Learning And-Or Models to Represent Context and Occlusion for Car Detection and Viewpoint Estimation

This paper presents a method for learning And-Or models 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... (read more)

Results in Papers With Code
(↓ scroll down to see all results)