Attention Based CNN-ConvLSTM for Pedestrian Attribute Recognition

As a result of its important role in video surveillance, pedestrian attribute recognition has become an attractive facet of computer vision research. Because of the changes in viewpoints, illumination, resolution and occlusion, the task is very challenging. In order to resolve the issue of unsatisfa...

Full beskrivning

Sparad:
Bibliografiska uppgifter
Huvudupphovsmän: Yang Li, Huahu Xu, Minjie Bian, Junsheng Xiao
Materialtyp: Artigo
Språk:Inglês
Publicerad: MDPI AG 2020-02-01
Serie:Sensors
Ämnen:
pedestrian attribute recognition
convolutional neutral networks (cnn)
conventional long short-term memory (convlstm)
channel attention (catt)
multi-label classification
Länkar:https://www.mdpi.com/1424-8220/20/3/811
Taggar: Lägg till en tagg
Inga taggar, Lägg till första taggen!

Liknande verk