MTOR: Generalizable AI-Generated Video Detection with Multimodal Semantics and Temporal Over-Regularity

cs.CV

Submitted: 2026-10-05

Updated: 2026-10-05

Comments: 18 pages, 4 figures, 19 tables

Code: https://github.com/hwang-cs-ime/MTOR

Project page: http://www4.comp.polyu.edu.hk

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Training-free Detection of Generated Videos via Spatial-Temporal Likelihoods
• DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmark
• VideoPhy: Evaluating Physical Commonsense for Video Generation
• Youku-mPLUG: A 10 Million Large-scale Chinese Video-Language Dataset for Pre-training and Benchmarks
• ModelScope Text-to-Video Technical Report
• VideoCrafter1: Open Diffusion Models for High-Quality Video Generation
• DreaMoving: A Human Video Generation Framework based on Diffusion Models
• InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models