CASIA OpenIR
(本次检索基于用户作品认领结果)

浏览/检索结果: 共6条,第1-6条 帮助

限定条件            
已选(0)清除 条数/页:   排序方式:
Hierarchical Memory Modelling for Video Captioning 会议论文
, Seoul, Republic of Korea, 2018-10
作者:  Wang, Junbo;  Wang, Wei;  Huang, Yan;  Wang, Liang;  Tan, Tieniu
浏览  |  Adobe PDF(3565Kb)  |  收藏  |  浏览/下载:268/96  |  提交时间:2020/01/07
M3: Multimodal Memory Modelling for Video Captioning 会议论文
, Salt Lake City, USA, 2018-6
作者:  Wang, Junbo;  Wang, Wei;  Huang, Yan;  Wang, Liang;  Tan, Tieniu
浏览  |  Adobe PDF(661Kb)  |  收藏  |  浏览/下载:212/62  |  提交时间:2020/01/07
MV-RNN: A Multi-View Recurrent Neural Network for Sequential Recommendation 期刊论文
IEEE Transactions on Knowledge and Data Engineering (TKDE), 2018, 期号: no, 页码: no
作者:  Qiang Cui;  Shu Wu;  Qiang Liu;  Wen Zhong;  Liang Wang
Adobe PDF(979Kb)  |  收藏  |  浏览/下载:276/41  |  提交时间:2019/05/09
Multi-view  Sequential Recommendation  Recurrent Neural Network  Cold Start  
Beyond Joints: Learning Representations From Primitive Geometries for Skeleton-Based Action Recognition and Detection 期刊论文
IEEE Transactions on Image Processing, 2018, 卷号: 27, 期号: 9, 页码: 4382 - 4394
作者:  Wang Hongsong(王洪松);  Wang Liang(王亮)
Adobe PDF(2429Kb)  |  收藏  |  浏览/下载:342/88  |  提交时间:2018/06/03
Skeleton-based Action Recognition  Geometric Relations  Viewpoint Transformation  Action Detection  
Learning Content and Style: Joint Action Recognition and Person Identification from Human Skeletons 期刊论文
Pattern Recognition, 2018, 期号: 81, 页码: 23-35
作者:  Wang Hongsong(王洪松);  Wang Liang(王亮)
浏览  |  Adobe PDF(1622Kb)  |  收藏  |  浏览/下载:330/113  |  提交时间:2018/06/01
Content And Style  Action Recognition  Person Identification From Motions  Skeleton Transformation  Multi-task Rnn  
Video Super-Resolution via Bidirectional Recurrent Convolutional Networks 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2018, 卷号: 40, 期号: 4, 页码: 1015-1028
作者:  Huang, Yan;  Wang, Wei;  Wang, Liang
浏览  |  Adobe PDF(10250Kb)  |  收藏  |  浏览/下载:777/292  |  提交时间:2017/06/19
Deep Learning  Recurrent Neural Networks  3d Convolution  Video Super-resolution