2 papers
cs.CV2026
RED: Reconstruction Evolution Dynamics for Generalizable AI-Generated Image Detection
Wenpeng Mu, Junshan Jin, Tanfeng Sun +2
The rapid evolution of image generators calls for forensic cues that generalize beyond known generation mechanisms. Existing detectors often rely on static image representations or…
cs.CV2025
Landmark Guided Visual Feature Extractor for Visual Speech Recognition with Limited Resource
Lei Yang, Junshan Jin, Mingyuan Zhang +3
Visual speech recognition is a technique to identify spoken content in silent speech videos, which has raised significant attention in recent years. Advancements in data-driven dee…