arXiv cs.CV
· Papers
CLIP-AUTT: Test-Time Personalization with Action Unit Prompting for Fine-Grained Video Emotion Recognition
arXiv:2603.27999v3 Announce Type: replace Abstract: Personalization in emotion recognition (ER) is essential for accurate interpretation of subtle and subject-specific expressive patterns. Recent advances in vision-language models (VLMs), such as CLIP, demonstrate strong potential for leveraging joint image-text repres