182 citations
Showing 2019 · cs.CVShow all
2 papers · 2 filters
cs.CV2019★ 2 cited
To Beta or Not To Beta: Information Bottleneck for DigitaL Image Forensics
Aurobrata Ghosh, Zheng Zhong, Steve Cruz +3
We consider an information theoretic approach to address the problem of identifying fake digital images. We propose an innovative method to formulate the issue of localizing manipu…
cs.CV2019★ 182 cited
DRIT++: Diverse Image-to-Image Translation via Disentangled Representations
Hsin-Ying Lee, Hung-Yu Tseng, Qi Mao +4
Image-to-image translation aims to learn the mapping between two visual domains. There are two main challenges for this task: 1) lack of aligned training pairs and 2) multiple poss…