首页 > 最新文献

2021 International Conference on Culture-oriented Science & Technology (ICCST)最新文献

英文 中文
An Improved Efficient Convolutional Neural Network for Weed Seedlings Detection 一种改进的高效卷积神经网络用于杂草幼苗检测
Pub Date : 2021-11-01 DOI: 10.1109/ICCST53801.2021.00067
Mengqiu Dou, Zhiguo Hong, Minyong Shi
The growth of weeds in the fields is one of the important factors affecting crop yields. Timely detection and controlling of weeds have a great positive effect on the healthy growth of crop seedlings. Identifying the types of weeds correctly can effectively improve the efficiency of weed removal. Convolutional neural network is a good method for the detection of weed seedlings. With a suitable convolutional neural network model, the types of seedlings can be classified through pictures, which improves the efficiency of agricultural work greatly. This paper constructs a convolutional neural network model based on MobileNet and TensorFlow. The model is trained by inputting pictures of crops and weeds seedlings in 12 different types. The training model is evaluated with performance of 96.88% in identifying seedling types. Due to the features of high efficiency and lightweight of MobileNet, this model can be better applied to mobile devices than others, which is convenient for agricultural workers to use.
田间杂草的生长是影响作物产量的重要因素之一。及时发现和防治杂草对作物幼苗的健康生长有很大的积极作用。正确识别杂草种类,可以有效提高除草效率。卷积神经网络是一种很好的杂草幼苗检测方法。利用合适的卷积神经网络模型,可以通过图片对苗种进行分类,大大提高了农业工作的效率。本文构建了基于MobileNet和TensorFlow的卷积神经网络模型。该模型通过输入12种不同类型的作物和杂草幼苗的图片来训练。训练模型对幼苗类型的识别率为96.88%。由于MobileNet的高效率和轻量化的特点,这种模式比其他模式更适合于移动设备,方便农业工人使用。
{"title":"An Improved Efficient Convolutional Neural Network for Weed Seedlings Detection","authors":"Mengqiu Dou, Zhiguo Hong, Minyong Shi","doi":"10.1109/ICCST53801.2021.00067","DOIUrl":"https://doi.org/10.1109/ICCST53801.2021.00067","url":null,"abstract":"The growth of weeds in the fields is one of the important factors affecting crop yields. Timely detection and controlling of weeds have a great positive effect on the healthy growth of crop seedlings. Identifying the types of weeds correctly can effectively improve the efficiency of weed removal. Convolutional neural network is a good method for the detection of weed seedlings. With a suitable convolutional neural network model, the types of seedlings can be classified through pictures, which improves the efficiency of agricultural work greatly. This paper constructs a convolutional neural network model based on MobileNet and TensorFlow. The model is trained by inputting pictures of crops and weeds seedlings in 12 different types. The training model is evaluated with performance of 96.88% in identifying seedling types. Due to the features of high efficiency and lightweight of MobileNet, this model can be better applied to mobile devices than others, which is convenient for agricultural workers to use.","PeriodicalId":222463,"journal":{"name":"2021 International Conference on Culture-oriented Science & Technology (ICCST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126200430","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: 2
Research on the Evaluation of Program Influence Based on PageRank Algorithm 基于PageRank算法的节目影响力评价研究
Pub Date : 2021-11-01 DOI: 10.1109/ICCST53801.2021.00113
Feng Qing, Yan Wang, Yantong Zhang
The paper introduces the complex network theory into the program influence evaluation system. We collect relevant data of the variety shows on Tencent Video Platform from 2016-2021 and establish the program comprehensive influence algorithm program. The comprehensive influence consists of two direct and indirect parts, the direct influence is calculated from the total view counts, the comments in the latest issue, and the fans of the official program account. The indirect influence is calculated by PageRank, LeaderRank and TimedPageRank through the program page. The results obtained by the algorithm shows that the output of highly influential variety shows has increased in recent years. Even though COVID-19 in 2020 reduced the total production of variety shows, it still produces a relatively high proportion of influential programs. High influence programs are mainly “Develop” and “Game” programs, “Cultural” programs rank low. Inspire our need to strengthen the content production and value concept guidance of the variety show market, and deepen the content innovation and reform of the “Cultural” programs themselves.
将复杂网络理论引入到节目影响评价体系中。我们收集2016-2021年腾讯视频平台综艺节目相关数据,建立节目综合影响力算法方案。综合影响力由直接和间接两部分组成,直接影响力由总观看数、最新一期评论数、公众号粉丝数计算。间接影响由PageRank, LeaderRank和timmedpagerank通过程序页面计算。算法结果表明,近年来影响力较大的综艺节目产量有所增加。尽管2020年的新冠疫情导致综艺节目总量减少,但有影响力的节目仍占比较高的比例。影响力较大的节目主要是“发展”和“游戏”类节目,“文化”类节目排名较低。启示我们需要加强综艺节目市场的内容生产和价值观念引导,深化“文化”类节目本身的内容创新和改革。
{"title":"Research on the Evaluation of Program Influence Based on PageRank Algorithm","authors":"Feng Qing, Yan Wang, Yantong Zhang","doi":"10.1109/ICCST53801.2021.00113","DOIUrl":"https://doi.org/10.1109/ICCST53801.2021.00113","url":null,"abstract":"The paper introduces the complex network theory into the program influence evaluation system. We collect relevant data of the variety shows on Tencent Video Platform from 2016-2021 and establish the program comprehensive influence algorithm program. The comprehensive influence consists of two direct and indirect parts, the direct influence is calculated from the total view counts, the comments in the latest issue, and the fans of the official program account. The indirect influence is calculated by PageRank, LeaderRank and TimedPageRank through the program page. The results obtained by the algorithm shows that the output of highly influential variety shows has increased in recent years. Even though COVID-19 in 2020 reduced the total production of variety shows, it still produces a relatively high proportion of influential programs. High influence programs are mainly “Develop” and “Game” programs, “Cultural” programs rank low. Inspire our need to strengthen the content production and value concept guidance of the variety show market, and deepen the content innovation and reform of the “Cultural” programs themselves.","PeriodicalId":222463,"journal":{"name":"2021 International Conference on Culture-oriented Science & Technology (ICCST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115929659","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
Non-parallel and Many-to-One Musical Timbre Morphing using DDSP-Autoencoder and Spectral Feature Interpolation 使用ddsp -自动编码器和频谱特征插值的非并行和多对一音乐音色变形
Pub Date : 2021-11-01 DOI: 10.1109/ICCST53801.2021.00040
Yi Zou, Jingyu Liu, Wei Jiang
Abstract - Timbre morphing is a signal processing technology that involves the use of an interpolation algorithm to gradually change the timbre of one instrument into that of another. However, the prepared target audio, which possesses the same music content (such as score and rhythm) as the original audio, is essential to the input used in the morphing technique. To meet the application requirements of non-parallel and many-to-one processing, we combined the signal processing technology of spectral feature interpolation with the deep learning technology of the autoencoder to provide the timbre morphing technology with a generalization ability. The complex framework, which focuses on the processing of harmonic information, is built using the pitch tracking, temporal signal processing, decoder, source-filter modeling, and spectral feature interpolation. Notably, unlike the neural vocoder that is commonly used in voice conversion, the decoder, which is trained using a data reconstruction method, is used to map the input audio features to the harmonic amplitude distribution with the target timbre. Experiments were conducted in which the clarinet timbre was morphed into a trumpet. An evaluation of the spectral features demonstrated the validity of the morphing technology.
音色变形是一种信号处理技术,它涉及到使用插值算法将一种乐器的音色逐渐改变为另一种乐器的音色。然而,准备好的目标音频具有与原始音频相同的音乐内容(如乐谱和节奏),对于变形技术中使用的输入是必不可少的。为了满足非并行和多对一处理的应用需求,我们将频谱特征插值的信号处理技术与自编码器的深度学习技术相结合,使音色变形技术具有泛化能力。利用基音跟踪、时间信号处理、解码器、源-滤波器建模和频谱特征插值等技术,构建了以谐波信息处理为重点的复杂框架。值得注意的是,与语音转换中常用的神经声码器不同,使用数据重建方法训练的解码器用于将输入音频特征映射到目标音色的谐波幅度分布。实验中,单簧管的音色变成了小号的音色。对光谱特征的评价证明了该变形技术的有效性。
{"title":"Non-parallel and Many-to-One Musical Timbre Morphing using DDSP-Autoencoder and Spectral Feature Interpolation","authors":"Yi Zou, Jingyu Liu, Wei Jiang","doi":"10.1109/ICCST53801.2021.00040","DOIUrl":"https://doi.org/10.1109/ICCST53801.2021.00040","url":null,"abstract":"Abstract - Timbre morphing is a signal processing technology that involves the use of an interpolation algorithm to gradually change the timbre of one instrument into that of another. However, the prepared target audio, which possesses the same music content (such as score and rhythm) as the original audio, is essential to the input used in the morphing technique. To meet the application requirements of non-parallel and many-to-one processing, we combined the signal processing technology of spectral feature interpolation with the deep learning technology of the autoencoder to provide the timbre morphing technology with a generalization ability. The complex framework, which focuses on the processing of harmonic information, is built using the pitch tracking, temporal signal processing, decoder, source-filter modeling, and spectral feature interpolation. Notably, unlike the neural vocoder that is commonly used in voice conversion, the decoder, which is trained using a data reconstruction method, is used to map the input audio features to the harmonic amplitude distribution with the target timbre. Experiments were conducted in which the clarinet timbre was morphed into a trumpet. An evaluation of the spectral features demonstrated the validity of the morphing technology.","PeriodicalId":222463,"journal":{"name":"2021 International Conference on Culture-oriented Science & Technology (ICCST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134025183","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
Intelligent Yoga Coaching System Based on Posture Recognition 基于姿态识别的智能瑜伽教练系统
Pub Date : 2021-11-01 DOI: 10.1109/ICCST53801.2021.00068
Xiangjie Huang, Da Pan, Yiming Huang, Junli Deng, Pengyu Zhu, Ping Shi, Ruisi Xu, Zelu Qi, Jingqian He
Nowadays, yoga as a popular sport has received more and more people’s attention. However, many people do not have enough time and suitable places to practice yoga. In recent years, the development of posture estimation methods has provided convenience for intelligent yoga coaches. This research aims to develop a yoga training system based on real-time pose estimation. The system is composed of a posture recognition network, a yoga standard movement posture library, a yoga movement correction algorithm and a system UI interface. Taking the real-time human motion video stream collected by the camera as input, the gesture recognition network based on OpenPose is used to extract the joint points of human gestures. According to our proposed correction algorithm based on entropy weight, real-time feedback and correction suggestions can be obtained. Experimental results show that this method can show high real-time performance on home computers and high accuracy on real data sets.
如今,瑜伽作为一项流行的运动已经受到越来越多的人的关注。然而,很多人没有足够的时间和合适的场所练习瑜伽。近年来,姿态估计方法的发展为智能瑜伽教练提供了方便。本研究旨在开发一个基于实时姿态估计的瑜伽训练系统。该系统由姿势识别网络、瑜伽标准动作姿势库、瑜伽动作校正算法和系统UI界面组成。以摄像机采集的实时人体运动视频流为输入,利用基于OpenPose的手势识别网络提取人体手势的结合点。根据我们提出的基于熵权的校正算法,可以得到实时反馈和校正建议。实验结果表明,该方法在家用计算机上具有较高的实时性,在实际数据集上具有较高的精度。
{"title":"Intelligent Yoga Coaching System Based on Posture Recognition","authors":"Xiangjie Huang, Da Pan, Yiming Huang, Junli Deng, Pengyu Zhu, Ping Shi, Ruisi Xu, Zelu Qi, Jingqian He","doi":"10.1109/ICCST53801.2021.00068","DOIUrl":"https://doi.org/10.1109/ICCST53801.2021.00068","url":null,"abstract":"Nowadays, yoga as a popular sport has received more and more people’s attention. However, many people do not have enough time and suitable places to practice yoga. In recent years, the development of posture estimation methods has provided convenience for intelligent yoga coaches. This research aims to develop a yoga training system based on real-time pose estimation. The system is composed of a posture recognition network, a yoga standard movement posture library, a yoga movement correction algorithm and a system UI interface. Taking the real-time human motion video stream collected by the camera as input, the gesture recognition network based on OpenPose is used to extract the joint points of human gestures. According to our proposed correction algorithm based on entropy weight, real-time feedback and correction suggestions can be obtained. Experimental results show that this method can show high real-time performance on home computers and high accuracy on real data sets.","PeriodicalId":222463,"journal":{"name":"2021 International Conference on Culture-oriented Science & Technology (ICCST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132023664","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: 3
A Comparative Analysis of Lighting Design Software 灯光设计软件的比较分析
Pub Date : 2021-11-01 DOI: 10.1109/ICCST53801.2021.00127
Mingyang Su, Jingbing Wu, Hanxi Wang
With the rapid economic development and technical progress, the traditional means of lighting design can no longer meet the needs of people, leading to the emergence of new lighting design methods and lighting design software. With humanistic thought as the design concept in the art of lighting, lighting design is gradually becoming professional and standardized. Domestic and foreign software related to lighting design are developing at a fast pace in this industry, and each software has its own unique advantages and disadvantages. In this paper, a comparative analysis is made on DIALux, AGI32, Ecotect and Lightscape, the four commonly used domestic lighting design software.
随着经济的快速发展和技术的进步,传统的照明设计手段已经不能满足人们的需求,导致了新的照明设计方法和照明设计软件的出现。照明艺术以人文思想为设计理念,照明设计逐渐走向专业化、规范化。国内外与照明设计相关的软件在这个行业发展速度很快,每种软件都有其独特的优点和缺点。本文对国内常用的四种照明设计软件DIALux、AGI32、Ecotect和Lightscape进行了对比分析。
{"title":"A Comparative Analysis of Lighting Design Software","authors":"Mingyang Su, Jingbing Wu, Hanxi Wang","doi":"10.1109/ICCST53801.2021.00127","DOIUrl":"https://doi.org/10.1109/ICCST53801.2021.00127","url":null,"abstract":"With the rapid economic development and technical progress, the traditional means of lighting design can no longer meet the needs of people, leading to the emergence of new lighting design methods and lighting design software. With humanistic thought as the design concept in the art of lighting, lighting design is gradually becoming professional and standardized. Domestic and foreign software related to lighting design are developing at a fast pace in this industry, and each software has its own unique advantages and disadvantages. In this paper, a comparative analysis is made on DIALux, AGI32, Ecotect and Lightscape, the four commonly used domestic lighting design software.","PeriodicalId":222463,"journal":{"name":"2021 International Conference on Culture-oriented Science & Technology (ICCST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133886388","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: 1
Customer Value Co-creation and Perception in Museum Cultural and Creative Product Design 博物馆文创产品设计中的顾客价值共创与感知
Pub Date : 2021-11-01 DOI: 10.1109/ICCST53801.2021.00060
Yuan Zhu, Shijian Luo, Zuyao Zhang, Menglin Fan
This paper aims to establish the value co-creation and perception mechanism between customers and museum cultural and creative products, then put forward corresponding design strategies while demonstrating its feasibility. It expounds the features and types of user value, establishes a co-creation model and perception model of customer value by quantifying the resources, touchpoints and stages in the co-creation process, and puts to the design experiment and assessment. This paper aims to provide a customer value model reference and design guidance for the museum cultural and creative products design and assessment, and to improve the quality and efficiency of design.
本文旨在建立顾客与博物馆文创产品的价值共创造与感知机制,并在论证其可行性的同时提出相应的设计策略。阐述了用户价值的特征和类型,通过量化共同创造过程中的资源、接触点和阶段,建立了共同创造模型和客户价值感知模型,并进行了设计实验和评估。本文旨在为博物馆文创产品的设计和评估提供客户价值模型参考和设计指导,提高设计的质量和效率。
{"title":"Customer Value Co-creation and Perception in Museum Cultural and Creative Product Design","authors":"Yuan Zhu, Shijian Luo, Zuyao Zhang, Menglin Fan","doi":"10.1109/ICCST53801.2021.00060","DOIUrl":"https://doi.org/10.1109/ICCST53801.2021.00060","url":null,"abstract":"This paper aims to establish the value co-creation and perception mechanism between customers and museum cultural and creative products, then put forward corresponding design strategies while demonstrating its feasibility. It expounds the features and types of user value, establishes a co-creation model and perception model of customer value by quantifying the resources, touchpoints and stages in the co-creation process, and puts to the design experiment and assessment. This paper aims to provide a customer value model reference and design guidance for the museum cultural and creative products design and assessment, and to improve the quality and efficiency of design.","PeriodicalId":222463,"journal":{"name":"2021 International Conference on Culture-oriented Science & Technology (ICCST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133424123","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 Soundscape of Urban Tourism Based on Acoustic Ecology 基于声生态学的城市旅游声景观研究
Pub Date : 2021-11-01 DOI: 10.1109/ICCST53801.2021.00014
Jun Zhang, Fengping Lu, Ying Yang
Acoustic ecology treats sound as a landscape in the environment, emphasizing the relationship between people, sound and the environment. For a long time, urban tourism research has basically stayed in the field of visual elements. Tourism experience is an all-round perception process, and the optimization of soundscape can provide new ideas for improving the urban ecological environment and enhancing the quality of tourism landscapes. Through empirical research taking Nanjing as an example, it is possible to explore the relationship between sound level and tourists’ perception, as well as the characteristics of the basic tone, symbol tone, and signal tone. On this basis, the paper puts forward practical suggestions on the design and management of soundscape from the perspective of acoustic ecology.
声生态学将声音视为环境中的景观,强调人、声音和环境之间的关系。长期以来,城市旅游研究基本停留在视觉元素领域。旅游体验是一个全方位的感知过程,声景观的优化可以为改善城市生态环境、提升旅游景观质量提供新的思路。通过以南京为例的实证研究,可以探索声级与游客感知的关系,以及基本语气、符号语气、信号语气的特征。在此基础上,从声生态的角度对声景观的设计与管理提出了切实可行的建议。
{"title":"Research on Soundscape of Urban Tourism Based on Acoustic Ecology","authors":"Jun Zhang, Fengping Lu, Ying Yang","doi":"10.1109/ICCST53801.2021.00014","DOIUrl":"https://doi.org/10.1109/ICCST53801.2021.00014","url":null,"abstract":"Acoustic ecology treats sound as a landscape in the environment, emphasizing the relationship between people, sound and the environment. For a long time, urban tourism research has basically stayed in the field of visual elements. Tourism experience is an all-round perception process, and the optimization of soundscape can provide new ideas for improving the urban ecological environment and enhancing the quality of tourism landscapes. Through empirical research taking Nanjing as an example, it is possible to explore the relationship between sound level and tourists’ perception, as well as the characteristics of the basic tone, symbol tone, and signal tone. On this basis, the paper puts forward practical suggestions on the design and management of soundscape from the perspective of acoustic ecology.","PeriodicalId":222463,"journal":{"name":"2021 International Conference on Culture-oriented Science & Technology (ICCST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131552172","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
3D-VRVT: 3D Voxel Reconstruction from A Single Image with Vision Transformer 3D- vrvt:基于视觉转换器的单幅图像三维体素重建
Pub Date : 2021-11-01 DOI: 10.1109/ICCST53801.2021.00078
Xi Li, Ping Kuang
Deep CNN methods have shown very competitive performance in 3D voxel reconstruction from single-view synthetic clean-background images. However, how to generate the target object from a real-world image with clutter background is rarely studied. In this paper, we present a novel network named 3D-VRVT for 3D voxel reconstruction from a single image. Unlike pure CNN-based methods in the past, our 3D-VRVT extracts region features with Vision Transformer (ViT) encoder based on self-attention mechanism, and then a well-designed voxel decoder is used to generate three-dimensional voxel from the encoded image features. The experimental results show that our 3D-VRVT can reconstruct 3D voxel from both synthetic clean-background and real-world images effectively.
深度CNN方法在单视图合成干净背景图像的三维体素重建中显示出非常有竞争力的性能。然而,如何从具有杂波背景的真实图像中生成目标物体却鲜有研究。本文提出了一种新的3D- vrvt网络,用于单幅图像的三维体素重建。与以往纯基于cnn的方法不同,我们的3D-VRVT采用基于自注意机制的视觉变换(Vision Transformer, ViT)编码器提取区域特征,然后使用设计良好的体素解码器从编码后的图像特征中生成三维体素。实验结果表明,我们的3D- vrvt可以有效地从合成的干净背景图像和真实图像中重建三维体素。
{"title":"3D-VRVT: 3D Voxel Reconstruction from A Single Image with Vision Transformer","authors":"Xi Li, Ping Kuang","doi":"10.1109/ICCST53801.2021.00078","DOIUrl":"https://doi.org/10.1109/ICCST53801.2021.00078","url":null,"abstract":"Deep CNN methods have shown very competitive performance in 3D voxel reconstruction from single-view synthetic clean-background images. However, how to generate the target object from a real-world image with clutter background is rarely studied. In this paper, we present a novel network named 3D-VRVT for 3D voxel reconstruction from a single image. Unlike pure CNN-based methods in the past, our 3D-VRVT extracts region features with Vision Transformer (ViT) encoder based on self-attention mechanism, and then a well-designed voxel decoder is used to generate three-dimensional voxel from the encoded image features. The experimental results show that our 3D-VRVT can reconstruct 3D voxel from both synthetic clean-background and real-world images effectively.","PeriodicalId":222463,"journal":{"name":"2021 International Conference on Culture-oriented Science & Technology (ICCST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123995808","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: 2
Data-driven Construction of Rural Persona Based on Text Mining and Knowledge Association* 基于文本挖掘和知识关联的农村人物角色数据驱动构建*
Pub Date : 2021-11-01 DOI: 10.1109/ICCST53801.2021.00056
Xi Zeng, Jiang Wu, Zhenghao Liu
The implementation of rural revitalization strategy in China makes “rural tourism” become one of the key industries of rural development. A comprehensive mining of the characteristics of various villages is helpful to promote the overall development of rural economy and realize the modernization of agriculture and rural areas. Based on big data and relevant policy texts, this paper develops a labelling framework, and proposes a deep mining of the rural themes and labels by integrating the deep learning-based text classification and LDA topic mining. In the study, a knowledge graphs of 4,814 entities and 7,369 relationships including villages, scenic spots and featured products is constructed using multi-source heterogeneous data, and we also realizes label fusion and system construction. Through the visualization and analysis of the rural panoramic feature persona, the development modes and the features of villages are described in different aspects. By the construction of rural personas, the study presents the typical features of key villages in rural tourism in China from multiple perspectives, which provides a strong data support for building the recommendation system of online tourism websites and is of great value for promoting the rural tourism.
中国乡村振兴战略的实施,使“乡村旅游”成为乡村发展的重点产业之一。综合挖掘各村特色,有利于促进农村经济全面发展,实现农业农村现代化。基于大数据和相关政策文本,本文开发了标签框架,并将基于深度学习的文本分类和LDA主题挖掘相结合,提出了农村主题和标签的深度挖掘。本研究利用多源异构数据,构建了包含村庄、景点、特色产品在内的4814个实体和7369个关系的知识图谱,并实现了标签融合和系统构建。通过对乡村全景特征人物形象的可视化分析,从不同角度描述乡村的发展模式和特征。本研究通过乡村人物角色的构建,多角度呈现出中国乡村旅游重点乡村的典型特征,为构建在线旅游网站推荐系统提供了强有力的数据支持,对推动乡村旅游具有重要价值。
{"title":"Data-driven Construction of Rural Persona Based on Text Mining and Knowledge Association*","authors":"Xi Zeng, Jiang Wu, Zhenghao Liu","doi":"10.1109/ICCST53801.2021.00056","DOIUrl":"https://doi.org/10.1109/ICCST53801.2021.00056","url":null,"abstract":"The implementation of rural revitalization strategy in China makes “rural tourism” become one of the key industries of rural development. A comprehensive mining of the characteristics of various villages is helpful to promote the overall development of rural economy and realize the modernization of agriculture and rural areas. Based on big data and relevant policy texts, this paper develops a labelling framework, and proposes a deep mining of the rural themes and labels by integrating the deep learning-based text classification and LDA topic mining. In the study, a knowledge graphs of 4,814 entities and 7,369 relationships including villages, scenic spots and featured products is constructed using multi-source heterogeneous data, and we also realizes label fusion and system construction. Through the visualization and analysis of the rural panoramic feature persona, the development modes and the features of villages are described in different aspects. By the construction of rural personas, the study presents the typical features of key villages in rural tourism in China from multiple perspectives, which provides a strong data support for building the recommendation system of online tourism websites and is of great value for promoting the rural tourism.","PeriodicalId":222463,"journal":{"name":"2021 International Conference on Culture-oriented Science & Technology (ICCST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124330749","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: 1
Research on Finite-time Control of Motor Systems: Application to Small-scale Cultural Service Complex 运动系统的有限时间控制研究:在小型文化服务综合体中的应用
Pub Date : 2021-11-01 DOI: 10.1109/ICCST53801.2021.00022
Jiabin Hu, Hongjie Ni, Li-feng Wu, Dan Zhang
In order to realize the function of rapid space transformation in finite time for small-scale cultural service complex applications, this paper proposes the permanent magnet synchronous motor (PMSM) device as the execution unit, and designs a non-singular terminal sliding mode control scheme based on an improved approaching rate. The design of the sliding surface is combined with a special terminal attractor, which not only ensures the rapid convergence of the system state in finite time, but also strengthens the anti-interference ability of the PMSM speed control system. The introduction of the new approaching rate effectively improves the chattering phenomenon in the control process and improves the control accuracy of the system. Finally, a simulation study on the PMSM system is performed, and the experimental results prove the effectiveness of the control scheme.
为了实现小规模文化服务复杂应用在有限时间内快速空间变换的功能,本文提出以永磁同步电机(PMSM)装置为执行单元,设计了一种基于提高逼近率的非奇异终端滑模控制方案。该设计结合了特殊的终端吸引器,既保证了系统状态在有限时间内的快速收敛,又增强了永磁同步电机调速系统的抗干扰能力。新逼近率的引入有效地改善了控制过程中的抖振现象,提高了系统的控制精度。最后,对永磁同步电机系统进行了仿真研究,实验结果证明了该控制方案的有效性。
{"title":"Research on Finite-time Control of Motor Systems: Application to Small-scale Cultural Service Complex","authors":"Jiabin Hu, Hongjie Ni, Li-feng Wu, Dan Zhang","doi":"10.1109/ICCST53801.2021.00022","DOIUrl":"https://doi.org/10.1109/ICCST53801.2021.00022","url":null,"abstract":"In order to realize the function of rapid space transformation in finite time for small-scale cultural service complex applications, this paper proposes the permanent magnet synchronous motor (PMSM) device as the execution unit, and designs a non-singular terminal sliding mode control scheme based on an improved approaching rate. The design of the sliding surface is combined with a special terminal attractor, which not only ensures the rapid convergence of the system state in finite time, but also strengthens the anti-interference ability of the PMSM speed control system. The introduction of the new approaching rate effectively improves the chattering phenomenon in the control process and improves the control accuracy of the system. Finally, a simulation study on the PMSM system is performed, and the experimental results prove the effectiveness of the control scheme.","PeriodicalId":222463,"journal":{"name":"2021 International Conference on Culture-oriented Science & Technology (ICCST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114160622","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
期刊
2021 International Conference on Culture-oriented Science & Technology (ICCST)
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1