Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates.

IEEE Transactions on Pattern Analysis and Machine Intelligence(2018)

引用 500|浏览506
暂无评分
摘要
Skeleton-based human action recognition has attracted a lot of research attention during the past few years. Recent works attempted to utilize recurrent neural networks to model the temporal dependencies between the 3D positional configurations of human body joints for better analysis of human activities in the skeletal data. The proposed work extends this idea to spatial domain as well as tempora...
更多
查看译文
关键词
Logic gates,Recurrent neural networks,Spatiotemporal phenomena,Three-dimensional displays,Feature extraction,Hidden Markov models
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要