Flow-Based Spatio-Temporal Structured Prediction of Motion Dynamics

Conditional Normalizing Flows (CNFs) are flexible generative models capable of representing complicated distributions with high dimensionality and large interdimensional correlations, making them appealing for structured output learning. Their effectiveness in modelling multivariates spatio-temporal...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence 2023-11, Vol.45 (11), p.1-13
Hauptverfasser:	Zand, Mohsen, Etemad, Ali, Greenspan, Michael
Format:	Artikel
Sprache:	eng
Schlagworte:	Computational modeling Data models Dynamics Estimation Masked Convolutions Normalizing Flows Predictive models Spatio-Temporal Modelling Spatiotemporal data Statistical analysis Structured data Structured Prediction Task analysis Time dependence Trajectory
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!