发布求助
文献互助 智能选刊 最新文献

Comput. Vis. Image Underst.最新文献

筛选
英文 中文
Spatial Location Constraint Prototype Loss for Open Set Recognition 开放集识别的空间位置约束原型损失
Comput. Vis. Image Underst. Pub Date : 2021-10-21 DOI: 10.2139/ssrn.4076750
Ziheng Xia, Ganggang Dong, Penghui Wang, Hongwei Liu
{"title":"Spatial Location Constraint Prototype Loss for Open Set Recognition","authors":"Ziheng Xia, Ganggang Dong, Penghui Wang, Hongwei Liu","doi":"10.2139/ssrn.4076750","DOIUrl":"https://doi.org/10.2139/ssrn.4076750","url":null,"abstract":"One of the challenges in pattern recognition is open set recognition. Compared with closed set recognition, open set recognition needs to reduce not only the empirical risk, but also the open space risk, and the reduction of these two risks corresponds to classifying the known classes and identifying the unknown classes respectively. How to reduce the open space risk is the key of open set recognition. This paper explores the origin of the open space risk by analyzing the distribution of known and unknown classes features. On this basis, the spatial location constraint prototype loss function is proposed to reduce the two risks simultaneously. Extensive experiments on multiple benchmark datasets and many visualization results indicate that our methods is superior to most existing approaches.","PeriodicalId":10549,"journal":{"name":"Comput. Vis. Image Underst.","volume":"1 1","pages":"103651"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88564485","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: 5
Adapting Game Engines to Curved Spaces 调整游戏引擎到弯曲空间
Comput. Vis. Image Underst. Pub Date : 2021-10-11 DOI: 10.1007/s00371-021-02303-2
László Szirmay-Kalos, M. Magdics
{"title":"Adapting Game Engines to Curved Spaces","authors":"László Szirmay-Kalos, M. Magdics","doi":"10.1007/s00371-021-02303-2","DOIUrl":"https://doi.org/10.1007/s00371-021-02303-2","url":null,"abstract":"","PeriodicalId":10549,"journal":{"name":"Comput. Vis. Image Underst.","volume":"47 1","pages":"4383-4395"},"PeriodicalIF":0.0,"publicationDate":"2021-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85693472","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
Three-stage generative network for single-view point cloud completion 单视图点云补全的三阶段生成网络
Comput. Vis. Image Underst. Pub Date : 2021-10-08 DOI: 10.1007/s00371-021-02301-4
Bingling Xiao, F. Da
{"title":"Three-stage generative network for single-view point cloud completion","authors":"Bingling Xiao, F. Da","doi":"10.1007/s00371-021-02301-4","DOIUrl":"https://doi.org/10.1007/s00371-021-02301-4","url":null,"abstract":"","PeriodicalId":10549,"journal":{"name":"Comput. Vis. Image Underst.","volume":"412 1","pages":"4373-4382"},"PeriodicalIF":0.0,"publicationDate":"2021-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84883660","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
Object-based illumination transferring and rendering for applications of mixed reality 混合现实应用中基于物体的照明传输和渲染
Comput. Vis. Image Underst. Pub Date : 2021-10-07 DOI: 10.1007/s00371-021-02292-2
Di Xu, Zhen Li, Qinglei Cao
{"title":"Object-based illumination transferring and rendering for applications of mixed reality","authors":"Di Xu, Zhen Li, Qinglei Cao","doi":"10.1007/s00371-021-02292-2","DOIUrl":"https://doi.org/10.1007/s00371-021-02292-2","url":null,"abstract":"","PeriodicalId":10549,"journal":{"name":"Comput. Vis. Image Underst.","volume":"97 1","pages":"4251-4265"},"PeriodicalIF":0.0,"publicationDate":"2021-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73571992","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
High-quality image multi-focus fusion to address ringing and blurring artifacts without loss of information 高质量的图像多焦点融合，以解决振铃和模糊的工件，而不丢失信息
Comput. Vis. Image Underst. Pub Date : 2021-10-05 DOI: 10.1007/s00371-021-02300-5
N. Jagtap, Sudeep D. Thepade
{"title":"High-quality image multi-focus fusion to address ringing and blurring artifacts without loss of information","authors":"N. Jagtap, Sudeep D. Thepade","doi":"10.1007/s00371-021-02300-5","DOIUrl":"https://doi.org/10.1007/s00371-021-02300-5","url":null,"abstract":"","PeriodicalId":10549,"journal":{"name":"Comput. Vis. Image Underst.","volume":"39 1","pages":"4353-4371"},"PeriodicalIF":0.0,"publicationDate":"2021-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73190103","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: 5
Global structure-guided learning framework for underwater image enhancement 水下图像增强的全局结构引导学习框架
Comput. Vis. Image Underst. Pub Date : 2021-10-04 DOI: 10.1007/s00371-021-02305-0
Runji Lin, Jinyuan Liu, Risheng Liu, Xin Fan
{"title":"Global structure-guided learning framework for underwater image enhancement","authors":"Runji Lin, Jinyuan Liu, Risheng Liu, Xin Fan","doi":"10.1007/s00371-021-02305-0","DOIUrl":"https://doi.org/10.1007/s00371-021-02305-0","url":null,"abstract":"","PeriodicalId":10549,"journal":{"name":"Comput. Vis. Image Underst.","volume":"45 1","pages":"4419-4434"},"PeriodicalIF":0.0,"publicationDate":"2021-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80862498","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
An image super-resolution network based on multi-scale convolution fusion 基于多尺度卷积融合的图像超分辨率网络
Comput. Vis. Image Underst. Pub Date : 2021-10-04 DOI: 10.1007/s00371-021-02297-x
Xin Yang, Yitian Zhu, Yingqing Guo, Dake Zhou
{"title":"An image super-resolution network based on multi-scale convolution fusion","authors":"Xin Yang, Yitian Zhu, Yingqing Guo, Dake Zhou","doi":"10.1007/s00371-021-02297-x","DOIUrl":"https://doi.org/10.1007/s00371-021-02297-x","url":null,"abstract":"","PeriodicalId":10549,"journal":{"name":"Comput. Vis. Image Underst.","volume":"55 1","pages":"4307-4317"},"PeriodicalIF":0.0,"publicationDate":"2021-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87021458","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: 11
Dynamic information enhancement for video classification 视频分类的动态信息增强
Comput. Vis. Image Underst. Pub Date : 2021-10-01 DOI: 10.1016/J.IMAVIS.2021.104244
Rongchang Li, Xiaojun Wu, Cong Wu, Tianyang Xu, J. Kittler
{"title":"Dynamic information enhancement for video classification","authors":"Rongchang Li, Xiaojun Wu, Cong Wu, Tianyang Xu, J. Kittler","doi":"10.1016/J.IMAVIS.2021.104244","DOIUrl":"https://doi.org/10.1016/J.IMAVIS.2021.104244","url":null,"abstract":"","PeriodicalId":10549,"journal":{"name":"Comput. Vis. Image Underst.","volume":"1 1","pages":"104244"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83362366","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
Omnidirectional stereo depth estimation based on spherical deep network 基于球面深度网络的全向立体深度估计
Comput. Vis. Image Underst. Pub Date : 2021-10-01 DOI: 10.1016/J.IMAVIS.2021.104264
Ming Li, Xuejiao Hu, J. Dai, Yang Li, S. Du
{"title":"Omnidirectional stereo depth estimation based on spherical deep network","authors":"Ming Li, Xuejiao Hu, J. Dai, Yang Li, S. Du","doi":"10.1016/J.IMAVIS.2021.104264","DOIUrl":"https://doi.org/10.1016/J.IMAVIS.2021.104264","url":null,"abstract":"","PeriodicalId":10549,"journal":{"name":"Comput. Vis. Image Underst.","volume":"11 1","pages":"104264"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75189676","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: 4
A review of deep learning techniques for 2D and 3D human pose estimation 二维和三维人体姿态估计的深度学习技术综述
Comput. Vis. Image Underst. Pub Date : 2021-10-01 DOI: 10.1016/J.IMAVIS.2021.104282
Miniar Ben Gamra, M. Akhloufi
{"title":"A review of deep learning techniques for 2D and 3D human pose estimation","authors":"Miniar Ben Gamra, M. Akhloufi","doi":"10.1016/J.IMAVIS.2021.104282","DOIUrl":"https://doi.org/10.1016/J.IMAVIS.2021.104282","url":null,"abstract":"","PeriodicalId":10549,"journal":{"name":"Comput. Vis. Image Underst.","volume":"47 1","pages":"104282"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85620216","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: 35
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
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
请完成安全验证×
相关产品
×
本文献相关产品
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信