CASIA OpenIR
(本次检索基于用户作品认领结果)

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:
Adversarial Cross-Spectral Face Completion for NIR-VIS Face Recognition 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2020, 卷号: 42, 期号: 5, 页码: 1024 - 1037
作者:  He, Ran;  Cao, Jie;  Song, Lingxiao;  Sun, Zhenan;  Tan, Tieniu
Adobe PDF(4148Kb)  |  收藏  |  浏览/下载:213/44  |  提交时间:2021/06/16
heterogeneous face recognition  near infrared-visible matching  face completion  face inpainting  
Relational graph neural network for situation recognition 期刊论文
Pattern Recognition, 2020, 期号: 108, 页码: 107544
作者:  Jing Y(荆雅);  Wang JB(王君波);  Wang W(王威);  Wang L(王亮);  Tan TN(谭铁牛)
Adobe PDF(3098Kb)  |  收藏  |  浏览/下载:203/48  |  提交时间:2021/06/07
Situation recognition  Relationship modeling  Graph neural network  Reinforcement learning  
Large-Scale Object Detection in the Wild from Imbalanced Multi-Labels 会议论文
, 美国, 2020
作者:  Peng, Junran;  Bu, Xingyuan;  Sun, Ming;  Zhang, Zhaoxiang;  Tan, Tieniu;  Yan, Junjie
Adobe PDF(4727Kb)  |  收藏  |  浏览/下载:281/46  |  提交时间:2021/01/19
Object detection  Large-scale recognition  Multi-label recognition  
Skeleton-based action recognition with hierarchical spatial reasoning and temporal stack learning network 期刊论文
PATTERN RECOGNITION, 2020, 卷号: 107, 期号: 107511, 页码: 12
作者:  Si, Chenyang;  Jing, Ya;  Wang, Wei;  Wang, Liang;  Tan, Tieniu
Adobe PDF(2378Kb)  |  收藏  |  浏览/下载:390/74  |  提交时间:2020/08/31
Skeleton-based action recognition  Hierarchical spatial reasoning  Temporal stack learning  Clip-based incremental loss  
Deep Unbiased Embedding Transfer for Zero-Shot Learning 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2020, 卷号: 29, 期号: 29, 页码: 1958-1971
作者:  Jia, Zhen;  Zhang, Zhang;  Wang, Liang;  Shan, Caifeng;  Tan, Tieniu
Adobe PDF(3428Kb)  |  收藏  |  浏览/下载:428/72  |  提交时间:2020/03/30
Visualization  Feature extraction  Semantics  Training  Seals  Prototypes  Indexes  Zero-shot learning  image classification  projection domain shift  convolutional neural network  generative adversarial network