GA2MIF

Reported on 4 benchmarks across 1 task · 1 paper · 1 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· 2022-07-25
69.75
best: 73.95 (SDT)
SOTA
GA2MIF: Graph and Attention Based Two-Stage Multi-Source Information Fusion for Conversational Emotion Detection arXiv:2207.11900
Emotion RecognitiononMELD
Accuracy· 2022-07-25
61.65
best: 68.7 (ELR-GNN)
GA2MIF: Graph and Attention Based Two-Stage Multi-Source Information Fusion for Conversational Emotion Detection arXiv:2207.11900
Emotion RecognitiononMELD
Weighted-F1· 2022-07-25
58.94
best: 69.9 (ELR-GNN)
GA2MIF: Graph and Attention Based Two-Stage Multi-Source Information Fusion for Conversational Emotion Detection arXiv:2207.11900
Emotion RecognitiononIEMOCAP
Weighted-F1· 2022-07-25
70
best: 74.08 (SDT)
GA2MIF: Graph and Attention Based Two-Stage Multi-Source Information Fusion for Conversational Emotion Detection arXiv:2207.11900