Unsupervised Disentanglement of Pose, Appearance and Background from Images and Videos

Unsupervised landmark learning is the task of learning semantic keypoint-like representations without the use of expensive input keypoint annotations. A popular approach is to factorize an image into a pose and appearance data stream, then to reconstruct the image from the factorized components. The...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence 2022-07, Vol.44 (7), p.3883-3894
Hauptverfasser:	Dundar, Aysegul, Shih, Kevin J., Garg, Animesh, Pottorf, Robert, Tao, Anrew, Catanzaro, Bryan
Format:	Artikel
Sprache:	eng
Schlagworte:	Annotations Data transmission Decoding foreground-background separation Image color analysis Image reconstruction keypoints Learning Pipelines Representations Task analysis Training Unsupervised landmarks video prediction Videos
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!