D3-LND: A two-stream framework with discriminant deep descriptor, linear CMDT and nonlinear KCMDT descriptors for action recognition
Sign Up to like & getrecommendations! Published in 2019 at "Neurocomputing"
DOI: 10.1016/j.neucom.2018.09.086
Abstract: Abstract In order to improve recognition accuracy, a two-stream framework which incorporates deep-learned stream and hand-crafted stream is proposed. Firstly, a discriminant nonlinear feature fusion method is proposed, which introduces the category structure information and… read more here.
Keywords: discriminant deep; stream; stream framework; deep descriptor ... See more keywords