Spatial–Temporal Heatmap Masked Autoencoder for Skeleton-Based Action Recognition

Skeleton representation learning offers substantial advantages for action recognition by encoding intricate motion details and spatial–temporal dependencies among joints. However, fully supervised approaches necessitate large amounts of annotated data, which are often labor-intensive and costly to a...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Sensors (Basel, Switzerland) Jg. 25; H. 10; S. 3146
Hauptverfasser:	Bian, Cunling, Yang, Yang, Wang, Tao, Lu, Weigang
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Switzerland MDPI AG 16.05.2025 MDPI
Schlagworte:	Artificial intelligence Comparative analysis Computer vision Human acts Human behavior Identification and classification Machine learning Machine vision masked autoencoder Methods Neural networks self-supervised learning Semantics skeleton-based action recognition spatial–temporal heatmap visual transformer China masked autoencoder self-supervised learning skeleton-based action recognition spatial–temporal heatmap visual transformer
ISSN:	1424-8220, 1424-8220
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!