Self-Supervised Spatiotemporal Representation Learning for Skeleton-Based Human Action Recognition

Skeleton-based human action recognition (HAR) plays an important role in video analytics and recognition systems, with the goal of accurately identifying human actions in videos. However, large-scale action annotation is costly, which has led to the growing interest in HAR research using self-superv...

Descrición completa

Detalles Bibliográficos

Principais autores:	Jinhyeok Park, Seoung Bum Kim
Formato:	Artigo
Idioma:	Inglês
Publicado:	IEEE 2025-01-01
Series:	IEEE Access
Assuntos:	Skeleton-based human action recognition self-supervised learning skeleton-specific transformation graph representation learning non-contrastive learning
Acceso en liña:	https://ieeexplore.ieee.org/document/10945847/
Tags:	Engadir etiqueta Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!