中文版 | English

在结果中检索

CSpace

浏览/检索结果: 共5条，第1-5条 帮助

限定条件            
已选(0)清除 条数/页：   排序方式：
SkeletonNet: A Hybrid Network With a Skeleton-Embedding Process for Multi-View Image Representation Learning 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2019, 卷号: 21, 期号: 11, 页码: 2916-2929
作者:  Yang, Shijie;  Li, Liang;  Wang, Shuhui;  Zhang, Weigang;  Huang, Qingming;  Tian, Qi
收藏  |  浏览/下载：51/0  |  提交时间：2020/12/10
Semantics  Correlation  Visualization  Skeleton  Matrix decomposition  Kernel  Laplace equations  Unsupervised multi-view subspace learning  semantic inconsistency  tensor factorization  deep auto-encoders  
Exploring Coherent Motion Patterns via Structured Trajectory Learning for Crowd Mood Modeling 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2017, 卷号: 27, 期号: 3, 页码: 635-648
作者:  Zhang, Yanhao;  Qin, Lei;  Ji, Rongrong;  Zhao, Sicheng;  Huang, Qingming;  Luo, Jiebo
收藏  |  浏览/下载：61/0  |  提交时间：2019/12/12
Coherent motion pattern  crowd behavior analysis  emotional motion feature  structured trajectory learning (STL)  
Learning Label-Specific Features and Class-Dependent Labels for Multi-Label Classification 期刊论文
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2016, 卷号: 28, 期号: 12, 页码: 3309-3323
作者:  Huang, Jun;  Li, Guorong;  Huang, Qingming;  Wu, Xindong
收藏  |  浏览/下载：40/0  |  提交时间：2019/12/13
Multi-label classification  label correlation  feature selection  
Effective Multimodality Fusion Framework for Cross-Media Topic Detection 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2016, 卷号: 26, 期号: 3, 页码: 556-569
作者:  Chu, Lingyang;  Zhang, Yanyan;  Li, Guorong;  Wang, Shuhui;  Zhang, Weigang;  Huang, Qingming
收藏  |  浏览/下载：39/0  |  提交时间：2019/12/13
Cross-media  fusion  multimodality  topic detection  topic recovery (TR)  We-Media  
Fusing cross-media for topic detection by dense keyword groups 期刊论文
NEUROCOMPUTING, 2015, 卷号: 169, 页码: 169-179
作者:  Zhang, Weigang;  Chen, Tianlong;  Li, Guorong;  Pang, Junbiao;  Huang, Qingming;  Gao, Wen
收藏  |  浏览/下载：43/0  |  提交时间：2019/12/13
Topic detection  Cross-media  Dense keyword group  Near-duplicate keyframe  Web video