Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Leveraging Recent Advances in Deep Learning for Audio-Visual Emotion Recognition

About

Emotional expressions are the behaviors that communicate our emotional state or attitude to others. They are expressed through verbal and non-verbal communication. Complex human behavior can be understood by studying physical features from multiple modalities; mainly facial, vocal and physical gestures. Recently, spontaneous multi-modal emotion recognition has been extensively studied for human behavior analysis. In this paper, we propose a new deep learning-based approach for audio-visual emotion recognition. Our approach leverages recent advances in deep learning like knowledge distillation and high-performing deep architectures. The deep feature representations of the audio and visual modalities are fused based on a model-level fusion strategy. A recurrent neural network is then used to capture the temporal dynamics. Our proposed approach substantially outperforms state-of-the-art approaches in predicting valence on the RECOLA dataset. Moreover, our proposed visual facial expression feature extraction network outperforms state-of-the-art results on the AffectNet and Google Facial Expression Comparison datasets.

Liam Schoneveld, Alice Othmani, Hazem Abdelkawy• 2021

Related benchmarks

TaskDatasetResultRank
Emotion RecognitionAffectNet 7 classes (test val)
Accuracy65.4
25
Emotion RecognitionAffectNet 8 classes (test val)
Accuracy61.6
20
Triplet PredictionGoogle FEC (test)
Accuracy86.5
10
Facial Expression RecognitionAffectNet (val)
Accuracy61.6
6
Emotion RecognitionRECOLA
Arousal CCC0.719
6
Emotion RecognitionRECOLA (dev)
Arousal CCC0.8
4
Emotion RecognitionRECOLA (test)
Arousal CCC0.7
3
Showing 7 of 7 rows

Other info

Follow for update