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...

Полное описание

Сохранить в:
Библиографические подробности
Главные авторы: Yang Li, Huahu Xu, Minjie Bian, Junsheng Xiao
Формат: Artigo
Язык:Inglês
Опубликовано: MDPI AG 2020-02-01
Серии:Sensors
Предметы:
pedestrian attribute recognition
convolutional neutral networks (cnn)
conventional long short-term memory (convlstm)
channel attention (catt)
multi-label classification
Online-ссылка:https://www.mdpi.com/1424-8220/20/3/811
Метки: Добавить метку
Нет меток, Требуется 1-ая метка записи!

Схожие документы