AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

MCID: Multi-aspect Copyright Infringement Detection for Generated Images

Chuanwei Huang, Zexi Jia, Hongyan Fei, Yeshuang Zhu, Zhiqiang Yuan, Ying Deng, Jiapei Zhang, Xiaoyue Duan, Jinchao Zhang, Jie Zhou

ICCV 2025 · Image generation › Autoregressive and latent generation · approach: Generalizable fake image detection · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add multi-aspect similarity scores to the VLM input (ablation)HIDM (GPT-4o) · MCID testsetaccuracy (%): 23.27 -> 72.46Improved
add similarity scores to the VLM input (ablation)HIDM (GPT-4V) · MCID testsetaccuracy (%): 22.03 -> 69.49Improved
add similarity scores to the VLM input (ablation)HIDM (GPT-4o mini) · MCID testsetaccuracy (%): 18.64 -> 64.41Improved
use GPT-4o mini instead of GPT-4o as the VLM (ablation)HIDM · MCID testsetaccuracy (%): 72.46 -> 64.41Hurt
decouple features by attribute with three separate encoders instead of one aggregated network (ablation)HIDM · MCID testsetaccuracy (%)Improved
replace VLM decision-making with an FFN classifier (ablation)HIDM · MCID testsetaccuracy (%)Hurt
aggregate content, style, structure encoders instead of a single encoder (ablation)HIDM encoder · MCID retrievalµAP: 0.502 -> 0.671Improved
use HIDM instead of Gowthami [42] for infringement classificationHIDM · MCID testsetaverage accuracy (%): 42.80 -> 72.46Improved
use HIDM instead of Gowthami [42] on structural infringementHIDM · MCID testsetaccuracy (%): 18.64 -> 64.41Improved
use HIDM instead of Gowthami [42] on CPDMHIDM · CPDMaccuracy (%): 48.32 -> 64.17Improved
use HIDM VLM-based pipeline instead of Wang [49] for IP infringementHIDM · MCID testset IPaccuracy (%): 62.71 -> 59.32No clear effect
add multi-aspect LoRA encoders on a shared backboneHIDM · inference costGFLOPs: 22.30 -> 22.39No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy