Tencent Youtu and Shenzhen University's ForgeryVCR wins ACM MM 2026 Oral for image forensics

jiqizhixin · x · 2026-09-30

Image editing and generative models make tampering nearly invisible, yet existing multimodal forensics relies on a text-centric pipeline: describe anomalies in natural language first, then judge forgery from those descriptions. Tencent Youtu Lab and Shenzhen University argue this loses information, since key tampering evidence lives in subtle low-level visual traces that language can't express. Their ForgeryVCR unifies a forensics toolbox, vision-centric reasoning, and strategic tool learning, and was accepted as an Oral at ACM Multimedia 2026.

Original post →

More from Research

Research channel →