Language guided 3D object detection in point clouds for MEP scenes

Abstract In recent years, contrastive language‐image pre‐training (CLIP) has gained popularity for processing 2D data. However, the application of cross‐modal transferable learning to 3D data remains a relatively unexplored area. In addition, high‐quality, labelled point cloud data for Mechanical, E...

Бүрэн тодорхойлолт

Номзүйн дэлгэрэнгүй

Үндсэн зохиолчид:	Junjie Li, Shengli Du, Jianfeng Liu, Weibiao Chen, Manfu Tang, Lei Zheng, Lianfa Wang, Chunle Ji, Xiao Yu, Wanli Yu
Формат:	Artigo
Хэл сонгох:	Inglês
Хэвлэсэн:	Wiley 2024-06-01
Цуврал:	IET Computer Vision
Нөхцлүүд:	computer vision object detection
Онлайн хандалт:	https://doi.org/10.1049/cvi2.12261
Шошгууд:	Шошго нэмэх Шошго байхгүй, Энэхүү баримтыг шошголох эхний хүн болох!