Improved Video Action Recognition Based on Pyramid Pooling and Dual-Stream C3D Networks

This paper proposes an innovative video behaviour classification method based on pyramid pooling and a variable-scale training strategy, which aims to improve the video behaviour-recognition performance of a 3D convolutional neural network (3D-CNN) and a dual-stream C3D network. By introducing pyram...

Fuld beskrivelse

Bibliografiske detaljer

Principais autores:	Yuzhe Tan, Xueliang Fu, Honghui Li
Format:	Artigo
Sprog:	Inglês
Udgivet:	MDPI AG 2025-04-01
Serier:	Applied Sciences
Fag:	video behaviour recognition 3D convolutional neural network pyramid pooling dual-stream C3D network
Online adgang:	https://www.mdpi.com/2076-3417/15/8/4454
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!