| ActivityForensics: A Comprehensive Benchmark for Localizing Manipulated Activity in Videos |
CVPR |
2026 |
General Detection |
Localizing Manipulated Activity in Videos |
Code |
| Training-free Detection of Generated Videos via Spatio-Temporal Likelihoods |
CVPR |
2026 |
General Detection |
A zero-shot, training-free method that detects AI-generated videos by jointly modeling spatial and temporal likelihoods from pretrained embeddings |
Code |
| Physics-Driven Spatiotemporal Modeling for AI-Generated Video Detection |
NeurIPS |
2025 |
General Detection |
Normalized spatio-temporal gradient (NSG) statistic quantifies the ratio of the spatial probability gradient of the video to the change in temporal density through the principle of conservation of probability flow |
Code |
| VIDGUARD-R1: AI-GENERATED VIDEO DETECTION AND EXPLANATION VIA REASONING MLLMS AND RL |
arXiv |
2025 |
General Detection |
Using GRPO with two specialized reward models that target temporal artifacts and generation complexity |
Code |
| Video Forgery Detection with Optical Flow Residuals and Spatial-Temporal Consistency |
arXiv |
2025 |
General Detection |
Optical Flow Residuals |
- |
| D3: Training-Free AI-Generated Video Detection Using Second-Order Features |
arXiv |
2025 |
General Detection |
Second-order Central Difference features |
Code |
| BusterX++: Towards Unified Cross-Modal AI-Generated Content Detection and Explanation with MLLM |
arXiv |
2025 |
General Detection |
Hybrid reasoning |
Code |
| IVY-FAKE: A Unified Explainable Framework and Benchmark for Image and Video AIGC Detection |
arXiv |
2025 |
General Detection |
Explanation model |
— |
| BusterX: MLLM-Powered AI-Generated Video Forgery Detection and Explanation |
arXiv |
2025 |
General Detection |
MLLM + DAPO, reasoning/explanation model |
— |
| GenVidBench: A Challenging Benchmark for Detecting AI-Generated Video |
arXiv |
2025 |
General Detection |
None new methods |
Code |
| Towards a Universal Synthetic Video Detector: From Face or Background Manipulations to Fully AI-Generated Content |
CVPR |
2025 |
General Detection |
Universal Network for Identifying Tampered and synthEtic videos (UNITE), with its attention-diversity (AD) loss, effectively detects both face/background manipulations and fully synthetic content |
— |
| Beyond Deepfake Images: Detecting AI-Generated Videos |
CVPR Workshop |
2024 |
General Detection |
None new methods |
— |
| What Matters in Detecting AI-Generated Videos like Sora? |
arXiv |
2024 |
General Detection |
Appearance + Motion + Geometry feature fusion |
Code |
| Turns Out I'm Not Real: Towards Robust Detection of AI-Generated Videos |
CVPR Workshop |
2024 |
General Detection |
Dire frame & CNN + LSTM detector |
— |
| DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmark |
arXiv |
2024 |
General Detection |
Detail Mamba modeling spatial-temporal artifacts |
Code |
| Exposing AI-generated Videos: A Benchmark Dataset and a Local-and-Global Temporal Defect Based Detection Method |
arXiv |
2024 |
General Detection |
Local and global artifacts |
— |
| Distinguish Any Fake Videos: Unleashing the Power of Large-scale Data and Motion Features |
arXiv |
2024 |
General Detection |
Dual path feature fusing: spatial-temporal and optical flow |
— |
| AI-Generated Video Detection via Spatio-Temporal Anomaly Learning |
PRCV |
2024 |
General Detection |
Spatial Domain Detector/Optical Flow Detector |
— |
| DeCoF: Generated Video Detection via Frame Consistency |
arXiv |
2024 |
General Detection |
Video-based, CLIP+Transformer modeling temporal artifacts |
— |
| TALL: Thumbnail Layout for Deepfake Video Detection |
ICCV |
2023 |
Face Detection |
Transforms a video clip into a pre-defined layout to realize the preservation of spatial and temporal dependencies |
Code |
| ISTVT: Interpretable Spatial-Temporal Video Transformer for Deepfake Detection |
TIFS |
2023 |
Face Detection |
Decomposed spatial-temporal self-attention and a self-subtract mechanism to capture spatial artifacts and temporal inconsistency |
— |
| Exploiting Complementary Dynamic Incoherence for DeepFake Video Detection |
TCSVT |
2023 |
Face Detection |
Dynamic facial feature analysis |
— |
| Hierarchical Contrastive Inconsistency Learning for Deepfake Video Detection |
ECCV |
2022 |
Face Detection |
Hierarchical contrastive inconsistency learning |
— |
| Spatiotemporal Inconsistency Learning for DeepFake Video Detection |
ACM MM |
2021 |
Face Detection |
Video-based, STIL modeling spatiotemporal artifacts |
Code |