HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction

CVPR2022 We present HOI4D, a large-scale 4D egocentric dataset with rich annotations, to catalyze the research of category-level human-object interaction. HOI4D consists of 2.4M RGB-D egocentric video frames over 4000 sequences collected by 4 participants interacting with 800 different object instan...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Liu, Yunze, Liu, Yun, Jiang, Che, Lyu, Kangbo, Wan, Weikang, Shen, Hao, Liang, Boqiang, Fu, Zhoujie, Wang, He, Yi, Li
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computer Vision and Pattern Recognition
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!