KSC-Net: a biologically inspired spatio-temporal correlation network for video-based human action recognition

Abstract Video-based action recognition remains a challenging task due to the difficulty in accurately modeling spatio-temporal dynamics and distinguishing foreground motion from static background clutter. Existing methods often struggle with capturing long-range temporal dependencies and tend to ov...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Hui Ma, Xuelian Ma
Formato:	Artigo
Idioma:	Inglês
Publicado em:	Springer 2025-08-01
coleção:	Discover Applied Sciences
Assuntos:	Spatio-temporal correlation network Human perception Dynamic filter Spatio-temporal self-similarity gated module Action recognition
Acesso em linha:	https://doi.org/10.1007/s42452-025-07504-1
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!