中文版 | English

在结果中检索

CSpace

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：
Asymmetric GAN for Unpaired Image-to-Image Translation 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 卷号: 28, 期号: 12, 页码: 5881-5896
作者:  Li, Yu;  Tang, Sheng;  Zhang, Rui;  Zhang, Yongdong;  Li, Jintao;  Yan, Shuicheng
收藏  |  浏览/下载：262/0  |  提交时间：2019/12/10
Generative adversarial networks  cycle GAN  asymmetric GAN  image-to-image translation  unpaired translation  
Cross-Modality Bridging and Knowledge Transferring for Image Understanding 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2019, 卷号: 21, 期号: 10, 页码: 2675-2685
作者:  Yan, Chenggang;  Li, Liang;  Zhang, Chunjie;  Liu, Bingtao;  Zhang, Yongdong;  Dai, Qionghai
收藏  |  浏览/下载：276/0  |  提交时间：2019/12/10
Object and scene recognition  image semantic search  cross-modality bridging  multi-task learning  knowledge transferring  
Dual-Stream Recurrent Neural Network for Video Captioning 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2019, 卷号: 29, 期号: 8, 页码: 2482-2493
作者:  Xu, Ning;  Liu, An-An;  Wong, Yongkang;  Zhang, Yongdong;  Nie, Weizhi;  Su, Yuting;  Kankanhalli, Mohan
收藏  |  浏览/下载：75/0  |  提交时间：2019/12/10
Video captioning  hidden state fusion  dual stream  recurrent neural network  attention module  
Multi-Domain and Multi-Task Learning for Human Action Recognition 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 卷号: 28, 期号: 2, 页码: 853-867
作者:  Liu, An-An;  Xu, Ning;  Nie, Wei-Zhi;  Su, Yu-Ting;  Zhang, Yong-Dong
收藏  |  浏览/下载：79/0  |  提交时间：2019/04/03
Domain-invariant Learning  multi-task learning  human action recognition  
Detection and tracking based tubelet generation for video object detection 期刊论文
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2019, 卷号: 58, 页码: 102-111
作者:  Wang, Bin;  Tang, Sheng;  Xiao, Jun-Bin;  Yan, Quan-Feng;  Zhang, Yong-Dong
收藏  |  浏览/下载：74/0  |  提交时间：2019/04/03
Object detection  Tubelet generation  Tubelet fusion