Cross-BERT for Point Cloud Pretraining

Introducing BERT into cross-modal settings raises difficulties in its optimization for handling multiple modalities. Both the BERT architecture and training objective need to be adapted to incorporate and model information from different modalities. In this paper, we address these challenges by expl...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Li, Xin, Li, Peng, Wei, Zeyong, Zhu, Zhe, Wei, Mingqiang, Hou, Junhui, Nan, Liangliang, Qin, Jing, Xie, Haoran, Wang, Fu Lee
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!