CASIA OpenIR

Browse/Search Results:  1-10 of 18 Help

  Show only claimed items
Selected(0)Clear Items/Page:    Sort:
PiCor: Multi-Task Deep Reinforcement Learning with Policy Correction 会议论文
Proceedings of the AAAI Conference on Artificial Intelligence, 美国 华盛顿, 2023.02.07 - 2023.02.14
Authors:  Bai FS(白丰硕);  Zhang HM(张鸿铭);  Tao TY(陶天阳);  Wu ZH(武志亨);  Wang YN(王燕娜);  Xu B(徐博)
Adobe PDF(1663Kb)  |  Favorite  |  View/Download:206/47  |  Submit date:2023/07/05
Reinforcement Learning Algorithms  Transfer  Domain Adaptation  Multi-Task Learning  
Unconstrained end-to-end text reading with feature rectification 期刊论文
PATTERN RECOGNITION LETTERS, 2021, 卷号: 149, 页码: 1-8
Authors:  Du, Chen;  Wang, Yanna;  Wang, Chunheng;  Xiao, Baihua;  Shi, Cunzhao
Adobe PDF(1133Kb)  |  Favorite  |  View/Download:340/71  |  Submit date:2021/11/02
Text recognition  Text detection  Position-sensitive network  Features incompatibility  End-to-end  
An effective binarization method for disturbed camera-captured document images 会议论文
, Niagara Falls,USA, 2018/08/05
Authors:  Zhao JY(赵晋媛);  Shi CZ(史存召);  Jia FX(贾馥溪);  Wang YN(王燕娜);  Xiao BH(肖柏华)
Adobe PDF(579Kb)  |  Favorite  |  View/Download:192/66  |  Submit date:2021/05/26
Adversarial learning based attentional scene text recognizer 期刊论文
PATTERN RECOGNITION LETTERS, 2020, 卷号: 138, 期号: 1, 页码: 217-222
Authors:  Zhao, Jinyuan;  Wang, Yanna;  Xiao, Baihua;  Shi, Cunzhao;  Jiang, Jingzhong;  Wang, Chunheng
Adobe PDF(1152Kb)  |  Favorite  |  View/Download:393/91  |  Submit date:2021/01/07
Scene text recognition  Generative adversarial network  Image rectification  
DetectGAN: GAN-based text detector for camera-captured document images 期刊论文
INTERNATIONAL JOURNAL ON DOCUMENT ANALYSIS AND RECOGNITION, 2020, 卷号: 23, 期号: 4, 页码: 267-277
Authors:  Zhao, Jinyuan;  Wang, Yanna;  Xiao, Baihua;  Shi, Cunzhao;  Jia, Fuxi;  Wang, Chunheng
Adobe PDF(3817Kb)  |  Favorite  |  View/Download:349/62  |  Submit date:2020/09/21
Text detection  Camera-captured document images  Multi-scale context features  Generative adversarial networks  
OSTER: An Orientation Sensitive Scene Text Recognizer with CenterLine Rectification 会议论文
, Auckland, New Zealand, 2019.11.26-2019.11.29
Authors:  Feng, Zipeng;  Du, Chen;  Wang, Yanna;  Xiao, Baihua
View  |  Adobe PDF(1567Kb)  |  Favorite  |  View/Download:236/61  |  Submit date:2020/06/12
Scene text recognition  Arbitrarily-aligned Chinese texts  Attention selective network  Centerline rectification  Sequence-to-sequence  
A Text Localization Method Based on Weak Supervision 会议论文
, Sydney, Australia, Australia, 20-25 Sept. 2019
Authors:  Zhang, Jiyuan;  Du, Chen;  Feng, Zipeng;  Wang, Yanna;  Wang, Chunheng
View  |  Adobe PDF(1179Kb)  |  Favorite  |  View/Download:278/90  |  Submit date:2020/06/11
weak supervision  fully convolutional network  text localization map  
Selective feature connection mechanism: Concatenating multi-layer CNN features with a feature selector 期刊论文
PATTERN RECOGNITION LETTERS, 2020, 卷号: 129, 页码: 108-114
Authors:  Du, Chen;  Wang, Chunheng;  Wang, Yanna;  Shi, Cunzhao;  Xiao, Baihua
Adobe PDF(2583Kb)  |  Favorite  |  View/Download:392/60  |  Submit date:2020/03/30
Feature combination  Network architecture  Selective feature connection mechanism  Convolutional neural network  
Document image binarization with cascaded generators of conditional generative adversarial networks 期刊论文
PATTERN RECOGNITION, 2019, 卷号: 96, 期号: 1, 页码: 12
Authors:  Zhao, Jinyuan;  Shi, Cunzhao;  Jia, Fuxi;  Wang, Yanna;  Xiao, Baihua
Adobe PDF(3892Kb)  |  Favorite  |  View/Download:507/89  |  Submit date:2019/12/16
Cascaded generator  Conditional generative adversarial networks  Document image binarization  Image generation  Historical document analysis  
CRF based text detection for natural scene images using convolutional neural network and context information 期刊论文
NEUROCOMPUTING, 2018, 卷号: 295, 页码: 46-58
Authors:  Wang, Yanna;  Shi, Cunzhao;  Xiao, Baihua;  Wang, Chunheng;  Qi, Chengzuo
Adobe PDF(3736Kb)  |  Favorite  |  View/Download:282/12  |  Submit date:2018/10/10
Scene Text Detection  Mser  Cnn  Crf  Context Information  Shape-specific Classifiers