Chinese classical poetry exhibits neat sentence patterns and melodic rhythms, which pose high challenges for creators. Most existing systems focus on generation models without considering user participation. Based on the open-source data of the Gushiwen website, THUNLP-AIPoet, we design and implement WPFY, a visual authoring system for Chinese classical poetry: a configuration view supports specify sentence patterns and emotions; an authoring view automatically generates poetry as the basis, and visualizes the multi-dimensional attributes of poetry such as rhythms and emotions; an auxiliary view presents suggested recommendations. User studies concerning the fluency, emotions, and rhythms of the creations demonstrate the usefulness and effectiveness of WPFY.
{"title":"WPFY: Visual Interactive Authoring System for Chinese Classical Poetry","authors":"Yingchaojie Feng, Zihan Zhou, Wei Zhang, S. Tan, Ruimin Shao, Jiazhou Chen, Wei Chen","doi":"10.3724/sp.j.1089.2021.18980","DOIUrl":"https://doi.org/10.3724/sp.j.1089.2021.18980","url":null,"abstract":"Chinese classical poetry exhibits neat sentence patterns and melodic rhythms, which pose high challenges for creators. Most existing systems focus on generation models without considering user participation. Based on the open-source data of the Gushiwen website, THUNLP-AIPoet, we design and implement WPFY, a visual authoring system for Chinese classical poetry: a configuration view supports specify sentence patterns and emotions; an authoring view automatically generates poetry as the basis, and visualizes the multi-dimensional attributes of poetry such as rhythms and emotions; an auxiliary view presents suggested recommendations. User studies concerning the fluency, emotions, and rhythms of the creations demonstrate the usefulness and effectiveness of WPFY.","PeriodicalId":52442,"journal":{"name":"计算机辅助设计与图形学学报","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46896692","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}
Pub Date : 2021-09-01DOI: 10.3724/sp.j.1089.2021.18979
Dong Tian, Guan Li, Shiyu Cheng, Lei Kong, X. Tang, Qing Zhao, Yang Gao, Guihua Shan, Xue-bin Chi
{"title":"Visual Analysis System for Fine-Grained Inline Relationship of Air Quality Data","authors":"Dong Tian, Guan Li, Shiyu Cheng, Lei Kong, X. Tang, Qing Zhao, Yang Gao, Guihua Shan, Xue-bin Chi","doi":"10.3724/sp.j.1089.2021.18979","DOIUrl":"https://doi.org/10.3724/sp.j.1089.2021.18979","url":null,"abstract":"","PeriodicalId":52442,"journal":{"name":"计算机辅助设计与图形学学报","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46170051","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}
: The flame image of the sintering section is usually interfered by smoke and halo, which would cause the blurring of flame edge and material layer in the image. In order to solve the problem that tradi-tional saliency detection method based on two-dimensional image features is difficult to effectively obtain the actual saliency of the time are taken as evaluation indexes. The experimental results show that the proposed method is superior to the other 5 methods, and the detection performance of each stage is gradually enhanced, which lays a foun-dation for improving the effective information extraction of sintering flame section image.
{"title":"Multiple Kernel Boosting Saliency Detection of Flame Image of Sintering Section","authors":"Fubin Wang, Hefei Liu, Rui Wang, Jianghong He, Chenggen Wu","doi":"10.3724/sp.j.1089.2021.18686","DOIUrl":"https://doi.org/10.3724/sp.j.1089.2021.18686","url":null,"abstract":": The flame image of the sintering section is usually interfered by smoke and halo, which would cause the blurring of flame edge and material layer in the image. In order to solve the problem that tradi-tional saliency detection method based on two-dimensional image features is difficult to effectively obtain the actual saliency of the time are taken as evaluation indexes. The experimental results show that the proposed method is superior to the other 5 methods, and the detection performance of each stage is gradually enhanced, which lays a foun-dation for improving the effective information extraction of sintering flame section image.","PeriodicalId":52442,"journal":{"name":"计算机辅助设计与图形学学报","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45297403","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}
Pub Date : 2021-09-01DOI: 10.3724/sp.j.1089.2021.18683
Lin Gan, Li Liu, Lijun Liu, Xiaodong Fu, Qingsong Huang
{"title":"Accurate Human Parsing Model by Edge Contour and Pose Feature","authors":"Lin Gan, Li Liu, Lijun Liu, Xiaodong Fu, Qingsong Huang","doi":"10.3724/sp.j.1089.2021.18683","DOIUrl":"https://doi.org/10.3724/sp.j.1089.2021.18683","url":null,"abstract":"","PeriodicalId":52442,"journal":{"name":"计算机辅助设计与图形学学报","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46847106","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}
Pub Date : 2021-09-01DOI: 10.3724/sp.j.1089.2021.18699
Guoming Xu, Hongwu Yuan, Mo-gen Xue, Feng Wang, Jie Wang
The spatial modulation full polarization computing imaging can obtain both visible and infrared channel images synchronously. However, due to the limitation of the detector, the spatial resolution of the two channels is inconsistent, which brings inconvenience to the following image fusion and target detection process. A spatial modulation computing imaging super-resolution method via scene feature transfer learning is proposed. Firstly, the scene feature transfer model is constructed. The model is based on the analysis of the spatial modulation computing imaging characteristics of different source images in the same scene. Secondly, the convolutional neural networks (CNN) structure of scene transfer is improved and the rectified linear unit 第 9 期 徐国明, 等: 空间调制全偏振计算成像场景迁移超分辨率方法 1441 activation function is selected. At the same time, the spatial resolution consistency constraint is added. Then, the optimal spectral transfer response learning strategy is designed and added to the super-resolution network as the front-end input. Finally, the parameters of spectral transfer response optimization and full polarization super-resolution reconstruction are learned together to obtain the high-resolution polarization image. Some super-resolution experiments with scale factors 2 and 3 are carried out using simulation data and system data of the actual imaging system. The experiments result is evaluated by multiple indicators with three aspects such as subjective visual effect, objective quantitative index and polarization parameter analysis results. In the visual effect, the method can keep the object contour and suppress the noise interference. On the 16 objective index data, the method obtains 10 better, 3 equal and 3 lower results compared with the others. The results verify the effectiveness of the method and also provide data support for calibration correction of imaging system.
{"title":"Spatial Modulation Full Polarization Computing Imaging Super-Resolution via Scene Transfer","authors":"Guoming Xu, Hongwu Yuan, Mo-gen Xue, Feng Wang, Jie Wang","doi":"10.3724/sp.j.1089.2021.18699","DOIUrl":"https://doi.org/10.3724/sp.j.1089.2021.18699","url":null,"abstract":"The spatial modulation full polarization computing imaging can obtain both visible and infrared channel images synchronously. However, due to the limitation of the detector, the spatial resolution of the two channels is inconsistent, which brings inconvenience to the following image fusion and target detection process. A spatial modulation computing imaging super-resolution method via scene feature transfer learning is proposed. Firstly, the scene feature transfer model is constructed. The model is based on the analysis of the spatial modulation computing imaging characteristics of different source images in the same scene. Secondly, the convolutional neural networks (CNN) structure of scene transfer is improved and the rectified linear unit 第 9 期 徐国明, 等: 空间调制全偏振计算成像场景迁移超分辨率方法 1441 activation function is selected. At the same time, the spatial resolution consistency constraint is added. Then, the optimal spectral transfer response learning strategy is designed and added to the super-resolution network as the front-end input. Finally, the parameters of spectral transfer response optimization and full polarization super-resolution reconstruction are learned together to obtain the high-resolution polarization image. Some super-resolution experiments with scale factors 2 and 3 are carried out using simulation data and system data of the actual imaging system. The experiments result is evaluated by multiple indicators with three aspects such as subjective visual effect, objective quantitative index and polarization parameter analysis results. In the visual effect, the method can keep the object contour and suppress the noise interference. On the 16 objective index data, the method obtains 10 better, 3 equal and 3 lower results compared with the others. The results verify the effectiveness of the method and also provide data support for calibration correction of imaging system.","PeriodicalId":52442,"journal":{"name":"计算机辅助设计与图形学学报","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49537111","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}
Medical insurance fraud causes serious economic losses, which has a great impact on the safety and stability of the medical insurance system. However, existing work does not support the joint analysis and exploration of various types of fraud. Based on the medical insurance data related to multi-dimensional time series, a visual analytics approach for anti-fraud in medical insurance is proposed. It can perform spatio-temporal filtering of medical insurance data, locate fraud quickly, and discover hidden frauds by performing the correlation analysis between different types and different subjects of fraud. We design and develop MedicareVis, a visual analysis system for medical insurance anti-fraud. We demonstrate the usefulness and effectiveness of our approach in helping detect the association of fraud through a case study on real-world medical insurance data and interviews with domain experts.
{"title":"MedicareVis: a Joint Visual Analytics Approach for Anti-Fraud in Medical Insurance","authors":"Jiehui Zhou, Rongchen Zhu, Wei Zhang, Junhua Lu, Haochao Ying, Jian Wu, Wei Chen","doi":"10.3724/sp.j.1089.2021.18981","DOIUrl":"https://doi.org/10.3724/sp.j.1089.2021.18981","url":null,"abstract":"Medical insurance fraud causes serious economic losses, which has a great impact on the safety and stability of the medical insurance system. However, existing work does not support the joint analysis and exploration of various types of fraud. Based on the medical insurance data related to multi-dimensional time series, a visual analytics approach for anti-fraud in medical insurance is proposed. It can perform spatio-temporal filtering of medical insurance data, locate fraud quickly, and discover hidden frauds by performing the correlation analysis between different types and different subjects of fraud. We design and develop MedicareVis, a visual analysis system for medical insurance anti-fraud. We demonstrate the usefulness and effectiveness of our approach in helping detect the association of fraud through a case study on real-world medical insurance data and interviews with domain experts.","PeriodicalId":52442,"journal":{"name":"计算机辅助设计与图形学学报","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48211343","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}
Pub Date : 2021-09-01DOI: 10.3724/sp.j.1089.2021.18725
Wenxiang She, B. Liu, J. Tao, Hao Zhang, Zhao Lyu
{"title":"Aggregation of Motion Features of Multiple Paths for Micro-Expression Recognition","authors":"Wenxiang She, B. Liu, J. Tao, Hao Zhang, Zhao Lyu","doi":"10.3724/sp.j.1089.2021.18725","DOIUrl":"https://doi.org/10.3724/sp.j.1089.2021.18725","url":null,"abstract":"","PeriodicalId":52442,"journal":{"name":"计算机辅助设计与图形学学报","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47169525","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}
Pub Date : 2021-09-01DOI: 10.3724/sp.j.1089.2021.18684
Huibiao Wen, Yajuan Li, Chongyang Deng
: In 2016, Várady, et al. introduced the generalized Bézier patch (GB-patch) using generalized barycentric coordinates and bivariate Bernstein functions. GB-patch has a simple control structure and wonderful geometric properties, but the parameters of Bernstein basis functions are rational polynomial of generalized barycentric coordinates. The linear form of generalized barycentric coordinates is used as parameters of the GB-patch. So, it is convenient to analyze the geometric properties of the patch. Furthermore, it is proved that the new GB-patch has the same blending condition as the original GB-patch between the shared boundary of adjacent patches. Next, the time complexity of the new GB-patch is compared to original GB-patch, which shows that the calculating time is reduced. Finally, several geometric examples are pre-sented to show that the geometric characteristics of the patch are almost the same as those of the original ones.
{"title":"Optimization for Parameters of Generalized Bézier Patch","authors":"Huibiao Wen, Yajuan Li, Chongyang Deng","doi":"10.3724/sp.j.1089.2021.18684","DOIUrl":"https://doi.org/10.3724/sp.j.1089.2021.18684","url":null,"abstract":": In 2016, Várady, et al. introduced the generalized Bézier patch (GB-patch) using generalized barycentric coordinates and bivariate Bernstein functions. GB-patch has a simple control structure and wonderful geometric properties, but the parameters of Bernstein basis functions are rational polynomial of generalized barycentric coordinates. The linear form of generalized barycentric coordinates is used as parameters of the GB-patch. So, it is convenient to analyze the geometric properties of the patch. Furthermore, it is proved that the new GB-patch has the same blending condition as the original GB-patch between the shared boundary of adjacent patches. Next, the time complexity of the new GB-patch is compared to original GB-patch, which shows that the calculating time is reduced. Finally, several geometric examples are pre-sented to show that the geometric characteristics of the patch are almost the same as those of the original ones.","PeriodicalId":52442,"journal":{"name":"计算机辅助设计与图形学学报","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42215240","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}
Pub Date : 2021-09-01DOI: 10.3724/sp.j.1089.2021.18718
Ke Li, Qian Zhang, Jinyuan Jia
With the rise of 5G and VR, the demand on visualizing large-scale BIM scene on mobile web browsers is increasing rapidly. However, due to the weakness of browser rendering and networking delay, it is still rather challenging to access huge Web3D scenes smoothly. Firstly, edge computing is introduced into WebBIM online visualization, and a cloud-edge-browser (CEB) collaboratively multi-granularity WebBIM framework is designed. Secondly, the interest degree is defined for each of BIM components and the multi-granularity WebBIM transmission scheduling is proposed based on interest degree. Then, the optimal viewpoint selection for initial loading is presented in terms of globality of viewing scope, light weightness and interest degree. Finally, the experimental platform is deployed using Alibaba Cloud service, and some large-scale BIM scenes are used for practical transmission testing. Experimental results show that the proposed algorithm can effectively reduce the data amount of loading WebBIM scenes. The initial loading speed is also improved significantly, and there is no obvious delay to occur when users move huge WebBIM scenes through freely.
{"title":"CEB-Collaboratively Multi-Granularity Interest Scheduling Algorithm for Loading Large WebBIM Scene","authors":"Ke Li, Qian Zhang, Jinyuan Jia","doi":"10.3724/sp.j.1089.2021.18718","DOIUrl":"https://doi.org/10.3724/sp.j.1089.2021.18718","url":null,"abstract":"With the rise of 5G and VR, the demand on visualizing large-scale BIM scene on mobile web browsers is increasing rapidly. However, due to the weakness of browser rendering and networking delay, it is still rather challenging to access huge Web3D scenes smoothly. Firstly, edge computing is introduced into WebBIM online visualization, and a cloud-edge-browser (CEB) collaboratively multi-granularity WebBIM framework is designed. Secondly, the interest degree is defined for each of BIM components and the multi-granularity WebBIM transmission scheduling is proposed based on interest degree. Then, the optimal viewpoint selection for initial loading is presented in terms of globality of viewing scope, light weightness and interest degree. Finally, the experimental platform is deployed using Alibaba Cloud service, and some large-scale BIM scenes are used for practical transmission testing. Experimental results show that the proposed algorithm can effectively reduce the data amount of loading WebBIM scenes. The initial loading speed is also improved significantly, and there is no obvious delay to occur when users move huge WebBIM scenes through freely.","PeriodicalId":52442,"journal":{"name":"计算机辅助设计与图形学学报","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44734962","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：