5 papers
Rationale-Guided Learning for Multimodal Emotion Recognition
Sujung Oh, Jung Uk Kim, Sangmin Lee
Multimodal emotion recognition in conversation (MERC) requires understanding complex interactions between verbal and non-verbal cues. However, most existing approaches fundamentall…
From Adaptation to Generalization: Adaptive Visual Prompting for Medical Image Segmentation
Evren Ãetinkaya, Sangmin Lee, Jung Uk Kim +2
Visual prompting has emerged as a powerful method for adapting pre-trained models to new domains without updating model parameters. However, existing prompting methods typically op…
Generate, Analyze, and Refine: Training-Free Sound Source Localization via MLLM Meta-Reasoning
Subin Park, Jung Uk Kim
Sound source localization task aims to identify the locations of sound-emitting objects by leveraging correlations between audio and visual modalities. Most existing SSL methods re…
Object-aware Sound Source Localization via Audio-Visual Scene Understanding
Sung Jin Um, Dongjin Kim, Sangmin Lee +1
Audio-visual sound source localization task aims to spatially localize sound-making objects within visual scenes by integrating visual and audio cues. However, existing methods str…
Watch Video, Catch Keyword: Context-aware Keyword Attention for Moment Retrieval and Highlight Detection
Sung Jin Um, Dongjin Kim, Sangmin Lee +1
The goal of video moment retrieval and highlight detection is to identify specific segments and highlights based on a given text query. With the rapid growth of video content and t…