中文版 | English

在结果中检索

CASIA OpenIR

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：
Hybrid Tree Guided PatchMatch and Quantizing Acceleration for Multiple Views Disparity Estimation 期刊论文
中国体视学与图像分析, 2021, 卷号: 26, 期号: 1, 页码: 47-61
作者:  Jiguang,Zhang;  Shibiao,Xu;  Xiaopeng,Zhang
Adobe PDF(1711Kb)  |  收藏  |  浏览/下载：144/21  |  提交时间：2022/04/07
stereo matching  multiple views  disparity estimation  hybrid tree  patch match  
Geometric Rectification of Document Images using Adversarial Gated Unwarping Network 期刊论文
Pattern Recognition, 2020, 卷号: 108, 期号: 108, 页码: 1-13
作者:  Xiyan Liu;  Gaofeng MENG;  Bin FAN;  Shiming Xiang;  Chunhong PAN
浏览  |  Adobe PDF(7916Kb)  |  收藏  |  浏览/下载：257/86  |  提交时间：2020/10/20
Distorted document image  Geometric rectification  Gated module  Deep learning  
Blind image quality assessment via learnable attention-based pooling 期刊论文
PATTERN RECOGNITION, 2019, 卷号: 91, 页码: 332-344
作者:  Gu, Jie;  Meng, Gaofeng;  Xiang, Shiming;  Pan, Chunhong
浏览  |  Adobe PDF(3081Kb)  |  收藏  |  浏览/下载：488/184  |  提交时间：2019/05/15
Image quality assessment  Perceptual image quality  Visual attention  Convolutional neural network  Learnable pooling  
Automatic Building Rooftop Extraction From Aerial Images via Hierarchical RGB-D Priors 期刊论文
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2018, 卷号: 56, 期号: 12, 页码: 7369-7387
作者:  Xu, Shibiao;  Pan, Xingjia;  Li, Er;  Wu, Baoyuan;  Bu, Shuhui;  Dong, Weiming;  Xiang, Shiming;  Zhang, Xiaopeng
浏览  |  Adobe PDF(30927Kb)  |  收藏  |  浏览/下载：408/35  |  提交时间：2019/07/12
High-order conditional random field (CRF)  multilevel segmentation  RGB-D priors  rooftop extraction  
Semantic labeling in very high resolution images via a self-cascaded convolutional neural network 期刊论文
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2018, 卷号: 145, 期号: 1, 页码: 78-95
作者:  Liu, Yongcheng;  Fan, Bin;  Wang, Lingfeng;  Bai, Jun;  Xiang, Shiming;  Pan, Chunhong
浏览  |  Adobe PDF(1679Kb)  |  收藏  |  浏览/下载：466/96  |  提交时间：2019/01/08
Semantic labeling  Convolutional neural networks (CNNs)  Multi-scale contexts  End-to-end