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:
GaitNet: An end-to-end network for gait based human identification 期刊论文
PATTERN RECOGNITION, 2019, 卷号: 96, 期号: 106988, 页码: 11
作者:  Song, Chunfeng;  Huang, Yongzhen;  Huang, Yan;  Jia, Ning;  Wang, Liang
浏览  |  Adobe PDF(3015Kb)  |  收藏  |  浏览/下载:626/164  |  提交时间:2019/12/16
Gait recognition  Video-based human identification  End-to-end CNN  Joint learning  
Adversarial Learning Semantic Volume for 2D/3D Face Shape Regression in the Wild 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 卷号: 28, 期号: 9, 页码: 4526-4540
作者:  Zhang, Hongwen;  Li, Qi;  Sun, Zhenan
Adobe PDF(4865Kb)  |  收藏  |  浏览/下载:334/52  |  提交时间:2019/10/08
2D/3D facial landmark localization  semantic volumetric representation  joint voxel and coordinate regression  auxiliary regression adversarial learning  
Variational Bayesian Learning for Dirichlet Process Mixture of Inverted Dirichlet Distributions in Non-Gaussian Image Feature Modeling 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2019, 卷号: 30, 期号: 2, 页码: 449-463
作者:  Ma, Zhanyu;  Lai, Yuping;  Kleijn, W. Bastiaan;  Song, Yi-Zhe;  Wang, Liang;  Guo, Jun
收藏  |  浏览/下载:352/0  |  提交时间:2019/07/12
Bayesian estimation  computer vision  Dirichlet process (DP) mixture  inverted Dirichlet distribution  variational learning  
Aggregating Randomized Clustering-Promoting Invariant Projections for Domain Adaptation 期刊论文
IEEE Trans. Pattern Anal. Machine Intell., 2019, 卷号: 41, 期号: 5, 页码: 1027-1042
作者:  Jian Liang;  Ran He;  Zhenan Sun;  Tieniu Tan
浏览  |  Adobe PDF(865Kb)  |  收藏  |  浏览/下载:440/146  |  提交时间:2019/06/10
Unsupervised Domain Adaptation  Domain-invariant Projection  Class-clustering  Sampling-and-fusion  
MAPNet: Multi-modal attentive pooling network for RGB-D indoor scene classification 期刊论文
PATTERN RECOGNITION, 2019, 期号: 90, 页码: 436-449
作者:  Li, Yabei;  Zhang, Zhang;  Cheng, Yanhua;  Wang, Liang;  Tan, Tieniu
浏览  |  Adobe PDF(5797Kb)  |  收藏  |  浏览/下载:416/44  |  提交时间:2019/04/23
Indoor scene classification  Multi-modal fusion  RGB-D  Attentive pooling