2 papers
cs.CV2026
EV-CLIP: Efficient Visual Prompt Adaptation for CLIP in Few-shot Action Recognition under Visual Challenges
Hyo Jin Jon, Longbin Jin, Eun Yi Kim
CLIP has demonstrated strong generalization in visual domains through natural language supervision, even for video action recognition. However, most existing approaches that adapt…
eess.AS2025
MATER: Multi-level Acoustic and Textual Emotion Representation for Interpretable Speech Emotion Recognition
Hyo Jin Jon, Longbin Jin, Hyuntaek Jung +3
This paper presents our contributions to the Speech Emotion Recognition in Naturalistic Conditions (SERNC) Challenge, where we address categorical emotion recognition and emotional…