CASIA OpenIR

浏览/检索结果: 共6条,第1-6条 帮助

限定条件                
已选(0)清除 条数/页:   排序方式:
Inductive Zero-Shot Image Annotation via Embedding Graph 期刊论文
IEEE ACCESS, 2019, 卷号: 7, 页码: 107816-107830
作者:  Wang, Fangxin;  Liu, Jie;  Zhang, Shuwu;  Zhang, Guixuan;  Li, Yuejun;  Yuan, Fei
浏览  |  Adobe PDF(1472Kb)  |  收藏  |  浏览/下载:321/81  |  提交时间:2019/10/08
Contextualized word embeddings  graph convolutional network  image annotation  Node2Vec  zero-shot  
Recurrent Neural Network Based Small-footprint Wake-up-word Speech Recognition System with a Score Calibration Method 会议论文
, Beijing, 2018-8
作者:  Li, Chenxing;  Zhu, Lei;  Xu, Shuang;  Gao, Peng;  Xu, Bo
浏览  |  Adobe PDF(4877Kb)  |  收藏  |  浏览/下载:163/60  |  提交时间:2020/07/20
Compression of Acoustic Model via Knowledge Distillation and Pruning 会议论文
, Beijing, 2018-8
作者:  Li, Chenxing;  Zhu, Lei;  Xu, Shuang;  Gao, Peng;  Xu, Bo
浏览  |  Adobe PDF(237Kb)  |  收藏  |  浏览/下载:187/71  |  提交时间:2020/07/20
Cbldnn-based Speaker-independent Speech Separation Via Generative Adversarial Training 会议论文
, Calgary, 2020-4
作者:  Li, Chenxing;  Zhu, Lei;  Xu, Shuang;  Gao, Peng;  Xu, Bo
浏览  |  Adobe PDF(791Kb)  |  收藏  |  浏览/下载:194/64  |  提交时间:2020/07/21
INDIVIDUALIZED MATCHING BASED ON LOGO DENSITY FOR SCALABLE LOGO RECOGNITION 会议论文
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), null, 2014
作者:  Zhang, Yuan;  Zhang, Shuwu;  Liang, Wei;  Guo, Qinzhen
浏览  |  Adobe PDF(544Kb)  |  收藏  |  浏览/下载:415/91  |  提交时间:2015/08/19
An integrated segmentation and recognition algorithm for text in video 期刊论文
Zidonghua Xuebao/Acta Automatica Sinica, 2010, 卷号: 36, 期号: 10, 页码: 1468-1476
作者:  Yang, Wu-Yi;  Zhang, Shu-Wu
浏览  |  Adobe PDF(1547Kb)  |  收藏  |  浏览/下载:195/51  |  提交时间:2015/08/12
Null