8 citations · 21 across the 11 of their papers we have counts for
13 papers
Domain-generalizable Face Anti-Spoofing with Patch-based Multi-tasking and Artifact Pattern Conversion
Seungjin Jung, Yonghyun Jeong, Minha Kim +3
Face Anti-Spoofing (FAS) algorithms, designed to secure face recognition systems against spoofing, struggle with limited dataset diversity, impairing their ability to handle unseen…
Beyond Spatial Frequency: Pixel-wise Temporal Frequency-based Deepfake Video Detection
Taehoon Kim, Jongwook Choi, Yonghyun Jeong +4
We introduce a deepfake video detection approach that exploits pixel-wise temporal inconsistencies, which traditional spatial frequency-based detectors often overlook. Traditional…
Group-wise Scaling and Orthogonal Decomposition for Domain-Invariant Feature Extraction in Face Anti-Spoofing
Seungjin Jung, Kanghee Lee, Yonghyun Jeong +3
Domain Generalizable Face Anti-Spoofing (DGFAS) methods effectively capture domain-invariant features by aligning the directions (weights) of local decision boundaries across domai…
Exploiting Style Latent Flows for Generalizing Deepfake Video Detection
Jongwook Choi, Taehoon Kim, Yonghyun Jeong +2
This paper presents a new approach for the detection of fake videos, based on the analysis of style latent vectors and their abnormal behavior in temporal changes in the generated…
Scaling of Class-wise Training Losses for Post-hoc Calibration
Seungjin Jung, Seungmo Seo, Yonghyun Jeong +1
The class-wise training losses often diverge as a result of the various levels of intra-class and inter-class appearance variation, and we find that the diverging class-wise traini…
FrePGAN: Robust Deepfake Detection Using Frequency-level Perturbations
Yonghyun Jeong, Doyeon Kim, Youngmin Ro +1
Various deepfake detectors have been proposed, but challenges still exist to detect images of unknown categories or GAN models outside of the training settings. Such issues arise f…
Self-supervised GAN Detector
Yonghyun Jeong, Doyeon Kim, Pyounggeon Kim +2
Although the recent advancement in generative models brings diverse advantages to society, it can also be abused with malicious purposes, such as fraud, defamation, and fake news.…
MToFNet: Object Anti-Spoofing with Mobile Time-of-Flight Data
Yonghyun Jeong, Doyeon Kim, Jaehyeon Lee +3
In online markets, sellers can maliciously recapture others' images on display screens to utilize as spoof images, which can be challenging to distinguish in human eyes. To prevent…
FICGAN: Facial Identity Controllable GAN for De-identification
Yonghyun Jeong, Jooyoung Choi, Sungwon Kim +5
In this work, we present Facial Identity Controllable GAN (FICGAN) for not only generating high-quality de-identified face images with ensured privacy protection, but also detailed…
ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models
Jooyoung Choi, Sungwon Kim, Yonghyun Jeong +2
Denoising diffusion probabilistic models (DDPM) have shown remarkable performance in unconditional image generation. However, due to the stochasticity of the generative process in…
BiHPF: Bilateral High-Pass Filters for Robust Deepfake Detection
Yonghyun Jeong, Doyeon Kim, Seungjai Min +3
The advancement in numerous generative models has a two-fold effect: a simple and easy generation of realistic synthesized images, but also an increased risk of malicious abuse of…
Toward Spatially Unbiased Generative Models
Jooyoung Choi, Jungbeom Lee, Yonghyun Jeong +1
Recent image generation models show remarkable generation performance. However, they mirror strong location preference in datasets, which we call spatial bias. Therefore, generator…
DefogGAN: Predicting Hidden Information in the StarCraft Fog of War with Generative Adversarial Nets
Yonghyun Jeong, Hyunjin Choi, Byoungjip Kim +1
We propose DefogGAN, a generative approach to the problem of inferring state information hidden in the fog of war for real-time strategy (RTS) games. Given a partially observed sta…