CASIA OpenIR
(Note: the search results are based on claimed items)

Browse/Search Results:  1-10 of 77 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:85/28  |  Submit date:2019/04/23
Visual question answering  Coherent dropout  Siamese dropout  Enhanced question encoder  
EgoGesture: A New Dataset and Benchmark for Egocentric Hand Gesture Recognition 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2018, 卷号: 20, 期号: 5, 页码: 1038-1050
Authors:  Zhang, Yifan;  Cao, Congqi;  Cheng, Jian;  Lu, Hanqing
View  |  Adobe PDF(1260Kb)  |  Favorite  |  View/Download:169/65  |  Submit date:2018/05/05
Benchmark  Dataset  Egocentric Vision  Gesture Recognition  First-person View  
Body Joint Guided 3-D Deep Convolutional Descriptors for Action Recognition 期刊论文
IEEE TRANSACTIONS ON CYBERNETICS, 2018, 卷号: 48, 期号: 3, 页码: 1095-1108
Authors:  Cao, Congqi;  Zhang, Yifan;  Zhang, Chunjie;  Lu, Hanqing
View  |  Adobe PDF(1731Kb)  |  Favorite  |  View/Download:99/5  |  Submit date:2018/02/02
Action Recognition  Body Joints  Convolutional Networks  Feature Pooling  Two-stream Bilinear Model  
Automatic group activity annotation for mobile videos 期刊论文
MULTIMEDIA SYSTEMS, 2017, 卷号: 23, 期号: 6, 页码: 667-677
Authors:  Zhao, Chaoyang;  Wang, Jinqiao;  Li, Jianqiang;  Lu, Hanqing
View  |  Adobe PDF(1533Kb)  |  Favorite  |  View/Download:101/27  |  Submit date:2018/01/07
Activity Annotation  Group Activity  Context Learning  
Egocentric Gesture Recognition Using Recurrent 3D Convolutional Neural Networks with Spatiotemporal Transformer Modules 会议论文
, Venice, Italy, 22-29 Oct. 2017
Authors:  Cao, Congqi;  Zhang, Yifan;  Wu, Yi;  Lu, Hanqing;  Cheng, Jian
View  |  Adobe PDF(702Kb)  |  Favorite  |  View/Download:96/13  |  Submit date:2018/05/05
Cross-media analysis and reasoning: advances and directions 期刊论文
FRONTIERS OF INFORMATION TECHNOLOGY & ELECTRONIC ENGINEERING, 2017, 卷号: 18, 期号: 1, 页码: 44-57
Authors:  Peng, Yu-xin;  Zhu, Wen-wu;  Zhao, Yao;  Xu, Chang-sheng;  Huang, Qing-ming;  Lu, Han-qing;  Zheng, Qing-hua;  Huang, Tie-jun;  Gao, Wen
Adobe PDF(981Kb)  |  Favorite  |  View/Download:152/57  |  Submit date:2017/05/05
Cross-media Analysis  Cross-media Reasoning  Cross-media Applications  
Egocentric Gesture Recognition Using Recurrent 3D Convolutional Neural Networks with Spatiotemporal Transformer Modules 会议论文
, Venice,Italy, 2017.10.22-10.29
Authors:  Cao,Congqi;  Zhang, Yifan;  Wu, Yi;  Lu, Hanqing;  Cheng, Jian
View  |  Adobe PDF(1370Kb)  |  Favorite  |  View/Download:83/12  |  Submit date:2018/01/07
A Coupled Hidden Conditional Random Field Model for Simultaneous Face Clustering and Naming in Videos 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2016, 卷号: 25, 期号: 12, 页码: 5780-5792
Authors:  Zhang, Yifan;  Tang, Zhiqiang;  Wu, Baoyuan;  Ji, Qiang;  Lu, Hanqing
Adobe PDF(3012Kb)  |  Favorite  |  View/Download:82/10  |  Submit date:2017/02/14
Face Clustering  Face Naming  Conditional Random Field  
Clustering based ensemble correlation tracking 期刊论文
COMPUTER VISION AND IMAGE UNDERSTANDING, 2016, 卷号: 153, 期号: 1, 页码: 55-63
Authors:  Zhu, Guibo;  Wang, Jinqiao;  Lu, Hanqing
View  |  Adobe PDF(235Kb)  |  Favorite  |  View/Download:130/31  |  Submit date:2016/06/27
Object Tracking  Sequential Clustering  Correlation Filter  
Real-time people counting for indoor scenes 期刊论文
SIGNAL PROCESSING, 2016, 卷号: 124, 期号: 无, 页码: 27-35
Authors:  Luo, Jun;  Wang, Jinqiao;  Xu, Huazhong;  Lu, Hanqing
View  |  Adobe PDF(1767Kb)  |  Favorite  |  View/Download:168/62  |  Submit date:2016/04/13
People Counting  Head-shoulder Matching  K-means Clustering