Haeun Noh — accepted AI-conference papers

2025

Beyond Spatial Frequency: Pixel-wise Temporal Frequency-based Deepfake Video Detection

Taehoon Kim, Jongwook Choi, Yonghyun Jeong, Haeun Noh, Jaejun Yoo, Seungryul Baek +1

ICCV 2025poster

We introduce a deepfake video detection approach that exploits pixel-wise temporal inconsistencies, which traditional spatial frequency-based detectors often overlook. The traditional detectors represent temporal information merely by stacking spatial frequency spectra across frames, resulting in th…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

Group-wise Scaling and Orthogonal Decomposition for Domain-Invariant Feature Extraction in Face Anti-Spoofing

Seungjin Jung, Kanghee Lee, Yonghyun Jeong, Haeun Noh, Jungmin Lee, Jongwon Choi

ICCV 2025poster

Domain Generalizable Face Anti-Spoofing (DG-FAS) methods effectively capture domain-invariant features by aligning the directions (weights) of local decision boundaries across domains. However, the bias terms associated with these boundaries remain misaligned, leading to inconsistent classification…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗