Transcoding across 3D shape representations for unsupervised learning of 3D shape feature
Pattern Recognition Letters(2020)
摘要
•Proposing “transcoding 3D shape representations” for unsupervised feature learning.•Implementing the approach as a DNN called Shape Auto-Transcoder (SAT).•Evaluating SAT under scenarios of retrieval and classification of 3D shapes.
更多查看译文
关键词
Unsupervised feature learning,3D shape retrieval and classification,Deep learning,Autoencoder
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要