CASIA OpenIR

Browse/Search Results:  1-10 of 89 Help

  Show only claimed items
Selected(0)Clear Items/Page:    Sort:
Cross-Modality Paired-Images Generation and Augmentation for RGB-Infrared Person Re-Identification 期刊论文
Neural Networks, 2020, 期号: 128, 页码: 294-304
Authors:  Guan'an Wangang;  Yang Yang;  Tianzhu Zhang;  Jian Cheng;  Zengguang Hou;  Prayag Tiwari;  Hari Mohan Pandey
Favorite  |  View/Download:5/0  |  Submit date:2020/10/27
Person re-identification  Cross-modality  Feature disentanglement  Image generation  Adversarial learning  
SMART: Joint Sampling and Regression for Visual Tracking 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 卷号: 28, 期号: 8, 页码: 3923-3935
Authors:  Gao, Junyu;  Zhang, Tianzhu;  Xu, Changsheng
View  |  Adobe PDF(9244Kb)  |  Favorite  |  View/Download:57/1  |  Submit date:2019/09/30
Visual tracking  deep learning  sampling and regression  
Video Highlight Detection via Region-Based Deep Ranking Model 期刊论文
INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 2019, 卷号: 33, 期号: 7, 页码: 14
Authors:  Jiao, Yifan;  Zhang, Tianzhu;  Huang, Shucheng;  Liu, Bin;  Xu, Changsheng
Favorite  |  View/Download:51/0  |  Submit date:2019/09/30
Video highlight detection  position-sensitive  fully convolutional network  
Graph Convolutional Tracking 会议论文
, Long Beach, USA, 2019-6
Authors:  Gao, Junyu;  Zhang, Tianzhu;  Xu, Changsheng
View  |  Adobe PDF(1645Kb)  |  Favorite  |  View/Download:21/2  |  Submit date:2020/06/11
I Know the Relationships: Zero-Shot Action Recognition via Two-Stream Graph Convolutional Networks and Knowledge Graphs 会议论文
, Hawaii, USA, 2019-1
Authors:  Gao, Junyu;  Zhang, Tianzhu;  Xu, Changsheng
View  |  Adobe PDF(742Kb)  |  Favorite  |  View/Download:18/3  |  Submit date:2020/06/11
Watch, Think and Attend: End-to-End Video Classification via Dynamic Knowledge Evolution Modeling 会议论文
, Seoul, Korea, 2018-10
Authors:  Gao, Junyu;  Zhang, Tianzhu;  Xu, Changsheng
View  |  Adobe PDF(3416Kb)  |  Favorite  |  View/Download:15/4  |  Submit date:2020/06/11
Three-Dimensional Attention-Based Deep Ranking Model for Video Highlight Detection 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2018, 卷号: 20, 期号: 10, 页码: 2693-2705
Authors:  Jiao,Yifan;  Li,Zhetao;  Huang,Shucheng;  Yang,Xiaoshan;  Liu,Bin;  Zhang,Tianzhu
View  |  Adobe PDF(4692Kb)  |  Favorite  |  View/Download:228/99  |  Submit date:2018/10/10
Video Highlight Detection  Attention Model  Deep Ranking  
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:221/50  |  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
Favorite  |  View/Download:34/0  |  Submit date:2019/12/16
Event analysis  unusual event detection  deep learning  
Cross-Domain Collaborative Learning via Discriminative Nonparametric Bayesian Model 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2018, 卷号: 20, 期号: 8, 页码: 2086-2099
Authors:  Qian, Shengsheng;  Zhang, Tianzhu;  Xu, Changsheng
Favorite  |  View/Download:35/0  |  Submit date:2019/12/16
Social media  discriminative non-parametric Bayesian model  multi-modality