CASIA OpenIR
(本次检索基于用户作品认领结果)

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:
Modelling Speaker-dependent Auditory Attention Using A Spiking Neural Network with Temporal Coding and Supervised Learning 会议论文
, Sydney, Australia, December 12-15, 2019
作者:  Yating Huang;  Jiaming Xu;  Bo Xu
Adobe PDF(3377Kb)  |  收藏  |  浏览/下载:195/46  |  提交时间:2022/09/17
Adapting translation models for transcript disfluency detection 会议论文
, Hawaii, 2019-2
作者:  Dong QQ(董倩倩);  Feng Wang(王峰);  Zhen Yang(杨振);  Wei Chen(陈炜);  Shuang Xu(徐爽);  Bo Xu(徐波)
Adobe PDF(287Kb)  |  收藏  |  浏览/下载:159/16  |  提交时间:2021/06/24
Text Attention and Focal Negative Loss for Scene Text Detection 会议论文
, Budapest, Hungary., 14-19 July 2019
作者:  Huang Randong;  Xu Bo
Adobe PDF(3570Kb)  |  收藏  |  浏览/下载:184/50  |  提交时间:2021/06/09
Efficient and Accurate Face Shape Reconstruction by Fusion of Multiple Landmark Databases 会议论文
, Taipei, Taiwan, 2019-9-22~2019-9-25
作者:  Wang, Pengrui;  Tian, Yi;  Che, Wujun;  Xu, Bo
Adobe PDF(537Kb)  |  收藏  |  浏览/下载:259/102  |  提交时间:2020/09/11
3D Face Reconstruction  Multi Database Fusion  Face Alignment  Deep Learning  
Self-Attention Aligner: A Latency-Control End-to-End Model for ASR using Self-attention Network and Chunk-hopping 会议论文
, Brighton, United Kingdom, 2019-05
作者:  Dong, Linhao;  Wang, Feng;  Xu, Bo
Adobe PDF(930Kb)  |  收藏  |  浏览/下载:254/44  |  提交时间:2020/06/13
speech recognition  self-attention network  encoder-decoder  end-to-end  latency-control  
NRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognition 会议论文
, Sydney, Australia, 2019-9-20 ~ 2019-9-25
作者:  Sheng, Fenfen;  Chen, Zhineng;  Xu, Bo
Adobe PDF(455Kb)  |  收藏  |  浏览/下载:245/73  |  提交时间:2020/06/12