首页 > 最新文献

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

英文 中文
Dynamic Imitation Learning Algorithm Based on Surrounding Vision 基于周围视觉的动态模仿学习算法
Pub Date : 2021-11-01 DOI: 10.1109/ICCST53801.2021.00021
Yanqing Wang, Ruyu Sheng, Xu Zhao
Aiming at the poor performance of current conditional imitation learning model in the field of autonomous driving in dynamic environment, a dynamic conditional imitation learning model using LSTM network to fuse historical visual information is proposed. The model first extracts the image features from the front images of four consecutive frames by using the residual network, and then obtains the fusion eigenvector through the LSTM network. The dynamic environment eigenvector is obtained by fusing eigenvector and the side image feature extracted by residual network. Then according to different navigation conditions, different decision networks are used to predict vehicle speed and steering wheel angle. Finally, proportional integral control method is used to realize vehicle longitudinal control. The experimental results show that the vehicle control can be better.
针对当前条件模仿学习模型在动态环境下自动驾驶领域表现不佳的问题,提出了一种利用LSTM网络融合历史视觉信息的动态条件模仿学习模型。该模型首先利用残差网络从连续四帧的正面图像中提取图像特征,然后通过LSTM网络获得融合特征向量。将特征向量与残差网络提取的侧像特征融合得到动态环境特征向量。然后根据不同的导航条件,使用不同的决策网络来预测车速和方向盘角度。最后,采用比例积分控制方法实现车辆纵向控制。实验结果表明,该方法能较好地控制车辆。
{"title":"Dynamic Imitation Learning Algorithm Based on Surrounding Vision","authors":"Yanqing Wang, Ruyu Sheng, Xu Zhao","doi":"10.1109/ICCST53801.2021.00021","DOIUrl":"https://doi.org/10.1109/ICCST53801.2021.00021","url":null,"abstract":"Aiming at the poor performance of current conditional imitation learning model in the field of autonomous driving in dynamic environment, a dynamic conditional imitation learning model using LSTM network to fuse historical visual information is proposed. The model first extracts the image features from the front images of four consecutive frames by using the residual network, and then obtains the fusion eigenvector through the LSTM network. The dynamic environment eigenvector is obtained by fusing eigenvector and the side image feature extracted by residual network. Then according to different navigation conditions, different decision networks are used to predict vehicle speed and steering wheel angle. Finally, proportional integral control method is used to realize vehicle longitudinal control. The experimental results show that the vehicle control can be better.","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":"131229728","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
Teaching practice and exploration of “creative manual printing and dyeing” based on the inheritance of Jingchu textile intangible cultural heritage 基于荆楚纺织非物质文化遗产传承的“创意手工印染”教学实践与探索
Pub Date : 2021-11-01 DOI: 10.1109/ICCST53801.2021.00069
Ni Wang, Xin Wei, Yufei Dong
Jingchu textile intangible cultural heritage is defined as the traditional textile, dyeing, weaving and embroidery intangible cultural heritage project in Hubei Province. At present, the traditional printing and dyeing intangible cultural heritage projects mainly include Tianmen blue calico dyeing technology and traditional plant dye dyeing technology. In order to better inherit the textile intangible cultural heritage on campus, This paper used fieldwork,literature research to explore a multi-faceted teaching model. And focuses on how to integrate the traditional printing and dyeing intangible cultural heritage into classroom teaching, innovative design, extracurricular practice, big innovation competition and other aspects in the course of “creative hand printing and dyeing” in Wuhan Textile University, combined with relevant scientific research projects to organically combine theoretical research and design practice, so as to enable students to understand and master the essence of Jingchu traditional hand printing and dyeing skills, develop students’ innovative and entrepreneurial thinking, and improve their comprehensive quality and ability.
荆楚纺织非物质文化遗产是湖北省传统纺织、印染、织绣非物质文化遗产项目。目前,传统印染非物质文化遗产项目主要有天门蓝印花布染色技术和传统植物染料染色技术。为了更好地传承校园纺织非物质文化遗产,本文采用实地调研、文献研究等方法,探索了一种多角度的教学模式。并重点探讨了在武汉纺织大学“创意手印染”课程中如何将传统印染非物质文化遗产融入课堂教学、创新设计、课外实践、大创新大赛等方面,结合相关科研项目,将理论研究与设计实践有机结合;使学生了解和掌握荆楚传统手工印染技艺的精髓,培养学生的创新创业思维,提高学生的综合素质和能力。
{"title":"Teaching practice and exploration of “creative manual printing and dyeing” based on the inheritance of Jingchu textile intangible cultural heritage","authors":"Ni Wang, Xin Wei, Yufei Dong","doi":"10.1109/ICCST53801.2021.00069","DOIUrl":"https://doi.org/10.1109/ICCST53801.2021.00069","url":null,"abstract":"Jingchu textile intangible cultural heritage is defined as the traditional textile, dyeing, weaving and embroidery intangible cultural heritage project in Hubei Province. At present, the traditional printing and dyeing intangible cultural heritage projects mainly include Tianmen blue calico dyeing technology and traditional plant dye dyeing technology. In order to better inherit the textile intangible cultural heritage on campus, This paper used fieldwork,literature research to explore a multi-faceted teaching model. And focuses on how to integrate the traditional printing and dyeing intangible cultural heritage into classroom teaching, innovative design, extracurricular practice, big innovation competition and other aspects in the course of “creative hand printing and dyeing” in Wuhan Textile University, combined with relevant scientific research projects to organically combine theoretical research and design practice, so as to enable students to understand and master the essence of Jingchu traditional hand printing and dyeing skills, develop students’ innovative and entrepreneurial thinking, and improve their comprehensive quality and ability.","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":"129736649","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 the Innovative Application of Ancient Chinese Official Hat Cultural Elements in the Design of Daily Necessities 中国古代官帽文化元素在日常用品设计中的创新应用研究
Pub Date : 2021-11-01 DOI: 10.1109/ICCST53801.2021.00051
Nuo Pang, Jiahong Pang, Yiqiu Wang
Due to the rapid economic growth in China and the improvement of living standards, improving the quality of life has become an essential requirement for the development of modern social life. We can’t live without food and clothing live line, and the requirement for eating is usually higher. Whether we eat outside or make food at home, the choice of ingredients and seasoning will affect the food flavor, especially the seasonings. The selection and use of every kind of collocation even bring out the different color and taste. However, it is important to choose a good condiment to improve the quality of delicious food and the feeling of the user. Nowadays, the seasoning appliances used by most families are relatively single, which cannot meet the aesthetic needs of people in modern society. Therefore, I want to design a seasoning pot with the characteristics of ancient official hat culture through continuous exploration of Chinese culture, which can not only realize the basic functions of seasoning utensils, but also have a unique beauty. At the same time, each seasoning pot represents a dynasty. Culture, combined together, presents a colorful Chinese culture. This not only satisfies people’s material needs, but also enriches people’s understanding of ancient Chinese culture. It has a certain inheritance significance and brings a different experience to users.
由于中国经济的快速增长和生活水平的提高,提高生活质量已经成为现代社会生活发展的本质要求。我们的生活离不开衣食住行,对吃的要求通常更高。无论我们在外面吃饭还是在家里做食物,食材和调味料的选择都会影响食物的风味,尤其是调味料。每一种搭配的选择和运用,更能衬托出不同的色彩和味道。然而,选择一种好的调味品对于提高美味食物的质量和使用者的感受是很重要的。现在大多数家庭使用的调味器具比较单一,不能满足现代社会人们的审美需求。因此,我想通过对中国文化的不断探索,设计出一款具有古代官帽文化特征的调味壶,既能实现调味器具的基本功能,又具有独特的美感。同时,每一个调味锅都代表一个朝代。文化,结合在一起,呈现出丰富多彩的中国文化。这不仅满足了人们的物质需求,也丰富了人们对中国古代文化的认识。具有一定的传承意义,给用户带来不一样的体验。
{"title":"Research on the Innovative Application of Ancient Chinese Official Hat Cultural Elements in the Design of Daily Necessities","authors":"Nuo Pang, Jiahong Pang, Yiqiu Wang","doi":"10.1109/ICCST53801.2021.00051","DOIUrl":"https://doi.org/10.1109/ICCST53801.2021.00051","url":null,"abstract":"Due to the rapid economic growth in China and the improvement of living standards, improving the quality of life has become an essential requirement for the development of modern social life. We can’t live without food and clothing live line, and the requirement for eating is usually higher. Whether we eat outside or make food at home, the choice of ingredients and seasoning will affect the food flavor, especially the seasonings. The selection and use of every kind of collocation even bring out the different color and taste. However, it is important to choose a good condiment to improve the quality of delicious food and the feeling of the user. Nowadays, the seasoning appliances used by most families are relatively single, which cannot meet the aesthetic needs of people in modern society. Therefore, I want to design a seasoning pot with the characteristics of ancient official hat culture through continuous exploration of Chinese culture, which can not only realize the basic functions of seasoning utensils, but also have a unique beauty. At the same time, each seasoning pot represents a dynasty. Culture, combined together, presents a colorful Chinese culture. This not only satisfies people’s material needs, but also enriches people’s understanding of ancient Chinese culture. It has a certain inheritance significance and brings a different experience to users.","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":"114895600","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
Information propagation based on information value 基于信息价值的信息传播
Pub Date : 2021-11-01 DOI: 10.1109/ICCST53801.2021.00072
Yu Gao, Ping Kuang
On social networks, the spread of a piece of information may attract a lot of people’s attention. Some people who are not interested in the beginning may become interested and start to spread it after repeated contact. Similarly, those who are interested in the beginning tend to disappear after a while. In this study, a propagation model, in which infective’s and removals can transform form each other, is constructed. We introduce the LIF neuron model in neurology and propose a SEIRI information propagation model based on this model. In the process of a piece of information, its information value will change with the range and time of propagation. To reflect the change of the actual value of information in the process of communication, this paper puts forward the influence of the change of information value with time and the range of propagation. The experimental results show that the propagation process can be divided into initial stage, rapid propagation stage, and stable stage. The process of spreading different messages is different, but the overall trend is similar.
在社交网络上,一条信息的传播可能会吸引很多人的注意力。一些一开始不感兴趣的人,可能会在反复接触后产生兴趣并开始传播。同样,那些对开始感兴趣的人往往会在一段时间后消失。本文建立了侵染体和脱毒体相互转化的传播模型。我们引入神经学中的LIF神经元模型,并在此基础上提出了一个SEIRI信息传播模型。在一条信息的传播过程中,其信息价值会随着传播范围和传播时间的变化而变化。为了反映信息在传播过程中实际价值的变化,本文提出了信息价值随时间和传播范围变化的影响。实验结果表明,传播过程可分为初始阶段、快速传播阶段和稳定传播阶段。传播不同信息的过程不同,但总体趋势是相似的。
{"title":"Information propagation based on information value","authors":"Yu Gao, Ping Kuang","doi":"10.1109/ICCST53801.2021.00072","DOIUrl":"https://doi.org/10.1109/ICCST53801.2021.00072","url":null,"abstract":"On social networks, the spread of a piece of information may attract a lot of people’s attention. Some people who are not interested in the beginning may become interested and start to spread it after repeated contact. Similarly, those who are interested in the beginning tend to disappear after a while. In this study, a propagation model, in which infective’s and removals can transform form each other, is constructed. We introduce the LIF neuron model in neurology and propose a SEIRI information propagation model based on this model. In the process of a piece of information, its information value will change with the range and time of propagation. To reflect the change of the actual value of information in the process of communication, this paper puts forward the influence of the change of information value with time and the range of propagation. The experimental results show that the propagation process can be divided into initial stage, rapid propagation stage, and stable stage. The process of spreading different messages is different, but the overall trend is similar.","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":"133794162","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 the Service Evaluation System of Radio, Television and Network Audiovisual Media under the Background of Convergent Development 融合发展背景下广电网络视听媒体业务评价体系研究
Pub Date : 2021-11-01 DOI: 10.1109/ICCST53801.2021.00088
Yan Wang, Haozhan Li, Wanlan Li
Under the background of integrated development establishing a service evaluation system for radio, television and network audiovisual media is an important link in the indepth development of China’s audiovisual media industry in the application of big data. This research analyzes the current development status of domestic media service. From the perspective of data application and industry common perspectives, it constructs a radio, television and network audiovisual consisting of four dimensions: media influence, media communication, content production, and media technology quality. Media service evaluation system, and explain the system framework and indicators. On this basis, the idea of determining index weights based on the combined weighting VIKOR method is proposed.
在融合发展背景下,建立广播电视网络视听媒体服务评价体系,是中国视听媒体产业在大数据应用中深度发展的重要一环。本研究分析了国内媒体服务的发展现状。从数据应用和行业共同视角出发,构建了一个由媒体影响力、媒体传播、内容生产、媒体技术质量四个维度组成的广电网络视听。媒体服务评价体系,并阐述了体系框架和指标。在此基础上,提出了基于组合加权VIKOR法确定指标权重的思路。
{"title":"Research on the Service Evaluation System of Radio, Television and Network Audiovisual Media under the Background of Convergent Development","authors":"Yan Wang, Haozhan Li, Wanlan Li","doi":"10.1109/ICCST53801.2021.00088","DOIUrl":"https://doi.org/10.1109/ICCST53801.2021.00088","url":null,"abstract":"Under the background of integrated development establishing a service evaluation system for radio, television and network audiovisual media is an important link in the indepth development of China’s audiovisual media industry in the application of big data. This research analyzes the current development status of domestic media service. From the perspective of data application and industry common perspectives, it constructs a radio, television and network audiovisual consisting of four dimensions: media influence, media communication, content production, and media technology quality. Media service evaluation system, and explain the system framework and indicators. On this basis, the idea of determining index weights based on the combined weighting VIKOR method is proposed.","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":"121702282","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
Analysis and Optimization of Urban Tourism Spatial Behavior Path : —Taking Nanjing City as an example 城市旅游空间行为路径分析与优化——以南京市为例
Pub Date : 2021-11-01 DOI: 10.1109/ICCST53801.2021.00013
Fengping Lu, Jun Zhang, Ying Yang
Urban tourism spatial behavior path refers to the spatial movement track of tourists in the destination city area. Taking Nanjing as an example, through empirical research, we can summarize the four existing urban tourism path models and their optimization development directions. Long-distance tourists often presents a “single node” path model, and its optimization goal is to achieve a “multi-node” travel path. Tourists from neighboring provinces are jumping “linear tourism” path model, and the optimization goal is “circular tourism” paths involving more urban tourist areas. Tourists in the province tend to adopt the “chain tourism” path model, and the optimization goal is to develop goals is the “axis-radiation tourism” path. The spatial behavior path of the urban aborigines is “near single node” tourism, and the development direction is “base tourism”.
城市旅游空间行为路径是指游客在目的地城市区域内的空间运动轨迹。以南京市为例,通过实证研究,总结出现有的四种城市旅游路径模型及其优化发展方向。长途旅游者往往呈现“单节点”路径模型,其优化目标是实现“多节点”的出行路径。邻近省份的游客正在跳过“线性旅游”路径模型,优化目标是涉及更多城市旅游区的“循环旅游”路径。全省游客倾向于采用“连锁旅游”路径模式,优化目标为发展目标为“轴-辐射旅游”路径。城市原住民空间行为路径为“近单节点”旅游,发展方向为“基地旅游”。
{"title":"Analysis and Optimization of Urban Tourism Spatial Behavior Path : —Taking Nanjing City as an example","authors":"Fengping Lu, Jun Zhang, Ying Yang","doi":"10.1109/ICCST53801.2021.00013","DOIUrl":"https://doi.org/10.1109/ICCST53801.2021.00013","url":null,"abstract":"Urban tourism spatial behavior path refers to the spatial movement track of tourists in the destination city area. Taking Nanjing as an example, through empirical research, we can summarize the four existing urban tourism path models and their optimization development directions. Long-distance tourists often presents a “single node” path model, and its optimization goal is to achieve a “multi-node” travel path. Tourists from neighboring provinces are jumping “linear tourism” path model, and the optimization goal is “circular tourism” paths involving more urban tourist areas. Tourists in the province tend to adopt the “chain tourism” path model, and the optimization goal is to develop goals is the “axis-radiation tourism” path. The spatial behavior path of the urban aborigines is “near single node” tourism, and the development direction is “base 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":"127393129","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
Multimodal Emotion Recognition in Deep Learning:a Survey 深度学习中的多模态情感识别研究
Pub Date : 2021-11-01 DOI: 10.1109/ICCST53801.2021.00027
Xin Gu, Yinghua Shen, Jie Xu
Emotion recognition is an active research issue in recent decades. It can be divided into implicit emotion recognition based on physiological signals and direct emotion recognition based on non-physiological signals. Direct emotion recognition through the processing of different modal information for emotion recognition is the emphasis of this paper. Firstly, we analyze the framework and research methods of video emotion recognition and music emotion recognition in detail, especially the research method based on deep learning. Then, the fusion technology in multimodal emotion recognition combining video and audio is compared. On the basis of the above contents, this paper reviews the research status of emotion recognition based on deep learning. Finally, according to the current research situation, we put forward some suggestions for future research.
情绪识别是近几十年来一个活跃的研究课题。它可以分为基于生理信号的内隐情绪识别和基于非生理信号的直接情绪识别。通过对不同模态信息的处理直接进行情感识别是本文研究的重点。首先,详细分析了视频情感识别和音乐情感识别的框架和研究方法,特别是基于深度学习的研究方法。然后,对视频和音频相结合的多模态情感识别融合技术进行了比较。在以上内容的基础上,本文综述了基于深度学习的情绪识别的研究现状。最后,根据目前的研究现状,对未来的研究提出了一些建议。
{"title":"Multimodal Emotion Recognition in Deep Learning:a Survey","authors":"Xin Gu, Yinghua Shen, Jie Xu","doi":"10.1109/ICCST53801.2021.00027","DOIUrl":"https://doi.org/10.1109/ICCST53801.2021.00027","url":null,"abstract":"Emotion recognition is an active research issue in recent decades. It can be divided into implicit emotion recognition based on physiological signals and direct emotion recognition based on non-physiological signals. Direct emotion recognition through the processing of different modal information for emotion recognition is the emphasis of this paper. Firstly, we analyze the framework and research methods of video emotion recognition and music emotion recognition in detail, especially the research method based on deep learning. Then, the fusion technology in multimodal emotion recognition combining video and audio is compared. On the basis of the above contents, this paper reviews the research status of emotion recognition based on deep learning. Finally, according to the current research situation, we put forward some suggestions for future research.","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":"130505471","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: 8
Commodity Image Retrieval Method Based on CNN and Score Fusion 基于CNN和分数融合的商品图像检索方法
Pub Date : 2021-11-01 DOI: 10.1109/ICCST53801.2021.00101
Zihao Liu, Xiaoyu Wu, Jiayao Qian, Zhiyi Zhu
Content-based image retrieval (CBIR) is an important research direction of computer vision and has been well studied for a long period. The important aim in CBIR is to reduce the semantic gap issue that improves the performance of image retrieval. It plays an important role in the field of e-commerce. This paper proposes a CBIR method based on ResNet and EfficientNet, and conducts experiments on the dataset of eProduct Visual Search Challenge 2021. First, because the dataset lacks direct query-index tags and the categories are not balanced, transfer learning is used to fine-tune the model with a balanced sub-dataset constructed by data augmentation. Second, the semantic features are extracted by the ResNet and EfficientNet and similarity comparison is calculated between the query and index image. Finally, the similarity result is decided through fusing the scores obtained by the two CNNs through a strategy. Experiments on the eProduct dataset demonstrate our algorithm can achieve a good performance.
基于内容的图像检索(CBIR)是计算机视觉的一个重要研究方向,长期以来得到了广泛的研究。CBIR的重要目标是减少语义间隙问题,从而提高图像检索的性能。它在电子商务领域扮演着重要的角色。本文提出了一种基于ResNet和effentnet的CBIR方法,并在eProduct Visual Search Challenge 2021数据集上进行了实验。首先,由于数据集缺乏直接查询索引标签,并且类别不平衡,因此使用迁移学习通过数据增强构建平衡子数据集来微调模型。其次,利用ResNet和effentnet提取语义特征,计算查询图像与索引图像的相似度比较;最后,通过策略将两个cnn得到的分数融合,确定相似度结果。在eProduct数据集上的实验表明,该算法可以取得较好的性能。
{"title":"Commodity Image Retrieval Method Based on CNN and Score Fusion","authors":"Zihao Liu, Xiaoyu Wu, Jiayao Qian, Zhiyi Zhu","doi":"10.1109/ICCST53801.2021.00101","DOIUrl":"https://doi.org/10.1109/ICCST53801.2021.00101","url":null,"abstract":"Content-based image retrieval (CBIR) is an important research direction of computer vision and has been well studied for a long period. The important aim in CBIR is to reduce the semantic gap issue that improves the performance of image retrieval. It plays an important role in the field of e-commerce. This paper proposes a CBIR method based on ResNet and EfficientNet, and conducts experiments on the dataset of eProduct Visual Search Challenge 2021. First, because the dataset lacks direct query-index tags and the categories are not balanced, transfer learning is used to fine-tune the model with a balanced sub-dataset constructed by data augmentation. Second, the semantic features are extracted by the ResNet and EfficientNet and similarity comparison is calculated between the query and index image. Finally, the similarity result is decided through fusing the scores obtained by the two CNNs through a strategy. Experiments on the eProduct dataset demonstrate our algorithm can achieve a good performance.","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":"130742894","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 Probe into the High-tech Equipment System of Culture and Tourism Integration Industry 文旅融合产业高技术装备体系探讨
Pub Date : 2021-11-01 DOI: 10.1109/ICCST53801.2021.00125
Hailong Fan, Bin Zhou, Hanxi Wang
Over the past few years, with the rapid development of culture and tourism integration industry, more and more high-tech equipment has been applied, and the content and form of such equipment are constantly enriched and increased. However, researches based on the high-tech system of culture and tourism integration industry have not drawn widespread attention in academic circles. Therefore, this paper introduces the relevant concepts, and points out its current form and direction. Finally, it summarizes what high technologies and equipment are included in the industry, as well as the construction process of these high-tech systems.
近年来,随着文化旅游融合产业的快速发展,越来越多的高科技设备得到了应用,这些设备的内容和形式也在不断丰富和增加。然而,基于文化与旅游融合产业高科技体系的研究并未引起学术界的广泛关注。因此,本文介绍了相关概念,并指出了其目前的形式和发展方向。最后,总结了产业中包含哪些高科技和设备,以及这些高科技系统的建设过程。
{"title":"A Probe into the High-tech Equipment System of Culture and Tourism Integration Industry","authors":"Hailong Fan, Bin Zhou, Hanxi Wang","doi":"10.1109/ICCST53801.2021.00125","DOIUrl":"https://doi.org/10.1109/ICCST53801.2021.00125","url":null,"abstract":"Over the past few years, with the rapid development of culture and tourism integration industry, more and more high-tech equipment has been applied, and the content and form of such equipment are constantly enriched and increased. However, researches based on the high-tech system of culture and tourism integration industry have not drawn widespread attention in academic circles. Therefore, this paper introduces the relevant concepts, and points out its current form and direction. Finally, it summarizes what high technologies and equipment are included in the industry, as well as the construction process of these high-tech systems.","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":"114231476","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
Multi-robot Cooperative Exploration Based on Geometric-topological Scene Map 基于几何拓扑场景地图的多机器人协同探索
Pub Date : 2021-11-01 DOI: 10.1109/ICCST53801.2021.00015
Yanqing Wang, Yongquan Li, Wenjun Lu
In view of the advantages and disadvantages of node geometry information and characteristic scene information, this paper proposes multi-robot cooperative exploration based on geometric-topological scene map. Our algorithm adds the geometric information of nodes to the feature scene map, so as to detect and recognize the node loop. Considering the spatial relationship between a single node and different nodes, we use the Hidden Markov Model (HMM) to locate nodes accurately, and use the geometrical-topological feature scene matching method to perform map fusion. The local map fusion of each robot is turned into a problem of geometrical-characteristic scene matching. Finally, the multitask assignment method of market method is used to realize the multi-robot cooperative exploration task on the simulation platform.
针对节点几何信息和特征场景信息的优缺点,提出了基于几何拓扑场景地图的多机器人协同探索方法。我们的算法将节点的几何信息加入到特征场景地图中,从而检测和识别节点环路。考虑到单个节点与不同节点之间的空间关系,采用隐马尔可夫模型(HMM)精确定位节点,并采用几何拓扑特征场景匹配方法进行地图融合。将各机器人的局部地图融合问题转化为几何特征场景匹配问题。最后,利用市场方法中的多任务分配方法,在仿真平台上实现了多机器人协同探索任务。
{"title":"Multi-robot Cooperative Exploration Based on Geometric-topological Scene Map","authors":"Yanqing Wang, Yongquan Li, Wenjun Lu","doi":"10.1109/ICCST53801.2021.00015","DOIUrl":"https://doi.org/10.1109/ICCST53801.2021.00015","url":null,"abstract":"In view of the advantages and disadvantages of node geometry information and characteristic scene information, this paper proposes multi-robot cooperative exploration based on geometric-topological scene map. Our algorithm adds the geometric information of nodes to the feature scene map, so as to detect and recognize the node loop. Considering the spatial relationship between a single node and different nodes, we use the Hidden Markov Model (HMM) to locate nodes accurately, and use the geometrical-topological feature scene matching method to perform map fusion. The local map fusion of each robot is turned into a problem of geometrical-characteristic scene matching. Finally, the multitask assignment method of market method is used to realize the multi-robot cooperative exploration task on the simulation platform.","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":"116677028","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