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...

Celý popis

Uloženo v:
Podrobná bibliografie
Hlavní autoři: Yang Li, Huahu Xu, Minjie Bian, Junsheng Xiao
Médium: Artigo
Jazyk:Inglês
Vydáno: MDPI AG 2020-02-01
Edice:Sensors
Témata:
pedestrian attribute recognition
convolutional neutral networks (cnn)
conventional long short-term memory (convlstm)
channel attention (catt)
multi-label classification
On-line přístup:https://www.mdpi.com/1424-8220/20/3/811
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo otaguje tento záznam!

Podobné jednotky