Recurrent 3D attentional networks for end-to-end active object recognition
Sign Up to like & getrecommendations! Published in 2019 at "Computational Visual Media"
DOI: 10.1007/s41095-019-0135-2
Abstract: Active vision is inherently attention-driven: an agent actively selects views to attend in order to rapidly perform a vision task while improving its internal representation of the scene being observed. Inspired by the recent success… read more here.
Keywords: active object; recurrent attentional; object recognition; recognition ... See more keywords