Deep Temporal–Spatial Aggregation for Video-Based Facial Expression Recognition

The proposed method has 30 streams, i.e., 15 spatial streams and 15 temporal streams. Each spatial stream corresponds to each temporal stream. Therefore, this work correlates with the symmetry concept. It is a difficult task to classify video-based facial expression owing to the gap between the visu...

Полное описание

Сохранить в:
Библиографические подробности
Главные авторы: Xianzhang Pan, Wenping Guo, Xiaoying Guo, Wenshu Li, Junjie Xu, Jinzhao Wu
Формат: Artigo
Язык:Inglês
Опубликовано: MDPI AG 2019-01-01
Серии:Symmetry
Предметы:
facial expression recognition
convolutional neural networks
temporal-spatial features
optical flow
feature aggregation
Online-ссылка:http://www.mdpi.com/2073-8994/11/1/52
Метки: Добавить метку
Нет меток, Требуется 1-ая метка записи!

Схожие документы