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...

Popoln opis

Shranjeno v:
Bibliografske podrobnosti
Main Authors: Yang Li, Huahu Xu, Minjie Bian, Junsheng Xiao
Format: Artigo
Jezik:Inglês
Izdano: MDPI AG 2020-02-01
Serija:Sensors
Teme:
pedestrian attribute recognition
convolutional neutral networks (cnn)
conventional long short-term memory (convlstm)
channel attention (catt)
multi-label classification
Online dostop:https://www.mdpi.com/1424-8220/20/3/811
Oznake: Označite
Brez oznak, prvi označite!

Podobne knjige/članki