Representation Learning through Multimodal Attention and Time-Sync Comments for Affective Video Content Analysis
Open paper
Benchmark
Model
Rank
Results
video-emotion-recognition-on-ekman6
TAM
–
Accuracy: 61.00
video-emotion-recognition-on-ekman6
TAM w/o TSC
–
Accuracy: 60.64
Rank counts only results with a code link.