AI Paper Atlas

Research map / Video / Video segmentation and tracking

CoCoVideo: The High-Quality Commercial-Model-Based Contrastive Benchmark for AI-Generated Video Detection

Huidong Feng, Wentao Chen, Jie Chen, Xinqi Cai, Ruolong Ma, Yinglin Zheng, Yuxin Lin, Ming Zeng

CVPR 2026 · Video › Video segmentation and tracking · approach: Deepfake video detection · 1 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 paired contrastive projection head to the backbone (ablation)CoCoDetect · CoCoVideo test ablationaccuracy (%): 81.05 -> 90.69Improved
add paired contrastive projection head to the backbone (ablation)CoCoDetect · CoCoVideo test ablationAUC (%): 91.39 -> 95.93Improved
add confidence-gated MLLM reasoning at inference (ablation)CoCoDetect · CoCoVideo test ablationaccuracy (%): 88.92 -> 90.69Improved
add confidence-gated MLLM reasoning at inference (ablation)CoCoDetect · CoCoVideo test ablationAUC (%): 95.46 -> 95.93Improved
add contrastive training and confidence-gated MLLM to the 3D ResNet backbone (ablation)3D ResNet · CoCoVideo test ablationaccuracy (%): 78.69 -> 90.69Improved
add contrastive projection branch plus confidence gate to backbone (ablation)3D ResNet · CoCoVideo test ablationF1 (%): 78.57 -> 90.62Improved
compare CoCoDetect with DeMamba on cross-dataset GVDDeMamba · GVD (cross-dataset)accuracy (%): 24.11 -> 71.49Improved
compare CoCoDetect with DeMamba on cross-dataset GVFDeMamba · GVF (cross-dataset)accuracy (%): 26.91 -> 74.56Improved
compare CoCoDetect with DeMamba on GenBusterDeMamba · GenBuster (cross-dataset)accuracy (%): 67.35 -> 64.80Hurt
compare CoCoDetect with DeMamba on GenVideo F1DeMamba · GenVideo (cross-dataset)F1 (%): 57.31 -> 33.19Hurt
compare CoCoDetect with DeMamba on GenVideo accuracyDeMamba · GenVideo (cross-dataset)accuracy (%): 48.17 -> 57.04Improved
compare training-free D3 with trained methodsD3 · CoCoVideo test (average over 13 generators)accuracy (%): 82.59 -> 48.95Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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