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：
XANet: An Efficient Remote Sensing Image Segmentation Model Using Element-Wise Attention Enhancement and Multi-Scale Attention Fusion 期刊论文
REMOTE SENSING, 2023, 卷号: 15, 期号: 1, 页码: 25
作者:  Liang, Chenbin;  Xiao, Baihua;  Cheng, Bo;  Dong, Yunyun
Adobe PDF(63859Kb)  |  收藏  |  浏览/下载：403/25  |  提交时间：2023/02/22
semantic segmentation  attention mechanism  cross-attention  feature fusion  
Different Contexts Lead to Different Word Embeddings 会议论文
Proceedings of COLING 2016: Technical Papers, Osaka, Japan, December 11-17 2016
作者:  Hu WP(胡文鹏);  Zhang JJ(张家俊);  Zheng N(郑楠)
Adobe PDF(159Kb)  |  收藏  |  浏览/下载：39/2  |  提交时间：2020/10/27
无权访问的条目 会议论文
作者:  Riheng Yao;  Qiudan Li;  Lei Wang;  Daniel Zeng
Adobe PDF(362Kb)  |  收藏  |  浏览/下载：38/6  |  提交时间：2019/10/11
Detecting Traffic Information From Social Media Texts With Deep Learning Approaches 期刊论文
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2019, 卷号: 20, 期号: 8, 页码: 3049-3058
作者:  Chen, Yuanyuan;  Lv, Yisheng;  Wang, Xiao;  Li, Lingxi;  Wang, Fei-Yue
浏览  |  Adobe PDF(2273Kb)  |  收藏  |  浏览/下载：450/112  |  提交时间：2019/08/28
Deep learning  social transportation  traffic information detection  social media  text mining  
Multi-order co-occurrence activations encoded with Fisher Vector for scene character recognition 期刊论文
PATTERN RECOGNITION LETTERS, 2017, 卷号: 97, 期号: 2017, 页码: 69-76
作者:  Wang, Yanna;  Shi, Cunzhao;  Wang, Chunheng;  Xiao, Baihua;  Qi, Chengzuo
浏览  |  Adobe PDF(1105Kb)  |  收藏  |  浏览/下载：322/91  |  提交时间：2018/01/03
Scene Character Recognition  Multi-order Co-occurrence Activations  Fisher Vector  Cnn  
Fisher vector for scene character recognition: A comprehensive evaluation 期刊论文
PATTERN RECOGNITION, 2017, 卷号: 72, 期号: 2017, 页码: 1-14
作者:  Shi, Cunzhao;  Wang, Yanna;  Jia, Fuxi;  He, Kun;  Wang, Chunheng;  Xiao, Baihua
浏览  |  Adobe PDF(2285Kb)  |  收藏  |  浏览/下载：405/104  |  提交时间：2018/01/02
Character Representation  Character Recognition  Fisher Vector (Fv)  Gaussian Mixture Models (Gmm)  Bag Of Visual Words (Bow)  
Stroke Detector and Structure Based Models for Character Recognition: A Comparative Study 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2015, 卷号: 24, 期号: 12, 页码: 4952-4964
作者:  Shi, Cun-Zhao;  Gao, Song;  Liu, Meng-Tao;  Qi, Cheng-Zuo;  Wang, Chun-Heng;  Xiao, Bai-Hua;  Shi Cunzhao
浏览  |  Adobe PDF(4543Kb)  |  收藏  |  浏览/下载：459/79  |  提交时间：2015/11/12
Character Recognition  Stroke Detector  Structure  Part-based Model  Tree-structure  Spatiality Embedded Codeword  
Scene text recognition by learning co-occurrence of strokes based on spatiality embedded dictionary 期刊论文
IET COMPUTER VISION, 2015, 卷号: 9, 期号: 1, 页码: 138-148
作者:  Gao, Song;  Wang, Chunheng;  Xiao, Baihua;  Shi, Cunzhao;  Zhou, Wen;  Zhang, Zhong
浏览  |  Adobe PDF(794Kb)  |  收藏  |  浏览/下载：357/88  |  提交时间：2015/09/18
Character Recognition  Dictionaries  Text Detection  Scene Text Recognition  High-level Image Understanding  Text Information  Scene Images  Local Strokes  Spatiality Embedded Dictionary  Sed  Robust Character Recognition  Localised Soft Coding  Max Pooling  Sparse Dictionary  Chars74 k Dataset  Icdar2003 Dataset  
End-to-end scene text recognition using tree-structured models 期刊论文
PATTERN RECOGNITION, 2014, 卷号: 47, 期号: 9, 页码: 2853-2866
作者:  Shi, Cunzhao;  Wang, Chunheng;  Xiao, Baihua;  Gao, Song;  Hu, Jinlong;  Wang Chunheng
浏览  |  Adobe PDF(14024Kb)  |  收藏  |  浏览/下载：358/73  |  提交时间：2015/08/12
End-to-end  Scene Text Recognition  Part-based Tree-structured Models (Tsms)  Normalized Pictorial Structure