Self-attention fusion for audiovisual emotion recognition with incomplete data
Open paper
Benchmark
Model
Rank
Results
emotion-recognition-on-ravdess
Intermediate-Attention-Fusion
#2
Accuracy: 81.58%
facial-emotion-recognition-on-ravdess
Intermediate-Transformer-Fusion, visual branch only
#2
Accuracy: 74.92%
Rank counts only results with a code link.