PointBLIP: Zero-Training Point Cloud Classification Network Based on BLIP-2 Model

Leveraging the open-world understanding capacity of large-scale visual-language pre-trained models has become a hot spot in point cloud classification. Recent approaches rely on transferable visual-language pre-trained models, classifying point clouds by projecting them into 2D images and evaluating...

Fuld beskrivelse

Bibliografiske detaljer

Principais autores:	Yunzhe Xiao, Yong Dou, Shaowu Yang
Format:	Artigo
Sprog:	Inglês
Udgivet:	MDPI AG 2024-07-01
Serier:	Remote Sensing
Fag:	point cloud classification zero-training large-scale vision-and-language model zero-shot classification few-shot classification
Online adgang:	https://www.mdpi.com/2072-4292/16/13/2453
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!