A Temporal Action Detection Algorithm Based on Spatio-Temporal Feature Pyramid Network

Authors

Liu Wang, School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, China;
Jinyu Sun, School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, China;
Shiwei Ma, School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, China;

Abstract

Abstract: In view of the discontinuity of motion timing detection in the frame-level prediction network structure, a novel algorithm based on spatio-temporal feature pyramid network (ST-FPN) is proposed. In the frame-level action prediction, several 3D convolution-de-convolution (CDC) networks are used to sample spatial feature down to 1 dimension and sample temporal feature up to corresponding proposal level. Then the prediction scores of different CDC networks are fused by non-maximum suppression (NMS). The softmax classifier is used to classify frame-level actions, and then temporal action detection is obtained. The experimental results on dataset THUMOS14 show that the proposed algorithm improves the accuracy of temporal action detection.

Recommended Citation

Wang, Liu; Sun, Jinyu; and Ma, Shiwei (2019) "A Temporal Action Detection Algorithm Based on Spatio-Temporal Feature Pyramid Network," Journal of System Simulation: Vol. 31: Iss. 11, Article 22.
DOI: 10.16182/j.issn1004731x.joss.19-FZ0369
Available at: https://dc-china-simulation.researchcommons.org/journal/vol31/iss11/22

First Page

2382

Revised Date

2019-07-23

DOI Link

https://doi.org/10.16182/j.issn1004731x.joss.19-FZ0369

Last Page

2387

CLC

TP391.4

Recommended Citation

Liu Wang, Sun Jinyu, Ma Shiwei. A Temporal Action Detection Algorithm Based on Spatio-Temporal Feature Pyramid Network[J]. Journal of System Simulation, 2019, 31(11): 2382-2387.

Corresponding Author

Shiwei Ma,

DOI

10.16182/j.issn1004731x.joss.19-FZ0369