| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multimodal Sentiment Analysis | MOSI | MAE0.695 | 132 | |
| Multimodal Sentiment Analysis | MOSI | Accuracy87 | 72 | |
| Multimodal Sentiment Analysis | MOSI (test) | MAE0.666 | 34 | |
| Emotion Recognition | MOSI | Accuracy (7-Class)40.84 | 26 | |
| Multimodal Sentiment Analysis | MOSI | WAF82.73 | 14 | |
| Sentiment Regression | MOSI (test) | R^20.709 | 14 | |
| Multimodal Sentiment Analysis | MOSI 2016 (test) | Accuracy (7-class)49.27 | 13 | |
| Multimodal Classification | MOSI | Accuracy70.69 | 13 | |
| Sentiment intensity prediction | CMU MOSI beta = 50% (test) | SRCC0.683 | 12 | |
| Sentiment Classification | MOSI (test) | Weighted F1 Score81 | 8 | |
| Streaming Social Task Detection | MOSI | Accuracy81.24 | 7 | |
| Emotion Recognition in Conversation | MOSI 2-class (test) | Weighted F187.9 | 5 | |
| Multimodal Sentiment Analysis | MOSI -> SIMS | Accuracy0.582 | 5 | |
| Multimodal Retrieval | MOSI | Recall@10 (Q: M23, T: M1)16.7 | 4 | |
| Classification | MOSI MultiBench (test) | Gap0.24 | 3 | |
| Sentiment intensity prediction | CMU MOSI beta = 0% (test) | SRCC0.757 | 1 |