MPT-HCL

Reported on 4 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Audio4 results

Emotion RecognitiononIEMOCAP
Accuracy· 2023-10-04
72.83
best: 73.95 (SDT)
SOTA
Multimodal Prompt Transformer with Hybrid Contrastive Learning for Emotion Recognition in Conversation arXiv:2310.04456
Emotion RecognitiononIEMOCAP
Weighted-F1· 2023-10-04
72.51
best: 74.08 (SDT)
SOTA
Multimodal Prompt Transformer with Hybrid Contrastive Learning for Emotion Recognition in Conversation arXiv:2310.04456
Emotion RecognitiononMELD
Accuracy· 2023-10-04
65.86
best: 68.7 (ELR-GNN)
Multimodal Prompt Transformer with Hybrid Contrastive Learning for Emotion Recognition in Conversation arXiv:2310.04456
Emotion RecognitiononMELD
Weighted-F1· 2023-10-04
65.02
best: 69.9 (ELR-GNN)
Multimodal Prompt Transformer with Hybrid Contrastive Learning for Emotion Recognition in Conversation arXiv:2310.04456