R1. Video forensics
Video forensics is an investigation technique for detecting manipulated(forged) video, and is a key technology for solving various image/video related legal problems.

1.1 Generalization of Deep Faked Image/Video Detection

[Cross-Attention to Explore Coarse to Fine-Grained Relationships for Generalization of Deepfake Detection, In preparation.]

1.2 Counter Anti-forensic for Defending Adversarial Attacks

[A robust open-set multi-instance learning for defending adversarial attacks in digital image, 2024.]
[Counter-act against GAN-based attacks: A collaborative learning approach for anti-forgery detection, 2024.]

1.3 Detection of Double Compression
 
[Deep learning-based counter anti-forensic of GAN-based attack in HEVC compressed domain using coding pattern analysis, 2023.]
[Double compression detection in HEVC-coded video with the same coding parameters using picture partitioning information, 2022.]

R2. Point Cloud Processing

2.1 Point Cloud Rendering

[CRISP: Cylindrical rendering for in-stream point clouds, 2026.]
[Rendering compressed point clouds with a voxel-based method, 2025.]
[Point-based volumetric surface rendering via multi-projection, 2024.]

2.2 Feature Extractions for Point Cloud Data

[A versatile point view descriptor of multi-view depth images for 3D shape classification, In preparation.]

R3. 3D Image/Video Processing

3.1 Immersive Video Processing

[Inactive region filling method for efficient compression using reinforcement learning, 2023.]

3.2 Depth Map Processing

[Deep convolutional grid warping network for joint depth map upsampling, 2020.]
[Depth map upsampling with a confidence-based joint guided filter, 2019.]