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...

Popoln opis

Shranjeno v:
Bibliografske podrobnosti
Main Authors: Xianzhang Pan, Wenping Guo, Xiaoying Guo, Wenshu Li, Junjie Xu, Jinzhao Wu
Format: Artigo
Jezik:Inglês
Izdano: MDPI AG 2019-01-01
Serija:Symmetry
Teme:
facial expression recognition
convolutional neural networks
temporal-spatial features
optical flow
feature aggregation
Online dostop:http://www.mdpi.com/2073-8994/11/1/52
Oznake: Označite
Brez oznak, prvi označite!

Podobne knjige/članki