3 citations · 3 across the 4 of their papers we have counts for
Showing cs.CVShow all
2 papers · 1 filter
cs.CV2024
VLEU: a Method for Automatic Evaluation for Generalizability of Text-to-Image Models
Jingtao Cao, Zheng Zhang, Hongru Wang +1
Progress in Text-to-Image (T2I) models has significantly improved the generation of images from textual descriptions. However, existing evaluation metrics do not adequately assess…
cs.CV2024
Detecting Inpainted Video with Frequency Domain Insights
Quanhui Tang, Jingtao Cao
Video inpainting enables seamless content removal and replacement within frames, posing ethical and legal risks when misused. To mitigate these risks, detecting manipulated regions…