| Paper | Code | Accuracy (20 classes) | Accuracy (Binary) | ModelName | ReleaseDate |
|---|---|---|---|---|---|
| MIntRec: A New Dataset for Multimodal Intent Recognition | ✓ Link | 85.51 | 94.72 | Human | 2022-09-09 |
| Token-Level Contrastive Learning with Modality-Aware Prompting for Multimodal Intent Recognition | ✓ Link | 73.62 | TCL-MAP | 2023-12-22 | |
| Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment | ✓ Link | 73.48 | SPECTRA | 2023-05-19 | |
| MIntRec: A New Dataset for Multimodal Intent Recognition | ✓ Link | 72.65 | 89.24 | MAG-BERT (Text + Audio + Video) | 2022-09-09 |
| MIntRec: A New Dataset for Multimodal Intent Recognition | ✓ Link | 72.52 | 89.19 | MulT (Text + Audio + Video) | 2022-09-09 |
| MIntRec: A New Dataset for Multimodal Intent Recognition | ✓ Link | 72.29 | 89.21 | MISA (Text + Audio + Video) | 2022-09-09 |