CASIA OpenIR

Browse/Search Results:  1-6 of 6 Help

  Show only claimed items
Selected(0)Clear Items/Page:    Sort:
基于深度学习的视听多模态融合及生成方法研究 学位论文
, 中国科学院自动化研究所: 中国科学院自动化研究所, 2019
Authors:  郝王丽
Adobe PDF(10215Kb)  |  Favorite  |  View/Download:48/4  |  Submit date:2019/06/18
多模态感知,模态补足,视听融合,视听生成  
Spatiotemporal Distilled Dense-Connectivity Network for Video Action Recognition 期刊论文
Pattern Recognition, 2019, 卷号: 10, 期号: 20, 页码: 100-130
Authors:  Wangli Hao;  Zhaoxiang Zhang
View  |  Adobe PDF(2496Kb)  |  Favorite  |  View/Download:46/22  |  Submit date:2019/04/19
Two-stream  Action Recognition  Dense-connectivity  Knowledge Distillation  
End-to-End Lifelong Learning: a Framework to Achieve Plasticities of both the Feature and Classifier Constructions 期刊论文
COGNITIVE COMPUTATION, 2018, 卷号: 10, 期号: 2, 页码: 321-333
Authors:  Hao, Wangli;  Fan, Junsong;  Zhang, Zhaoxiang;  Zhu, Guibo
View  |  Adobe PDF(1189Kb)  |  Favorite  |  View/Download:81/18  |  Submit date:2018/02/05
Plasticity  Lifelong Learning  End-to-end  Incremental Pcanet  Incremental Kmeansnet  Incremental Svm  
Integrating both Visual and Audio Cues for Enhanced Video Caption 会议论文
, Hilton New Orleans Riverside, American, 2018.2.1
Authors:  Wangli Hao;  Zhaoxiang Zhang;  He Guan
View  |  Adobe PDF(528Kb)  |  Favorite  |  View/Download:12/2  |  Submit date:2019/06/17
CMCGAN A Uniform Framework for CrossModal VisualAudio Mutual Generation 会议论文
, Hilton New Orleans Riverside, American, 2018.2.1
Authors:  Wangli Hao;  Zhaoxiang Zhang;  He Guan
View  |  Adobe PDF(2675Kb)  |  Favorite  |  View/Download:23/6  |  Submit date:2019/06/17
Incremental PCANet: A Lifelong Learning Framework to Achieve the Plasticity of both Feature and Classifier Constructions 会议论文
, 北京, 2017.5
Authors:  Wangli Hao;  Zhaoxiang Zhang
View  |  Adobe PDF(933Kb)  |  Favorite  |  View/Download:15/0  |  Submit date:2019/06/17