AI Paper Atlas

Research map / Video / Video segmentation and tracking

Your One-Stop Solution for AI-Generated Video Detection

Long Ma, Zihao Xue, Yan Wang, Zhiyuan Yan, Jin Xu, Xiaorui Jiang, Haiyang Yu, Yong Liao, Zhen Bi

CVPR 2026 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 13 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 Effort's fine-tuning strategy on top of the base CLIP-ViT-L/14 (ablation)CLIP-ViT-L/14 detector · AIGVDBench open and closed sourceAUC: 1.8% on open source, 28.79% on closed sourceImproved
train on a small dataset for more epochs (ForgeLens1) instead of a large dataset for fewer epochs (ForgeLens3) (ablation)ForgeLens · AIGVDBench open and closed sourceAUC: 2.22% on open-source, 8.16% on closed source; avg 89.60 -> 91.82Improved
move evaluation from open-source to closed-source generatorsI3D · AIGVDBenchAUC: 82.99 -> 61.18Hurt
move evaluation from open-source to closed-source generatorsCNNSpot · AIGVDBenchAUC: 85.61 -> 70.60Hurt
move evaluation from open-source to closed-source generatorsEffort · AIGVDBenchAUC: 87.49 -> 94.05Improved
move evaluation from open-source to closed-source generatorsTimeSformer · AIGVDBenchAUC: 81.50 -> 86.50Improved
evaluate on V2V instead of T2V videosTimeSformer · AIGVDBench open-sourceAUC: 86.84 -> 67.59Hurt
evaluate on V2V instead of T2V videosEffort · AIGVDBench open-sourceAUC: 90.20 -> 74.74Hurt
evaluate on I2V instead of T2V videosI3D · AIGVDBench open-sourceAUC: 80.78 -> 89.05Improved
evaluate on I2V instead of T2V videosTimeSformer · AIGVDBench open-sourceAUC: 86.84 -> 75.46Hurt
use a CLIP-based image detector (UnivFD) instead of a ResNet-based one (CNNSpot)image detector · AIGVDBench open-sourceAUC: 85.61 -> 85.69No clear effect
scale the VLM from Qwen2.5-VL-3B to 7B to 32BQwen2.5-VL · AIGVDBench open-sourceaccuracy: 50.35 -> 51.84 -> 51.12Mixed

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