S+PAGE

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 RecognitiononDailyDialog
Micro-F1· 2021-12-23
64.07
SOTA
S+PAGE: A Speaker and Position-Aware Graph Neural Network Model for Emotion Recognition in Conversation arXiv:2112.12389
Emotion RecognitiononEmoryNLP
Weighted-F1· 2021-12-23
39.14
best: 42.08 (CKERC)
S+PAGE: A Speaker and Position-Aware Graph Neural Network Model for Emotion Recognition in Conversation arXiv:2112.12389
Emotion RecognitiononMELD
Weighted-F1· 2021-12-23
63.32
best: 69.9 (ELR-GNN)
S+PAGE: A Speaker and Position-Aware Graph Neural Network Model for Emotion Recognition in Conversation arXiv:2112.12389
Emotion RecognitiononIEMOCAP
Weighted-F1· 2021-12-23
68.72
best: 74.08 (SDT)
S+PAGE: A Speaker and Position-Aware Graph Neural Network Model for Emotion Recognition in Conversation arXiv:2112.12389