EmoNeXt, a ConvNeXt variant using spatial transformers, squeeze-and-excitation blocks, and a self-attention variance regularizer, reports 76.12% accuracy on FER2013.
Facial Expression Recognition with Deep Learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
One of the most universal ways that people communicate is through facial expressions. In this paper, we take a deep dive, implementing multiple deep learning models for facial expression recognition (FER). Our goals are twofold: we aim not only to maximize accuracy, but also to apply our results to the real-world. By leveraging numerous techniques from recent research, we demonstrate a state-of-the-art 75.8% accuracy on the FER2013 test set, outperforming all existing publications. Additionally, we showcase a mobile web app which runs our FER models on-device in real time.
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
EmoNeXt: an Adapted ConvNeXt for Facial Emotion Recognition
EmoNeXt, a ConvNeXt variant using spatial transformers, squeeze-and-excitation blocks, and a self-attention variance regularizer, reports 76.12% accuracy on FER2013.