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...

Täydet tiedot

Tallennettuna:
Bibliografiset tiedot
Päätekijät: Yang Li, Huahu Xu, Minjie Bian, Junsheng Xiao
Aineistotyyppi: Artigo
Kieli:Inglês
Julkaistu: MDPI AG 2020-02-01
Sarja:Sensors
Aiheet:
pedestrian attribute recognition
convolutional neutral networks (cnn)
conventional long short-term memory (convlstm)
channel attention (catt)
multi-label classification
Linkit:https://www.mdpi.com/1424-8220/20/3/811
Tagit: Lisää tagi
Ei tageja, Lisää ensimmäinen tagi!

Samankaltaisia teoksia