CASIA OpenIR
(本次检索基于用户作品认领结果)

浏览/检索结果: 共48条,第1-10条 帮助

限定条件                            
已选(0)清除 条数/页:   排序方式:
Regularized Graph Structure Learning with Semantic Knowledge for Multi-variates Time-Series Forecasting 会议论文
, 维也纳, 2022
作者:  Yu HY(俞宏远);  Li, Ting;  Yu WC(余玮宸);  Li, Jianguo;  Huang Y(黄岩);  Wang L(王亮);  Liu, Alex
Adobe PDF(4154Kb)  |  收藏  |  浏览/下载:275/98  |  提交时间:2022/06/14
Joint Token and Feature Alignment Framework for Text-Based Person Search 期刊论文
IEEE SIGNAL PROCESSING LETTERS, 2022, 卷号: 29, 页码: 2238-2242
作者:  Li, Shangze;  Lu, Andong;  Huang, Yan;  Li, Chenglong;  Wang, Liang
收藏  |  浏览/下载:172/0  |  提交时间:2022/12/27
Feature extraction  Visualization  Representation learning  Logic gates  Image reconstruction  Transformers  Training  Cross-modal generation  feature alignment  text-based person search  token alignment  transformer  
Cyclic Differentiable Architecture Search 期刊论文
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 卷号: 2022, 期号: TPAMI.2022.3153065, 页码: DOI 10.1109
作者:  Yu HY(俞宏远);  Peng HW(彭厚文);  Huang Y(黄岩);  Fu JL(傅建龙);  Du, Hao;  Wang L(王亮);  Lin, Haibin
Adobe PDF(5244Kb)  |  收藏  |  浏览/下载:251/75  |  提交时间:2022/06/14
A Reconstruction-based Visual-Acoustic-Semantic Embedding Method for Speech-Image Retrieval 期刊论文
IEEE Transactions on Multimedia, 2022, 页码: 14
作者:  Cheng, Wenlong;  Tang, Wei;  Huang, Yan;  Luo, Yiwen;  Wang, Liang
Adobe PDF(1628Kb)  |  收藏  |  浏览/下载:236/89  |  提交时间:2022/06/14
Mask-guided contrastive attention and two-stream metric co-learning for person Re-identification 期刊论文
NEUROCOMPUTING, 2021, 卷号: 465, 页码: 561-573
作者:  Song, Chunfeng;  Shan, Caifeng;  Huang, Yan;  Wang, Liang
收藏  |  浏览/下载:215/0  |  提交时间:2021/11/03
Person ReID  Contrastive attention model  Two-stream metric learning  
Learning a Robust Part-Aware Monocular 3D Human Pose Estimator via Neural Architecture Search 期刊论文
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2021, 页码: 20
作者:  Chen, Zerui;  Huang, Yan;  Yu, Hongyuan;  Wang, Liang
收藏  |  浏览/下载:192/0  |  提交时间:2021/12/28
Monocular 3D human pose estimation  Heterogeneous human body parts  Neural architecture search  
End -to -end video text detection with online tracking 期刊论文
PATTERN RECOGNITION, 2021, 卷号: 113, 页码: 12
作者:  Yu, Hongyuan;  Huang, Yan;  Pi, Lihong;  Zhang, Chengquan;  Li, Xuan;  Wang, Liang
Adobe PDF(4997Kb)  |  收藏  |  浏览/下载:308/57  |  提交时间:2021/05/06
End-to-end  Video text detection  Online tracking  
On the Robustness of 3D Human Pose Estimation 会议论文
, Online, 2021.1.10-2021.1.15
作者:  Chen, Zerui;  Huang, Yan;  Wang, Liang
Adobe PDF(3841Kb)  |  收藏  |  浏览/下载:154/44  |  提交时间:2021/06/03
Attribute Prototype Learning for Interactive Face Retrieval 期刊论文
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2021, 卷号: 16, 页码: 2593-2607
作者:  Fang, Yuchun;  Xiao, Zhengye;  Zhang, Wei;  Huang, Yan;  Wang, Liang;  Boujemaa, Nozha;  Geman, Donald
收藏  |  浏览/下载:159/0  |  提交时间:2021/04/27
Prototypes  Faces  Face recognition  Databases  Adaptation models  Coherence  Semantics  Facial attribute  prototype learning  interactive retrieval  
PokerNet: Expanding Features Cheaply via Depthwise Convolutions 期刊论文
International Journal of Automation and Computing, 2021, 卷号: 18, 期号: 3, 页码: 432-442
作者:  Wei Tang;  Yan Huang;  Liang Wang
Adobe PDF(1163Kb)  |  收藏  |  浏览/下载:217/33  |  提交时间:2021/05/24
Deep learning  depthwise convolution  lightweight deep model  model compression  model acceleration