VEGA aligns multimodal emotion features with CLIP-derived visual emotion prototypes and reports SOTA on IEMOCAP and MELD.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Grounding Emotion Recognition with Visual Prototypes: VEGA -- Revisiting CLIP in MERC
VEGA aligns multimodal emotion features with CLIP-derived visual emotion prototypes and reports SOTA on IEMOCAP and MELD.