|
|
Frontiers of Information Technology & Electronic Engineering
ISSN 2095-9184 (print), ISSN 2095-9230 (online)
2022 Vol.23 No.9 P.1290-1297
Three-dimensional shape space learning for visual concept construction: challenges and research progress
Abstract: 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 (
Key words:
微软亚洲研究院，中国北京市，100080
摘要：人类可以熟练的对真实世界中物体按照形状或者功能进行分类，并在思维中建立每类物体的视觉概念和周围真实世界的视觉知识（Pan, 2019）。Pan（2021）指出建立这些视觉概念和视觉知识的计算表达是发展下一代人工智能的一个关键步骤。学习同一视觉概念下所有物体的三维形状空间是实现视觉概念计算表达的一个关键步骤。本文提出三维形状空间学习中面临的关键技术挑战，并围绕这些技术挑战回顾了这一领域的研究进展，最后讨论了三维形状空间学习领域的研究趋势和未来发展方向。
关键词组：
References:
Open peer comments: Debate/Discuss/Question/Opinion
<1>
DOI:
10.1631/FITEE.2200318
CLC number:
Download Full Text:
Downloaded:
1961
Clicked:
1633
Cited:
0
On-line Access:
2022-09-21
Received:
2022-07-26
Revision Accepted:
2022-09-21
Crosschecked:
2022-08-26