Conversational Memory Network for Emotion Recognition in Dyadic Dialogue Videos

Emotion recognition in conversations is crucial for the development of empathetic machines. Present methods mostly ignore the role of inter-speaker dependency relations while classifying emotions in conversations... (read more)

PDF Abstract

Datasets


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK BENCHMARK
Emotion Recognition in Conversation IEMOCAP CMN F1 56.13 # 16
Emotion Recognition in Conversation SEMAINE CMN MAE (Valence) 0.192 # 5
MAE (Arousal) 0.213 # 4
MAE (Expectancy) 0.195 # 5
MAE (Power) 8.74 # 5

Methods used in the Paper


METHOD TYPE
Memory Network
Working Memory Models