中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共9条，第1-9条 帮助

限定条件    
已选(0)清除 条数/页：   排序方式：
Table Structure Recognition and Form Parsing by End-to-End Object Detection and Relation Parsing 期刊论文
PATTERN RECOGNITION, 2022, 卷号: 132, 页码: 14
作者:  Li, Xiao-Hui;  Yin, Fei;  Dai, He-Sen;  Liu, Cheng-Lin
收藏  |  浏览/下载：210/0  |  提交时间：2022/11/14
Table detection  Table structure recognition  Template -free form parsing  Graph neural network  End -to -end training  
Train from scratch: Single-stage joint training of speech separation and recognition 期刊论文
COMPUTER SPEECH AND LANGUAGE, 2022, 卷号: 76, 页码: 15
作者:  Shi, Jing;  Chang, Xuankai;  Watanabe, Shinji;  Xu, Bo
收藏  |  浏览/下载：183/0  |  提交时间：2022/07/25
Cocktail party problem  Speech separation  Multi-speaker speech recognition  End-to-end  Joint-training  
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：202/0  |  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  
Gated Recurrent Fusion With Joint Training Framework for Robust End-to-End Speech Recognition 期刊论文
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2021, 期号: 29, 页码: 198-209
作者:  Fan, Cunhang;  Yi, Jiangyan;  Tao, Jianhua;  Tian, Zhengkun;  Liu, Bin;  Wen, Zhengqi
Adobe PDF(2534Kb)  |  收藏  |  浏览/下载：344/47  |  提交时间：2021/03/08
Speech enhancement  Speech recognition  Training  Noise measurement  Logic gates  Acoustic distortion  Task analysis  Gated recurrent fusion  robust end-to-end speech recognition  speech distortion  speech enhancement  speech transformer  
An end-to-end exemplar association for unsupervised person Re-identification 期刊论文
NEURAL NETWORKS, 2020, 卷号: 129, 页码: 43-54
作者:  Wu, Jinlin;  Yang, Yang;  Lei, Zhen;  Wang, Jinqiao;  Li, Stan Z.;  Tiwari, Prayag;  Pandey, Hari Mohan
Adobe PDF(3014Kb)  |  收藏  |  浏览/下载：312/76  |  提交时间：2020/09/07
End-to-end exemplar-based training  Exemplar association  Dynamic selection threshold  
Learning Driving Models From Parallel End-to-End Driving Data Set 期刊论文
PROCEEDINGS OF THE IEEE, 2020, 卷号: 108, 期号: 2, 页码: 262-273
作者:  Chen, Long;  Wang, Qing;  Lu, Xiankai;  Cao, Dongpu;  Wang, Fei-Yue
收藏  |  浏览/下载：200/0  |  提交时间：2020/03/30
Data models  Training  Adaptation models  Task analysis  Reinforcement learning  Decision making  Transforms  Data set  end-to-end driving  parallel driving  
End-to-End Post-Filter for Speech Separation With Deep Attention Fusion Features 期刊论文
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2020, 卷号: 28, 期号: 28, 页码: 1303-1314
作者:  Fan, Cunhang;  Tao, Jianhua;  Liu, Bin;  Yi, Jiangyan;  Wen, Zhengqi;  Liu, Xuefei
Adobe PDF(1344Kb)  |  收藏  |  浏览/下载：260/57  |  提交时间：2020/06/22
Feature extraction  Training  Interference  Speech enhancement  Clustering algorithms  Spectrogram  Speech separation  end-to-end post-filter  deep attention fusion features  deep clustering  permutation invariant training  
Forward-Backward Decoding Sequence for Regularizing End-to-End TTS 期刊论文
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2019, 卷号: 27, 期号: 12, 页码: 2067-2079
作者:  Zheng, Yibin;  Tao, Jianhua;  Wen, Zhengqi;  Yi, Jiangyan
收藏  |  浏览/下载：308/0  |  提交时间：2020/03/30
Decoding  Training  Speech processing  Linguistics  Acoustics  Speech recognition  Forward-backward  regularization  encoder-decoder with attention  end-to-end  joint-training  TTS  
Real-time segmentation of various insulators using generative adversarial networks 期刊论文
IET COMPUTER VISION, 2018, 卷号: 12, 期号: 5, 页码: 596-602
作者:  Chang, Wenkai;  Yang, Guodong;  Yu, Junzhi;  Liang, Zize
Adobe PDF(4584Kb)  |  收藏  |  浏览/下载：375/64  |  提交时间：2019/12/16
image segmentation  insulators  neural nets  power engineering computing  real-time pixel-level segmentation  generative adversarial networks  insulator segmentation algorithm  cluttered background  artificial thresholds  compact end-to-end neural network  visual saliency map  proposed two-stage training  segmentation quality