典型文献
Three-dimensional shape space learning for visual concept construction:challenges and research progress
文献摘要：
Human beings can easily categorize three-dimensional(3D)objects with similar shapes and functions into a set of"visual concepts"and learn"visual knowledge"of the surrounding 3D real world(Pan,2019).Developing efficient methods to learn the computational representation of the visual con-cept and the visual knowledge is a critical task in artificial intelligence(Pan,2021a).A crucial step to this end is to learn the shape space spanned by all 3D objects that belong to one visual concept.In this paper,we present the key technical challenges and recent research progress in 3D shape space learning and discuss the open problems and research oppor-tunities in this area.
文献关键词：
中图分类号：
作者姓名：
Xin TONG
作者机构：
Microsoft Research Asia,Beijing 100080,China
文献出处：
引用格式：
[1]Xin TONG-.Three-dimensional shape space learning for visual concept construction:challenges and research progress)[J].信息与电子工程前沿（英文）,2022(09):1290-1297
A类：
B类：
Three,dimensional,space,learning,visual,construction,challenges,research,progress,Human,beings,can,easily,categorize,three,objects,similar,shapes,functions,into,set,concepts,knowledge,surrounding,real,world,Pan,Developing,efficient,methods,computational,representation,critical,task,artificial,intelligence,2021a,crucial,step,this,end,spanned,by,that,belong,one,In,paper,we,key,technical,recent,discuss,open,problems,oppor,tunities,area
AB值：
0.573104
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
