2nd International Conference on Digital Society and Intelligent Systems (DSInS 2022)最新文献_第9页

FaST-Net: Face Style Self-Transfer Network for masked face inpainting FaST-Net:面部风格自传递网络蒙面彩绘

2nd International Conference on Digital Society and Intelligent Systems (DSInS 2022) Pub Date : 2023-04-03 DOI: 10.1117/12.2673410

Yiming Li, Jianpeng Chen, Yazhou Ren, X. Pu

{"title":"FaST-Net: Face Style Self-Transfer Network for masked face inpainting","authors":"Yiming Li, Jianpeng Chen, Yazhou Ren, X. Pu","doi":"10.1117/12.2673410","DOIUrl":"https://doi.org/10.1117/12.2673410","url":null,"abstract":"During the COVID-19 coronavirus epidemic, people usually wear masks to prevent the spread of the virus, which has become a major obstacle when we use face-based computer vision techniques such as face recognition and face detection. So masked face inpainting technique is desired. Actually, the distribution of face features is strongly correlated with each other, but existing inpainting methods typically ignore the relationship between face feature distributions. To address this issue, in this paper, we first show that the face image inpainting task can be seen as a distribution alignment between face features in damaged and valid regions, and style transfer is a distribution alignment process. Based on this theory, we propose a novel face inpainting model considering the probability distribution between face features, namely Face Style Self-Transfer Network (FaST-Net). Through the proposed style self-transfer mechanism, FaST-Net can align the style distribution of features in the inpainting region with the style distribution of features in the valid region of a face. Ablation studies have validated the effectiveness of FaST-Net, and experimental results on two popular human face datasets (CelebA and VGGFace) exhibit its superior performance compared with existing state-of-the-art methods.","PeriodicalId":176918,"journal":{"name":"2nd International Conference on Digital Society and Intelligent Systems (DSInS 2022)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134133880","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Video recording an automatic editing method based on artificial intelligence algorithm 一种基于人工智能算法的视频录制自动编辑方法

2nd International Conference on Digital Society and Intelligent Systems (DSInS 2022) Pub Date : 2023-04-03 DOI: 10.1117/12.2673367

Lei An

{"title":"Video recording an automatic editing method based on artificial intelligence algorithm","authors":"Lei An","doi":"10.1117/12.2673367","DOIUrl":"https://doi.org/10.1117/12.2673367","url":null,"abstract":"With the rise of short video platforms, video recording and automatic editing technology has become increasingly important to the development of short video, artificial intelligence algorithms can use massive video data to understand the content of time-series video, providing a technical basis for video recording and editing, specifically, video recording and automatic editing methods based on artificial intelligence algorithms already have the corresponding data base, technical basis and application basis In particular, AI algorithm-based video recording and automatic editing methods have the corresponding data, technical and application bases. Therefore, this paper discusses the method of video recording and automatic editing based on artificial intelligence algorithms. This paper firstly describes the automatic video editing process and the extraction of temporal action features, then designs the automatic editing system and the video recording and coding system, and finally analyses the detection speed of the system. The research results demonstrate that the AI algorithm-based automatic editing system passed the concurrency test with good performance and the AI retrieval scheme has a fast detection speed to meet the user's editing needs.","PeriodicalId":176918,"journal":{"name":"2nd International Conference on Digital Society and Intelligent Systems (DSInS 2022)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132102582","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A study of machine learning based credit card potential default customer identification 基于机器学习的信用卡潜在违约客户识别研究

2nd International Conference on Digital Society and Intelligent Systems (DSInS 2022) Pub Date : 2023-04-03 DOI: 10.1117/12.2673542

Sijie Xu, Peixin. Lin, Wanqi Luo, Wenjun Yang, Yuntao Jia

引用次数: 0

Remote sensing image registration of disaster-affected areas based on deep learning feature matching 基于深度学习特征匹配的灾区遥感图像配准

2nd International Conference on Digital Society and Intelligent Systems (DSInS 2022) Pub Date : 2023-04-03 DOI: 10.1117/12.2673374

Qiang Chen, Fei Song, Xianyuan Liu, Sanxing Zhang, Tao Lei, Ping Jiang

{"title":"Remote sensing image registration of disaster-affected areas based on deep learning feature matching","authors":"Qiang Chen, Fei Song, Xianyuan Liu, Sanxing Zhang, Tao Lei, Ping Jiang","doi":"10.1117/12.2673374","DOIUrl":"https://doi.org/10.1117/12.2673374","url":null,"abstract":"With the rapid development of remote sensing technology, remote sensing registration plays an important role in the assessment of various natural disasters, especially earthquakes. However, multi-temporal remote sensing images for the assessment have some characteristics, e.g. large-scale and rotation, resulting in challenges of remote sensing registration. In order to better register remote sensing images, we propose a new image registration method with a deep learning feature matching strategy. We first extract the pre-match point sets M and S by using SIFT-FLANN (SIFT-Fast Library for Approximate Nearest Neighbors). Second, we filter out the correct matching point pairs from M and S by using a multiscale neighborhood information network and a dual-path ConvNeXt network with self-attention-guided local information enhancement. Thirdly, we register multi-temporal remote sensing images by solve the model parameters of the spatial transformation. Finally, we evaluate our proposed method using a variety of remote sensing images with different phases, including visible light images with different illumination, scale and geometry changes. On the remote sensing image dataset containing images of pre- and post-earthquake, we compare our method to existing state-of-the-art methods and provide the results with the evaluation indexes such as Root Mean Square Error (RMSE). The results show that our method for multi-temporal remote sensing registration has a higher registration accuracy and more robustness.","PeriodicalId":176918,"journal":{"name":"2nd International Conference on Digital Society and Intelligent Systems (DSInS 2022)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131681767","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

CChain: a high throughput blockchain system CChain:一个高吞吐量区块链系统

2nd International Conference on Digital Society and Intelligent Systems (DSInS 2022) Pub Date : 2023-04-03 DOI: 10.1117/12.2673351

Yan Zhang, Jia Wang, Yingjie Han

引用次数: 0

Analysis of warship equipment prognostics and health management model under the background of civil-military integration 军民融合背景下舰船装备预测与健康管理模式分析

2nd International Conference on Digital Society and Intelligent Systems (DSInS 2022) Pub Date : 2023-04-03 DOI: 10.1117/12.2674179

Yan Tang, S. Shen, Jing Li

引用次数: 0

Research on characteristics of emergency logistics system based on interdependent network 基于相互依赖网络的应急物流系统特性研究

2nd International Conference on Digital Society and Intelligent Systems (DSInS 2022) Pub Date : 2023-04-03 DOI: 10.1117/12.2673619

N. Zhang, Boyu Feng, Yuhui Wang

引用次数: 0

Research on the construction of college Chinese teaching system based on deep learning technology 基于深度学习技术的大学语文教学系统构建研究

2nd International Conference on Digital Society and Intelligent Systems (DSInS 2022) Pub Date : 2023-04-03 DOI: 10.1117/12.2673596

Xiaocong Sui, Xiaohui Sui, Xiangping Shen

{"title":"Research on the construction of college Chinese teaching system based on deep learning technology","authors":"Xiaocong Sui, Xiaohui Sui, Xiangping Shen","doi":"10.1117/12.2673596","DOIUrl":"https://doi.org/10.1117/12.2673596","url":null,"abstract":"With the deepening of the concept of knowledge society, the traditional college Chinese education is undergoing profound changes, which has gradually changed to \"learning centered\". Therefore, deep learning, core literacy and other teaching concepts have become the focus of current higher education, which has gradually been integrated with new teaching methods, such as flipped classroom and Mu class. Through multi form teaching methods, the teaching mode of information technology and curriculum integration has become the pursuit of in-depth learning in Chinese teaching, which is a learning mode of pursuing more diversified learning objectives of students. Through in-depth learning, the learning process of college Chinese will be more engaged and participatory, which will help students' cognitive processing methods, mainly including the connection of new and old knowledge, critical understanding, information integration, etc. Deep learning will increase the level of students' input and participation in the learning process, which will better develop the core quality of long-term memory and transfer of knowledge. Therefore, the construction of college Chinese teaching system based on deep learning technology is very necessary. This paper first analyzes the current research on the application of deep learning technology. Then, this paper analyzes the data analysis model of deep learning process. Finally, this paper constructs the college Chinese teaching system and puts forward some suggestions, which can better construct the teaching system.","PeriodicalId":176918,"journal":{"name":"2nd International Conference on Digital Society and Intelligent Systems (DSInS 2022)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125991767","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Research on technology of electric energy centralized collection and metering system based on smart grid 基于智能电网的电能集中集计量系统技术研究

2nd International Conference on Digital Society and Intelligent Systems (DSInS 2022) Pub Date : 2023-04-03 DOI: 10.1117/12.2673550

Wenxing Lu, Cheng Liang, Junhua Liang, Cong Huang, Wu Xia, Diqiu Shen

引用次数: 0

A big data based conflict analysis, control and resolution effect evaluation platform 基于大数据的冲突分析、控制与解决效果评估平台

2nd International Conference on Digital Society and Intelligent Systems (DSInS 2022) Pub Date : 2023-04-03 DOI: 10.1117/12.2673561

Yuna Ma, Meng Peng, Yan Luo, Xiao-si Wang, Li-yong Zhang, Zuocheng Wang, Junhan Qiu

{"title":"A big data based conflict analysis, control and resolution effect evaluation platform","authors":"Yuna Ma, Meng Peng, Yan Luo, Xiao-si Wang, Li-yong Zhang, Zuocheng Wang, Junhan Qiu","doi":"10.1117/12.2673561","DOIUrl":"https://doi.org/10.1117/12.2673561","url":null,"abstract":"Focusing on the strategic goal of \"Safe China\", we will build a technical system for modernizing the theory and governance capacity of a smart society, and solve the problems of lagging theoretical innovation in resolving multiple conflicts and disputes, insufficient systematization of intelligent auxiliary technology for risk control and management, and poor coordination and linkage of governance. Enhance the ability to prevent and resolve major systemic risks, enhance scientific supervision and service capabilities, and provide scientific and technological support to promote the modernization of social governance system and governance capacity and build a smart society. Need to build a platform for analysis and control of conflicts and disputes and evaluation of their resolution effects. The platform aims to address the main problems in the resolution of multiple conflicts, build assessment indexes for the impact of conflicts and disputes, design intervention norms, multiple resolution mechanisms and policy tools synergistic model, build a large- scale dynamic knowledge map in the field of conflicts and disputes integrating the characteristics of the times, build an intelligent platform for the whole process of conflicts and disputes disposal, build a platform for psychological risk assessment and early warning, psychological assistance and automated psychological intervention, build The platform for analysis and control of contradictions and disputes and evaluation of the effectiveness of their resolution will be demonstrated and applied.","PeriodicalId":176918,"journal":{"name":"2nd International Conference on Digital Society and Intelligent Systems (DSInS 2022)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131142987","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0