CASIA OpenIR

浏览/检索结果: 共5条,第1-5条 帮助

限定条件                    
已选(0)清除 条数/页:   排序方式:
Audio-driven Dubbing for User Generated Contents via Style-aware Semi-parametric Synthesis 期刊论文
IEEE Transactions on Circuits and Systems for Video Technology, 2022, 卷号: 33, 期号: 3, 页码: 1247 - 1261
作者:  Song LS(宋林森);  Wu WY(吴文岩);  Fu CY(傅朝友);  Loy, Chen Change;  He R(赫然)
Adobe PDF(8629Kb)  |  收藏  |  浏览/下载:120/51  |  提交时间:2023/06/29
Talking Face Generation  Video Generation  GAN  Thin-plate Spline  
Multitask deep active contour-based iris segmentation for off-angle iris images 期刊论文
JOURNAL OF ELECTRONIC IMAGING, 2022, 卷号: 31, 期号: 4, 页码: 21
作者:  Lu, Tianhao;  Wang, Caiyong;  Wang, Yunlong;  Sun, Zhenan
Adobe PDF(5346Kb)  |  收藏  |  浏览/下载:271/35  |  提交时间:2022/11/14
iris recognition  iris segmentation  off-angle iris image  active contour  attention mechanism  
Learning Content and Style: Joint Action Recognition and Person Identification from Human Skeletons 期刊论文
Pattern Recognition, 2018, 期号: 81, 页码: 23-35
作者:  Wang Hongsong(王洪松);  Wang Liang(王亮)
浏览  |  Adobe PDF(1622Kb)  |  收藏  |  浏览/下载:335/116  |  提交时间:2018/06/01
Content And Style  Action Recognition  Person Identification From Motions  Skeleton Transformation  Multi-task Rnn  
Learning Relevance Restricted Boltzmann Machine for Unstructured Group Activity and Event Understanding 期刊论文
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2016, 卷号: 119, 期号: 3, 页码: 329-345
作者:  Zhao, Fang;  Huang, Yongzhen;  Wang, Liang;  Xiang, Tao;  Tan, Tieniu
浏览  |  Adobe PDF(6286Kb)  |  收藏  |  浏览/下载:423/131  |  提交时间:2016/10/20
Representation Learning  Video Analysis  Restricted Boltzmann Machine  Sparse Bayesian Learning  
Unconstrained Multimodal Multi-Label Learning 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2015, 卷号: 17, 期号: 11, 页码: 1923-1935
作者:  Huang, Yan;  Wang, Wei;  Wang, Liang
浏览  |  Adobe PDF(3011Kb)  |  收藏  |  浏览/下载:497/212  |  提交时间:2016/01/18
Multi-label Learning  Multi-task Learning  Multimodal Learning  Restricted Boltzmann Machine