Journal of System Simulation
Abstract
Abstract: Aiming at the lack of directionality of traditional dot product attention, this paper proposes a directed attention model (DAM) based on cosine similarity. To effectively represent the direction relationship between the spatial and temporal features of video frames, the paper defines the relationship function in the attention mechanism using the cosine similarity theory, which can remove the absolute value of the relationship between features. To reduce the computational burden of the attention mechanism, the operation is decomposed from two dimensions of time and space. The computational complexity is further optimized by combining linear attention operation. The experiment is divided into two stages : Four ablation experiments are carried out on each module of directed attention to show the best performance of DAM in accuracy and efficiency; the accuracy of the model is 7.3% higher than that of I3D-NL on the Sth-Sth V1(something something V1) dataset and 95.7% on the UCF101(101 human action classes from videos in the wild) dataset. The research results have a wide application prospect in safety monitoring, automatic driving, and so on.
Recommended Citation
Li, Chen; He, Ming; Dong, Chen; and Li, Wei
(2024)
"Action Recognition Model of Directed Attention Based on Cosine Similarity,"
Journal of System Simulation: Vol. 36:
Iss.
1, Article 5.
DOI: 10.16182/j.issn1004731x.joss.22-0937
Available at:
https://dc-china-simulation.researchcommons.org/journal/vol36/iss1/5
First Page
67
Last Page
82
CLC
TP391.4
Recommended Citation
Li Chen, He Ming, Dong Chen, et al. Action Recognition Model of Directed Attention Based on Cosine Similarity[J]. Journal of System Simulation, 2024, 36(1): 67-82.
DOI
10.16182/j.issn1004731x.joss.22-0937
Included in
Artificial Intelligence and Robotics Commons, Computer Engineering Commons, Numerical Analysis and Scientific Computing Commons, Operations Research, Systems Engineering and Industrial Engineering Commons, Systems Science Commons