DiaRelay: Relaying Dialogue Context with a Constant-Size Memory for Emotion Recognition in Conversation
Open paper
Benchmark
Model
Rank
Results
emotion-recognition-in-conversation-on-meld
DiaRelay (Qwen3-4B)
–
Weighted-F1: 65.53
Accuracy: 67.56
emotion-recognition-in-conversation-on-meld
DiaRelay (Qwen3-8B)
–
Weighted-F1: 70.06
Accuracy: 71.15
Rank counts only results with a code link.