Open AccessA research of action recognition based on attention mechanism
Author(s) -
Ruoxi Zhang,
jianan she,
Li Yu
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1966/1/012003
Subject(s) - softmax function , computer science , action recognition , artificial intelligence , residual , pattern recognition (psychology) , feature (linguistics) , mechanism (biology) , action (physics) , feature extraction , machine learning , artificial neural network , class (philosophy) , algorithm , linguistics , philosophy , physics , epistemology , quantum mechanics
To solve the problem of inadequate expression of action behavior features, this paper proposes an action recognition method based on attention mechanism. Firstly, in the feature extraction part, a CSE module is designed to model action features spatio-temporally, and then this module is incorporated into the residual network to improve the feature extraction ability of the model; after that, the LSTM network is used to solve the problem of temporal association of features; finally, the actions are classified by Softmax. The experimental results show that the improved recognition rates of this method on UCF101, HMDB51 and Kinetics400 datasets are 96.23%, 92.03% and 75.65%, respectively.