.png){kind=icon}
返回
View knowledge transfer network for multi-view action recognition
.png){kind=icon}
PRE
AI
DOI：10.1016/j.imavis.2021.104357.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
As many data in practical applications occur or can be captured in multiple views form, multi-view action recognition has received much attention recently, due to utilizing certain complementary and heterogeneous information in various views to promote the downstream task. However, most existing methods assume that multi-view data is complete, which may not always be met in real-world applications.To this end, in this paper, a novel View Knowledge Transfer Network (VKTNet) is proposed to handle multi-view action recognition, even when some views are incomplete. Specifically, the view knowledge transferring is utilized using conditional generative adversarial network(cGAN) to reproduce each view's latent representation, conditioning on the other view's information. As such, the high-level semantic features are effectively extracted to bridge the semantic gap between two different views. In addition, in order to efficiently fuse the decision result achieved by each view, a Siamese Scaling Network(SSN) is proposed instead of simply using a classifier. Experimental results show that our model achieves the superiority performance, on three public datasets, against others when all the views are available. Meanwhile, the degradation of performance is avoided under the case that some views are missing. (c) 2021 Elsevier B.V. All rights reserved.
Keyword:
Action recognition
Deep learning
Multi-view learning
Generative adversarial network
Late fusion
期刊
IF:
4.2
论文数:
4.1K
被引数:
6.7K
机构
引用论文
Economic benefit evaluation method for the micro-grid renewable energy system operation微网可再生能源系统运行经济效益评价方法
PREAI
分享收藏Unified subspace learning for incomplete and unlabeled multi-view data不完整和未标记多视图数据的统一子空间学习.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Mitochondrial Dysfunction Induces Formation of Lipid Droplets as a Generalized Response to Stress
OAAI
OAAI分享收藏Two-dimensional bricklayer arrangements of tolans using halogen bonding interactions使用卤素键相互作用的tolans的二维瓦工层布置
PREAI
分享收藏
查看更多内容