| Paper | Code | Average mAP | AUC | ModelName | ReleaseDate |
|---|---|---|---|---|---|
| VLLMs Provide Better Context for Emotion Understanding Through Common Sense Reasoning | ✓ Link | 26.66 | 69.83 | A. Xenos et al | 2024-04-10 |
| Learning Emotion Representations from Verbal and Nonverbal Communication | ✓ Link | 22.51 | 69.30 | EmotionCLIP(linear-probe evaluation) | 2023-05-22 |
| Leveraging Semantic Scene Characteristics and Multi-Stream Convolutional Architectures in a Contextual Approach for Video-Based Visual Emotion Recognition in the Wild | ✓ Link | 19.29 | 66.82 | Pikoulis et al | 2021-05-16 |