S
Seung-Hun Nam
Researcher at KAIST
Publications - 25
Citations - 321
Seung-Hun Nam is an academic researcher from KAIST. The author has contributed to research in topics: Digital watermarking & Watermark. The author has an hindex of 7, co-authored 25 publications receiving 181 citations.
Papers
More filters
Journal ArticleDOI
Finding robust domain from attacks: A learning framework for blind watermarking
TL;DR: In this article, a learning framework for robust and blind watermarking based on reinforcement learning is proposed, which can optimize the robustness while carefully considering the invisibility of the watermark.
Proceedings ArticleDOI
CAT-Net: Compression Artifact Tracing Network for Detection and Localization of Image Splicing
TL;DR: CAT-Net as discussed by the authors is an end-to-end fully convolutional neural network including RGB and DCT streams, which learns forensic features of compression artifacts on RGB and DCNN domains jointly.
Journal ArticleDOI
A SIFT features based blind watermarking for DIBR 3D images
TL;DR: A scale invariant feature transform (SIFT) features based blind watermarking algorithm that is robust against synchronization attacks from DIBR operation, and uses the spread spectrum technique for watermark embedding and perceptual masking taking into consideration the imperceptibility.
Proceedings ArticleDOI
Two-Stream Network for Detecting Double Compression of H.264 Videos
TL;DR: A two-stream neural network that incorporates two components that analyze intra-coded frames and predictive frames is proposed that can detect DC traces in videos more accurately than the prior method.
Proceedings ArticleDOI
Content-Aware Image Resizing Detection Using Deep Neural Network
TL;DR: This paper proposes a deep neural network architecture to capture subtle local artifacts caused by seam-based image resizing, and is the first attempt to solve a given forensic task with three-class classification: original, seam insertion, and seam carving.