20 Chinese character libraries and compares the results with CycleGAN, Zi2zi, MX-Font, and DG-Font. The findings indicate that the proposed method enhances both the local details and overall structure of generated glyphs, with specific evaluation metrics showing significant improvement. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Chinese Font Generation Algorithm with Redundant Feature Suppression 5

Chinese Font Generation Algorithm with Redundant Feature Sup...

引用

5th International Conference on Machine Learning and Computer Application, ICMLCA 2024

作者： Guo, Xiaoqi Wang, Cunrui Zhan, Guodong Zhou, Juxiang SEAC Key Laboratory of Big Data Applied Technology Dalian Minzu University Dalian China Dalian Chinese Font Design Technology Innovation Center Dalian Minzu University Dalian China Foundation of Key Laboratory of Education Informatization for Nationalities Yunnan Normal University Kunming China

ISBN: (纸本)9798331530334

Automated generation of Chinese character fonts can significantly enhance font library design efficiency and improve industrial productivity. Current algorithms for generating Chinese fonts often transmit redundant features from reference graphics into the model structure, alongside spatial and channel dimensions, resulting in pronounced redundancy in the generated outputs. This paper proposes a method that suppresses redundant features from both spatial and channel dimensions, reconstructs spatial features, and employs residual quantization to extract detailed font style characteristics. By mitigating redundant features, the overall stylistic expression of Chinese characters is reinforced, leading to the generation of high-quality font libraries. Experiments conducted on a dataset comprising 30 Chinese font libraries demonstrate the effectiveness of this method, with improvements observed in font feature expression metrics compared to CycleGAN, Zi i2zi, MX-Font, and DG-Font. © 2024 IEEE.

关键词： component font generation redundancy feature residual quantization

来源：评论

学校读者我要写书评

暂无评论

Speech Synthesis Method of Virtual Liver Based on Tacotron and Conditional ß- Variational Autoencoder

Speech Synthesis Method of Virtual Liver Based on Tacotron a...

引用

Electronic Information Engineering and Computer Science (EIECS), 2021 International Conference on

作者： Xiaodong Duan Yonghui Yuan Jiaqi Shen Bo Chen Yuangang Wang SEAC Key Laboratory of Big Data Applied Technology Dalian Minzu University Dalian China

ISBN: (数字)9798331531409

ISBN: (纸本)9798331531416

关键词： Social networking (online) Autoencoders Buildings Semantics Liver Training data data models Speech synthesis data mining Videos

来源：评论

学校读者我要写书评

暂无评论

A Survey of LLM datasets:From Autoregressive Model to AI Chatbot

引用

Journal of Computer Science & technology 2024年第3期39卷 542-566页

作者：杜非马新建杨婧如柳熠罗超然王学斌姜海鸥景翔 National Key Laboratory of Data Space Technology and System Beijing 100195China Advanced Institute of Big Data Beijing 100195China Fu Foundation School of Engineering and Applied Science Columbia UniversityNY 10027U.S.A. School of Software and Microelectronics Peking UniversityBeijing 100091China CCF IEEE

Since OpenAI opened access to ChatGPT,large language models(LLMs)become an increasingly popular topic attracting researchers’attention from abundant ***,public researchers meet some problems when developing LLMs given that most of the LLMs are produced by industries and the training details are typically *** datasets are an important setup of LLMs,this paper does a holistic survey on the training datasets used in both the pre-train and fine-tune *** paper first summarizes 16 pre-train datasets and 16 fine-tune datasets used in the state-of-the-art ***,based on the properties of the pre-train and fine-tune processes,it comments on pre-train datasets from quality,quantity,and relation with models,and comments on fine-tune datasets from quality,quantity,and *** study then critically figures out the problems and research trends that exist in current LLM *** study helps public researchers train and investigate LLMs by visual cases and provides useful comments to the research community regarding data *** the best of our knowledge,this paper is the first to summarize and discuss datasets used in both autoregressive and chat *** survey offers insights and suggestions to researchers and LLM developers as they build their models,and contributes to the LLM study by pointing out the existing problems of LLM studies from the perspective of data.

关键词： large language model(LLM) autoregressive model AI chatbot natural language processing(NLP)corpora OpenAI

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：