EmotionCLIP(linear-probe evaluation)

Reported on 3 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.

Audio3 results

Emotion RecognitiononBoLD
AUC· 2023-05-22
69.3
best: 69.83 (A. Xenos et al)
SOTA
Learning Emotion Representations from Verbal and Nonverbal Communication arXiv:2305.13500
Emotion RecognitiononBoLD
Average mAP· 2023-05-22
22.51
best: 26.66 (A. Xenos et al)
SOTA
Learning Emotion Representations from Verbal and Nonverbal Communication arXiv:2305.13500
Emotion RecognitiononEMOTIC
mAP· 2023-05-22
32.91
best: 38.52 (A. Xenos et al)
Learning Emotion Representations from Verbal and Nonverbal Communication arXiv:2305.13500