Multimodal Intent Recognition on MIntRec

12개 결과 · ⬇ CSV · JSON

Accuracy (20 classes)

Rank	Model	Accuracy (20 classes)	Accuracy (Binary)	Paper	Code	Year
1	Human	85.51	94.72	MIntRec: A New Dataset for Multimodal Intent Recognition	thuiar/mintrec	2022
2	TCL-MAP	73.62	–	Token-Level Contrastive Learning with Modality-Aware Prompting for Multimodal Intent Recognition	thuiar/TCL-MAP	2023
3	SPECTRA	73.48	–	Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment	alibabaresearch/damo-convai	2023
4	MAG-BERT (Text + Audio + Video)	72.65	89.24	MIntRec: A New Dataset for Multimodal Intent Recognition	thuiar/mintrec	2022
5	MulT (Text + Audio + Video)	72.52	89.19	MIntRec: A New Dataset for Multimodal Intent Recognition	thuiar/mintrec	2022
6	MISA (Text + Audio + Video)	72.29	89.21	MIntRec: A New Dataset for Multimodal Intent Recognition	thuiar/mintrec	2022
7	Human	85.51	94.72	MIntRec: A New Dataset for Multimodal Intent Recognition	thuiar/mintrec	2022
8	TCL-MAP	73.62	–	Token-Level Contrastive Learning with Modality-Aware Prompting for Multimodal Intent Recognition	thuiar/TCL-MAP	2023
9	SPECTRA	73.48	–	Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment	alibabaresearch/damo-convai	2023
10	MAG-BERT (Text + Audio + Video)	72.65	89.24	MIntRec: A New Dataset for Multimodal Intent Recognition	thuiar/mintrec	2022
11	MulT (Text + Audio + Video)	72.52	89.19	MIntRec: A New Dataset for Multimodal Intent Recognition	thuiar/mintrec	2022
12	MISA (Text + Audio + Video)	72.29	89.21	MIntRec: A New Dataset for Multimodal Intent Recognition	thuiar/mintrec	2022