CASIA OpenIR

Browse/Search Results:  1-10 of 15 Help

Filters    
Selected(0)Clear Items/Page:    Sort:
Improving visual question answering using dropout and enhanced question encoder 期刊论文
PATTERN RECOGNITION, 2019, 卷号: 90, 期号: 1, 页码: 404-414
Authors:  Fang, Zhiwei;  Liu, Jing;  Li, Yong;  Qiao, Yanyuan;  Lu, Hanqing
View  |  Adobe PDF(1624Kb)  |  Favorite  |  View/Download:58/12  |  Submit date:2019/04/23
Visual question answering  Coherent dropout  Siamese dropout  Enhanced question encoder  
Articulated motion and deformable objects 期刊论文
PATTERN RECOGNITION, 2018, 卷号: 79, 期号: 1, 页码: 55-64
Authors:  Wan, Jun;  Escalera, Sergio;  Perales, Francisco J.;  Kittler, Josef
View  |  Adobe PDF(500Kb)  |  Favorite  |  View/Download:55/17  |  Submit date:2018/10/08
Articulated Motion And Deformable Objects  Pose Estimation  Action Recognition  Gesture Recognition  Face Analysis  
Accurate and efficient ground-to-aerial model alignment 期刊论文
PATTERN RECOGNITION, 2018, 卷号: 76, 期号: 76, 页码: 288-302
Authors:  Gao, Xiang;  Hu, Lihua;  Cui, Hainan;  Shen, Shuhan;  Hu, Zhanyi
View  |  Adobe PDF(6450Kb)  |  Favorite  |  View/Download:121/54  |  Submit date:2018/10/09
Image Based Modeling  Ground-to-aerial Model Alignment  Ground-to-aerial Image Matching  
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
Authors:  Shi, Cunzhao;  Wang, Yanna;  Jia, Fuxi;  He, Kun;  Wang, Chunheng;  Xiao, Baihua
View  |  Adobe PDF(2285Kb)  |  Favorite  |  View/Download:108/37  |  Submit date:2018/01/02
Character Representation  Character Recognition  Fisher Vector (Fv)  Gaussian Mixture Models (Gmm)  Bag Of Visual Words (Bow)  
D2C: Deep cumulatively and comparatively learning for human age estimation 期刊论文
PATTERN RECOGNITION, 2017, 卷号: 66, 期号: 0, 页码: 95-105
Authors:  Li, Kai;  Xing, Junliang;  Hu, Weiming;  Maybank, Stephen J.
View  |  Adobe PDF(1176Kb)  |  Favorite  |  View/Download:142/42  |  Submit date:2017/07/18
Age Estimation  Deep Learning  Convolutional Neural Network  
Hierarchically Supervised Deconvolutional Network for Semantic Video Segmentation 期刊论文
PATTERN RECOGNITION, 2017, 卷号: 64, 期号: 1, 页码: 437-445
Authors:  Wang, Yuhang;  Liu, Jing;  Li, Yong;  Fu, Jun;  Xu, Min;  Lu, Hanqing;  Jing Liu
View  |  Adobe PDF(1470Kb)  |  Favorite  |  View/Download:216/112  |  Submit date:2017/02/20
Semantic Video Segmentation  Deconvolutional Neural Network  Coarse-to-fine Training  Spatio-temporal Consistence  
A Coupled Hidden Markov Random Field model for simultaneous face clustering and tracking in videos 期刊论文
PATTERN RECOGNITION, 2017, 卷号: 64, 期号: 2, 页码: 361-373
Authors:  Wu, Baoyuan;  Hu, Bao-Gang;  Ji, Qiang
View  |  Adobe PDF(733Kb)  |  Favorite  |  View/Download:81/17  |  Submit date:2017/05/05
Face Clustering  Face Tracking  Coupled Hidden Markov Random Field  
Multi-crop Convolutional Neural Networks for lung nodule malignancy suspiciousness classification 期刊论文
PATTERN RECOGNITION, 2017, 卷号: 61, 期号: 61, 页码: 663-673
Authors:  Shen, Wei;  Zhou, Mu;  Yang, Feng;  Yu, Dongdong;  Dong, Di;  Yang, Caiyun;  Zang, Yali;  Tian, Jie;  Feng Yang, Jie Tian
View  |  Adobe PDF(1358Kb)  |  Favorite  |  View/Download:471/258  |  Submit date:2016/10/21
Lung Nodule  Malignancy Suspiciousness  Convolutional Neural Network  Multi-crop Pooling  
Multi-label learning with missing labels for image annotation and facial action unit recognition 期刊论文
PATTERN RECOGNITION, 2015, 卷号: 48, 期号: 7, 页码: 2279-2289
Authors:  Wu, Baoyuan;  Lyu, Siwei;  Hu, Bao-Gang;  Ji, Qiang
View  |  Adobe PDF(706Kb)  |  Favorite  |  View/Download:126/54  |  Submit date:2015/09/21
Multi-label Learning  Missing Labels  Image Annotation  Facial Action Unit Recognition  
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
Authors:  Shi, Cunzhao;  Wang, Chunheng;  Xiao, Baihua;  Gao, Song;  Hu, Jinlong;  Wang Chunheng
View  |  Adobe PDF(14024Kb)  |  Favorite  |  View/Download:111/22  |  Submit date:2015/08/12
End-to-end  Scene Text Recognition  Part-based Tree-structured Models (Tsms)  Normalized Pictorial Structure