Injecting MLLM-generated multimodal reasoning traces into a fused audio-visual-text emotion model, plus a balanced dual-contrastive loss, raises average accuracy on MER2024 from 77.5 to 84.7 percent.
Tacfn: Transformer-based adaptive cross-modal fusion network for multimodal emotion recognition.Artificial Intelligence Research, 2, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Multimodal Video Emotion Recognition with Reliable Reasoning Priors
Injecting MLLM-generated multimodal reasoning traces into a fused audio-visual-text emotion model, plus a balanced dual-contrastive loss, raises average accuracy on MER2024 from 77.5 to 84.7 percent.