Research on Action Recognition Algorithm Based on SlowFast Network

As a major branch of video understanding, human action recognition has become a popular research topic in the field of computer vision and has a wide range of applications in many areas. To address the problems of high parameter consumption and weak spatiotemporal modeling capabilities in existing a...

Full description

Saved in:
Bibliographic Details
Published in:Journal of advanced computational intelligence and intelligent informatics Vol. 29; no. 5; pp. 1056 - 1061
Main Authors: Xu, Yinhao, Lu, Yuanyao
Format: Journal Article
Language:English
Published: Tokyo Fuji Technology Press Co. Ltd 20.09.2025
Subjects:
Accuracy
Algorithms
Computer vision
Consumption
Design
Human activity recognition
Informatics
Network design
Neural networks
Parameters
Semantics
ISSN:1343-0130, 1883-8014
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:As a major branch of video understanding, human action recognition has become a popular research topic in the field of computer vision and has a wide range of applications in many areas. To address the problems of high parameter consumption and weak spatiotemporal modeling capabilities in existing action recognition methods, this study proposes a lightweight dual-branch convolutional network called SlowFast-Light Net. Inspired and influenced by the renowned two-branch SlowFast network proposed by the expert Kaiming He, this study adopts a lightweight two-branch network design, which is an improvement based on the SlowFast network. The network significantly reduces parameter consumption by introducing a lightweight feature extraction network and accelerating the model convergence speed. This study conducts experimental verification on the UCF101 and HMDB51 datasets, achieving an action recognition accuracy of 93.80% and 80.00%, respectively, on the two test sets. The experimental results showed that the model proposed in this study achieved a recognition accuracy comparable to that of the original model with a considerably lower number of parameters.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1343-0130
1883-8014
DOI:10.20965/jaciii.2025.p1056