Dynamic Facial Expression Recognition by Concatenation of Raw, Semi-Raw, and Distance Features

2026 Open access

Read full text
Authors: Jose Sotelo-Barrales, Mariko Nakano-Miyatake, David Mata-Mendoza, Hector Manuel Perez-Meana, Enrique Escamilla-Hernández
DOI: 10.3390/engproc2026123005
Cited by: 0
References: 6

Abstract

We propose a method for dynamic facial expression recognition that integrates three complementary feature streams from video sequences: (1) raw texture features extracted with EfficientNet-B0, (2) deep geometric features from face mesh representations (semi-raw, EfficientNet-B0), and (3) explicit geometric features derived from facial landmark distances.

Fields of Study & Subjects

Face recognition and analysis Emotion and Mood Recognition Face and Expression Recognition

Publication details

Pages
5–5
Publication date
2 February 2026
Language
EN