Stochastic human motion prediction using a quantized conditional diffusion model

Human motion prediction is a fundamental task in computer vision, aiming to forecast future human poses based on observed motion sequences. Existing deterministic methods generate a single future motion sequence, neglecting the inherent stochasticity and diversity of human behaviors. To address this...

Celý popis

Podrobná bibliografia

Vydané v:	Knowledge-based systems Ročník 309; s. 112823
Hlavní autori:	Huang, Biaozhang, Li, Xinde, Hu, Chuanfei, Li, Heqing
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Elsevier B.V 30.01.2025
Predmet:	Conditional diffusion model Human motion prediction Vector quantized variational autoencoder Conditional diffusion model Human motion prediction Vector quantized variational autoencoder
ISSN:	0950-7051
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!