5 papers
SRAP: SVD-Refined Adversarial Perturbations for Imperceptible Face-Swap Defense
Sungwon Cho, Kwanghyun Ko, Myungjoo Kang
Deepfake technologies pose increasing threats to facial privacy and identity security, motivating proactive defenses that protect facial images before misuse. Although adversarial…
PointT2I: LLM-based text-to-image generation via keypoints
Taekyung Lee, Donggyu Lee, Myungjoo Kang
Text-to-image (T2I) generation model has made significant advancements, resulting in high-quality images aligned with an input prompt. However, despite T2I generation's ability to…
MMVA: Multimodal Matching Based on Valence and Arousal across Images, Music, and Musical Captions
Suhwan Choi, Kyu Won Kim, Myungjoo Kang
We introduce Multimodal Matching based on Valence and Arousal (MMVA), a tri-modal encoder framework designed to capture emotional content across images, music, and musical captions…
Spatial-and-Frequency-aware Restoration method for Images based on Diffusion Models
Kyungsung Lee, Donggyu Lee, Myungjoo Kang
Diffusion models have recently emerged as a promising framework for Image Restoration (IR), owing to their ability to produce high-quality reconstructions and their compatibility w…
MINR: Implicit Neural Representations with Masked Image Modelling
Sua Lee, Joonhun Lee, Myungjoo Kang
Self-supervised learning methods like masked autoencoders (MAE) have shown significant promise in learning robust feature representations, particularly in image reconstruction-base…