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

Browse/Search Results:  1-10 of 19 Help

Filters            
Selected(0)Clear Items/Page:    Sort:
Text2Video: An End-to-end Learning Framework for Expressing Text With Videos 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2018, 卷号: 20, 期号: 9, 页码: 2360-2370
Authors:  Yang, Xiaoshan;  Zhang, Tianzhu;  Xu, Changsheng
View  |  Adobe PDF(2281Kb)  |  Favorite  |  View/Download:128/26  |  Submit date:2018/02/07
Multimedia Storytelling  Video Analysis  Deep Learning  
Deep Structured Event Modeling for User-Generated Photos 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2018, 卷号: 20, 期号: 8, 页码: 2100-2113
Authors:  Yang, Xiaoshan;  Zhang, Tianzhu;  Xu, Changsheng
View  |  Adobe PDF(1164Kb)  |  Favorite  |  View/Download:95/13  |  Submit date:2018/01/03
Event Analysis  Unusual Event Detection  Deep Learning  
Online Multimodal Multiexpert Learning for Social Event Tracking 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2018, 卷号: 20, 期号: 10, 页码: 2733-2748
Authors:  Shengsheng Qian;  Tianzhu Zhang;  Changsheng Xu
View  |  Adobe PDF(4742Kb)  |  Favorite  |  View/Download:11/1  |  Submit date:2019/09/25
Social Event Tracking  Topic Model  Social Media  Topic Evolution  Multimodality  
Discriminative Multimodal Embedding for Event Classication 期刊论文
Journal of Nerual Computing, 2017, 卷号: Volume, 期号: Issue, 页码: pp
Authors:  Qi,Fan;  Yang,Xiaoshan;  Zhang,Tianzhu;  Xu,Changsheng
View  |  Adobe PDF(4696Kb)  |  Favorite  |  View/Download:66/22  |  Submit date:2018/10/10
Event Classi cation  Multimodal Embedding  
A Unified Personalized Video Recommendation via Dynamic Recurrent Neural Networks 会议论文
, Mountain View, CA, USA, 2017-10-23
Authors:  Gao, Junyu;  Zhang, Tianzhu;  Xu, Changsheng
View  |  Adobe PDF(2043Kb)  |  Favorite  |  View/Download:223/140  |  Submit date:2017/12/29
Video Highlight Detection via Deep Ranking Modeling 会议论文
, 武汉, 2017-10
Authors:  Jiao,Yifan;  Yang,Xiaoshan;  Zhang,Tianzhu;  Huang,Shucheng;  Xu,Changsheng
View  |  Adobe PDF(1063Kb)  |  Favorite  |  View/Download:65/13  |  Submit date:2018/02/28
Robust Visual Tracking via Exclusive Context Modeling 期刊论文
IEEE TRANSACTIONS ON CYBERNETICS, 2016, 卷号: 46, 期号: 1, 页码: 51-63
Authors:  Zhang, Tianzhu;  Ghanem, Bernard;  Liu, Si;  Xu, Changsheng;  Ahuja, Narendra
View  |  Adobe PDF(1451Kb)  |  Favorite  |  View/Download:92/4  |  Submit date:2016/03/19
Contextual Information  Exclusive Sparse Learning  Particle Filter  Tracking  
The Visual Object Tracking VOT2016 Challenge Results 会议论文
, Amsterdam, Netherlands, 2016-10
Authors:  Matej Kristan;  Ales Leonardis;  Jiri Matas;  Gao, Junyu;  Zhang, Tianzhu;  Xu, Changsheng
View  |  Adobe PDF(2757Kb)  |  Favorite  |  View/Download:62/20  |  Submit date:2018/02/07
Multi-object tracking via MHT with multiple information fusion in surveillance video 期刊论文
MULTIMEDIA SYSTEMS, 2015, 卷号: 21, 期号: 3, 页码: 313-326
Authors:  Ying, Long;  Zhang, Tianzhu;  Xu, Changsheng
View  |  Adobe PDF(7822Kb)  |  Favorite  |  View/Download:65/11  |  Submit date:2015/09/17
Multi-object Tracking  Data Association  Mht  Multiple Information Fusion  
Latent Support Vector Machine Modeling for Sign Language Recognition with Kinect 期刊论文
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY, 2015, 卷号: 6, 期号: 2
Authors:  Sun, Chao;  Zhang, Tianzhu;  Xu, Changsheng
Adobe PDF(1484Kb)  |  Favorite  |  View/Download:61/10  |  Submit date:2015/09/21
Algorithms  Experimentation  Performance  Sign Language Recognition  Kinect Sensor  Latent Svm