Action Recognition Network Based on Local Spatiotemporal Features and Global Temporal Excitation

Action Recognition Network Based on Local Spatiotemporal Features and Global Temporal Excitation

Temporal modeling is a key problem in action recognition, and it remains difficult to accurately model temporal information of videos. In this paper, we present a local spatiotemporal extraction module (LSTE) and a channel time excitation module (CTE), which are specially designed to accurately mode...

Full description

Bibliographic Details
Main Authors: Shukai Li, Xiaofang Wang, Dongri Shan, Peng Zhang
Format: Article
Language:English
Published: MDPI AG 2023-06-01
Series:Applied Sciences
Subjects:
local spatiotemporal features
channel time excitation
action recognition
feature enhancement
Online Access:https://www.mdpi.com/2076-3417/13/11/6811

Similar Items

Similar Items