Research map / Video / Video-language understanding
VMD-FACT: A New Video Dataset and MLLM-based method for Detecting Realistic AI-Generated Video Misinformation
Yongkang Zhang, Dongyu She, Baiyu Ji, Qichuan Geng, Zhong Zhou, Yan Wang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| fine-tune VideoLLaMA2-7B on RAVM subset instead of the dataset's own training set (ablation) | VideoLLaMA2-7B · FakeTT test | accuracy: 56.64 -> 78.26 | Improved |
| fine-tune VideoLLaMA2-7B on RAVM subset instead of the dataset's own training set (ablation) | VideoLLaMA2-7B · FakeSV test | accuracy: 66.04 -> 70.18 | Improved |
| fine-tune VideoLLaMA2-7B on RAVM subset instead of the dataset's own training set (ablation) | VideoLLaMA2-7B · FMNV test | accuracy: 60.99 -> 68.12 | Improved |
| fine-tune on FakeSV training set, test on RAVM (ablation) | VideoLLaMA2-7B · RAVM test | macro F1: 60.98 -> 49.07 | Hurt |
| fine-tune on FMNV training set, test on RAVM (ablation) | VideoLLaMA2-7B · RAVM test | macro F1: 60.98 -> 45.41 | Hurt |
| fine-tune on FakeTT training set, test on RAVM (ablation) | VideoLLaMA2-7B · RAVM test | accuracy: 65.73 -> 55.48 | Hurt |
| fine-tune on FakeSV training set, test on RAVM (ablation) | VideoLLaMA2-7B · RAVM test | accuracy: 65.73 -> 68.62 | Mixed |
| scale up open-source MLLM size | MLLMs on RAVM · RAVM test | accuracy | No clear effect |
| use evidence-graph distilled IEEG 7B instead of general MLLMs | RAVM detection · RAVM test | accuracy: 68.89 -> 75.99 | Improved |
Closest papers by meaning
- Fact-R1: Towards Explainable Video Misinformation Detection with Deep Reasoning (NeurIPS 2025 · similarity 0.90)
- Pioneering Explainable Video Fact-Checking with a New Dataset and Multi-role Multimodal Model Approach (AAAI 2025 · similarity 0.86)
- MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMs (ICLR 2025 · similarity 0.86)
- Drifting Away from Truth: GenAI-Driven News Diversity Challenges LVLM-Based Misinformation Detection (AAAI 2026 · similarity 0.85)
- The Coherence Trap: When MLLM-Crafted Narratives Exploit Manipulated Visual Contexts (CVPR 2026 · similarity 0.85)
- Text-Guided Fine-grained Counterfactual Inference for Short Video Fake News Detection (AAAI 2025 · similarity 0.85)
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.
