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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Emotion Recognition | AffectNet 7 classes (test val) | Accuracy65.4 | 25 | |
| Emotion Recognition | AffectNet 8 classes (test val) | Accuracy61.6 | 20 | |
| Triplet Prediction | Google FEC (test) | Accuracy86.5 | 10 | |
| Facial Expression Recognition | AffectNet (val) | Accuracy61.6 | 6 | |
| Emotion Recognition | RECOLA | Arousal CCC0.719 | 6 | |
| Emotion Recognition | RECOLA (dev) | Arousal CCC0.8 | 4 | |
| Emotion Recognition | RECOLA (test) | Arousal CCC0.7 | 3 |