3 papers
cs.CV2024
Video Inpainting Localization with Contrastive Learning
Zijie Lou, Gang Cao, Man Lin
Deep video inpainting is typically used as malicious manipulation to remove important objects for creating fake videos. It is significant to identify the inpainted regions blindly.…
cs.CV2024
Trusted Video Inpainting Localization via Deep Attentive Noise Learning
Zijie Lou, Gang Cao, Man Lin
Digital video inpainting techniques have been substantially improved with deep learning in recent years. Although inpainting is originally designed to repair damaged areas, it can…
cs.CV2024
AI-Generated Video Detection via Spatio-Temporal Anomaly Learning
Jianfa Bai, Man Lin, Gang Cao
The advancement of generation models has led to the emergence of highly realistic artificial intelligence (AI)-generated videos. Malicious users can easily create non-existent vide…