中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共23条，第1-10条 帮助

限定条件                        
已选(0)清除 条数/页：   排序方式：
Cross-Architecture Knowledge Distillation 会议论文
INTERNATIONAL JOURNAL OF COMPUTER VISION, Macau SAR, China, 2022.12.4-2022.12.8
作者:  Yufan Liu;  Jiajiong Cao;  Bing Li;  Weiming Hu;  Jingting Ding;  Liang Li
Adobe PDF(1020Kb)  |  收藏  |  浏览/下载：133/42  |  提交时间：2023/04/23
Knowledge distillation  Cross architecture  Model compression  Deep learning  
Task-aware adaptive attention learning for few-shot semantic segmentation 期刊论文
NEUROCOMPUTING, 2022, 卷号: 494, 页码: 104-115
作者:  Mao, Binjie;  Wang, Lingfeng;  Xiang, Shiming;  Pan, Chunhong
Adobe PDF(3903Kb)  |  收藏  |  浏览/下载：281/66  |  提交时间：2022/09/19
Few-shot semantic segmentation  Adaptive feature learning  Attention mechanism  Task-aware  
Joint Expression Synthesis and Representation Learning for Facial Expression Recognition 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2022, 卷号: 32, 期号: 3, 页码: 1681-1695
作者:  Zhang, Xi;  Zhang, Feifei;  Xu, Changsheng
收藏  |  浏览/下载：221/0  |  提交时间：2022/06/06
Face recognition  Task analysis  Generative adversarial networks  Image synthesis  Image recognition  Faces  Training  Facial expression recognition  facial image synthesis  generative adversarial network  representation learning  
HENet: Head-Level Ensemble Network for Very High Resolution Remote Sensing Images Semantic Segmentation 期刊论文
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 卷号: 19, 页码: 5
作者:  Cao, Yong;  Huo, Chunlei;  Xu, Nuo;  Zhang, Xin;  Xiang, Shiming;  Pan, Chunhong
收藏  |  浏览/下载：228/0  |  提交时间：2022/06/06
Head  Computational modeling  Semantics  Image segmentation  Feature extraction  Correlation  Mathematical models  Cooperative learning (CL)  ensemble learning  semantic segmentation  
Lifelong CycleGAN for continual multi-task image restoration 期刊论文
PATTERN RECOGNITION LETTERS, 2022, 卷号: 153, 页码: 183-189
作者:  Li, Yuping;  Nie, Xiangli;  Diao, Wenhui;  Zheng, Suiwu
收藏  |  浏览/下载：196/0  |  提交时间：2022/02/16
Image restoration  Lifelong  continual learning  CycleGAN  Knowledge distillation  
Weakly-Supervised Facial Expression Recognition in the Wild With Noisy Data 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2022, 卷号: 24, 页码: 1800-1814
作者:  Zhang, Feifei;  Xu, Mingliang;  Xu, Changsheng
收藏  |  浏览/下载：232/0  |  提交时间：2022/06/10
Noise measurement  Face recognition  Data models  Task analysis  Training data  Training  Annotations  Facial expression recognition  noisy labeled data  clean labels  end-to-end  pose modeling  noise modeling  
Image Inpainting With Local and Global Refinement 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 卷号: 31, 页码: 2405-2420
作者:  Quan, Weize;  Zhang, Ruisong;  Zhang, Yong;  Li, Zhifeng;  Wang, Jue;  Yan, Dong-Ming
收藏  |  浏览/下载：301/0  |  提交时间：2022/06/06
Image reconstruction  Generators  Convolution  Semantics  Image edge detection  Deep learning  Task analysis  Image inpainting  neural networks  receptive field  
Classifying Clear Air Echoes via Static and Motion Streams Network 期刊论文
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 卷号: 19, 页码: 5
作者:  Qu, Yuxun;  Zhang, Chenyang;  Yang, Xuebing;  Wu, Yajing;  Zhang, Wensheng;  Zhang, Guoping
Adobe PDF(2306Kb)  |  收藏  |  浏览/下载：290/44  |  提交时间：2022/01/27
Radar  Radar imaging  Atmospheric modeling  Training  Streaming media  Image segmentation  Image sequences  Classification of nonprecipitation echoes  clear air echoes  feature fusion  radar image segmentation  
Human Parsing With Part-Aware Relation Modeling 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2022, 卷号: 25, 页码: 2601-2612
作者:  Zhang, Xiaomei;  Chen, Yingying;  Tang, Ming;  Wang, Jinqiao;  Zhu, Xiangyu;  Lei, Zhen
Adobe PDF(6053Kb)  |  收藏  |  浏览/下载：111/8  |  提交时间：2023/11/17
Human parsing  modeling  part-aware relation  
Learning to Model Relationships for Zero-Shot Video Classification 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021, 卷号: 43, 期号: 10, 页码: 3476-3491
作者:  Gao, Junyu;  Zhang, Tianzhu;  Xu, Changsheng
收藏  |  浏览/下载：249/0  |  提交时间：2021/11/04
Zero-shot video classification  graph neural networks  zero-shot learning  deep attention model