CASIA OpenIR
(本次检索基于用户作品认领结果)

浏览/检索结果: 共33条,第1-10条 帮助

限定条件            
已选(0)清除 条数/页:   排序方式:
Personalized Graph Generation for Monocular 3D Human Pose and Shape Estimation 期刊论文
IEEE Transactions on Circuits and Systems for Video Technology, 2023, 卷号: 34, 期号: 4, 页码: 2399-2413
作者:  Junxing Hu;  Hongwen Zhang;  Yunlong Wang;  Min Ren;  Zhenan Sun
Adobe PDF(4963Kb)  |  收藏  |  浏览/下载:21/7  |  提交时间:2024/05/30
3D Human Pose and Shape Estimation  Personalized Graph Generation  Body-Oriented Adjacency Matrix  
Multiscale Dynamic Graph Representation for Biometric Recognition With Occlusions 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 卷号: 45, 期号: 12, 页码: 15120-15136
作者:  Ren, Min;  Wang, Yunlong;  Zhu, Yuhao;  Zhang, Kunbo;  Sun, Zhenan
收藏  |  浏览/下载:29/0  |  提交时间:2024/03/26
Biometrics  deep learning  face recognition  graph neural networks  iris recognition  
AIF-LFNet: All-in-Focus Light Field Super-Resolution Method Considering the Depth-Varying Defocus 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2023, 卷号: 33, 期号: 8, 页码: 3976-3988
作者:  Zhou, Shubo;  Hu, Liang;  Wang, Yunlong;  Sun, Zhenan;  Zhang, Kunbo;  Jiang, Xue-Qin
收藏  |  浏览/下载:116/0  |  提交时间:2023/11/17
Light field imaging  super-resolution  depth-varying defocus  dataset  convolutional neural network  
IrisGuideNet: Guided Localization and Segmentation Network for Unconstrained Iris Biometrics 期刊论文
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2023, 卷号: 18, 页码: 2723-2736
作者:  Muhammad, Jawad;  Wang, Caiyong;  Wang, Yunlong;  Zhang, Kunbo;  Sun, Zhenan
收藏  |  浏览/下载:90/0  |  提交时间:2023/11/17
Iris biometrics  iris segmentation  iris localization  heuristics guide  
Polarized Image Translation From Nonpolarized Cameras for Multimodal Face Anti-Spoofing 期刊论文
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2023, 卷号: 18, 页码: 5651-5664
作者:  Tian, Yu;  Huang, Yalin;  Zhang, Kunbo;  Liu, Yue;  Sun, Zhenan
收藏  |  浏览/下载:79/0  |  提交时间:2023/11/16
Face recognition  Faces  Feature extraction  Imaging  Three-dimensional displays  Robustness  Costs  Face antispoofing  image translation  polarization  multimodal  
PyMAF-X: Towards Well-Aligned Full-Body Model Regression From Monocular Images 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 卷号: 45, 期号: 10, 页码: 12287-12303
作者:  Zhang, Hongwen;  Tian, Yating;  Zhang, Yuxiang;  Li, Mengcheng;  An, Liang;  Sun, Zhenan;  Liu, Yebin
收藏  |  浏览/下载:89/0  |  提交时间:2023/11/16
Expressive human mesh recovery  full-body motion capture  mesh alignment feedback  monocular 3D reconstruction  
Pose-Appearance Relational Modeling for Video Action Recognition 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 卷号: 32, 页码: 295-308
作者:  Cui, Mengmeng;  Wang, Wei;  Zhang, Kunbo;  Sun, Zhenan;  Wang, Liang
收藏  |  浏览/下载:272/0  |  提交时间:2023/02/22
Action recognition  2D pose-appearance  relational modeling  temporal attention LSTM  
CASIA-Face-Africa: A Large-Scale African Face Image Database 期刊论文
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2021, 卷号: 16, 页码: 3634-3646
作者:  Muhammad, Jawad;  Wang, Yunlong;  Wang, Caiyong;  Zhang, Kunbo;  Sun, Zhenan
Adobe PDF(8916Kb)  |  收藏  |  浏览/下载:272/23  |  提交时间:2021/08/15
Face recognition  Image databases  Internet  Cameras  Image recognition  Skin  Face detection  African face recognition  racial bias  face image database  
Learning 3D Human Shape and Pose from Dense Body Parts 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 卷号: 44, 期号: 5, 页码: 2610-2627
作者:  Zhang, Hongwen;  Cao, Jie;  Lu, Guo;  Ouyang, Wanli;  Sun, Zhenan
Adobe PDF(4759Kb)  |  收藏  |  浏览/下载:215/54  |  提交时间:2021/06/16
3D human shape and pose estimation  decompose-and-aggregate network  position-aided rotation feature refinement  part-based dropout  
Towards High Fidelity Face Frontalization in the Wild 期刊论文
International Journal of Computer Vision, 2019, 卷号: 128, 期号: 1, 页码: 1485–1504
作者:  Cao, Jie;  Hu, Yibo;  Zhang, Hongwen;  He, Ran;  Sun, Zhenan
Adobe PDF(3816Kb)  |  收藏  |  浏览/下载:164/47  |  提交时间:2021/05/26
Face frontalization  Realistic face generation  Pose-invariant face recognition