Learning And-Or Models to Represent Context and Occlusion for Car Detection and Viewpoint Estimation.
IEEE Transactions on Pattern Analysis and Machine Intelligence(2016)
摘要
This paper presents a method for learning an And-Or model to represent context and occlusion for car detection and viewpoint estimation. The learned And-Or model represents car-to-car context and occlusion configurations at three levels: (i) spatially-aligned cars, (ii) single car under different occlusion configurations, and (iii) a small number of parts. The And-Or model embeds a grammar for rep...
更多查看译文
关键词
Solid modeling,Context modeling,Automobiles,Context,Data models,Estimation,Design automation
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络