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.
More from Research
- ProDyGS Turns Monocular Video Into Pseudo-Multi-Views for Dynamic Gaussian Splatting — kwangmoo_yi · 2026-09-30
- From PDF archives to a trainable model: an open-source fine-tuning data workflow — Puzzleheaded_Box2842 · 2026-09-30
- Depth may be the next scaling axis — if you pick the right residual connections — FinanceYF5 · 2026-09-30
- DepthBench aims to settle the race to beat the 'depth curse' in deep LLMs — FinanceYF5 · 2026-09-30
- Researchers found a 'pain direction' in 25 models; someone claims to have weaponized it on a local model — ZeroStateReflex · 2026-09-30
- Training an AI agent on its own explanations improves coding—no teacher, no verifier, no RL — CatAstro_Piyush · 2026-09-30