Research map / Vision-language and multimodal / Cross-modal learning
Bootstrapping Multi-View Representations for Fake News Detection
Qichao Ying, Xiaoxiao Hu, Yangming Zhou, Zhenxing Qian, Dan Zeng, Shiming Ge
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 |
|---|---|---|---|
| Use BMR instead of MCAN | multimodal fake news detection · Weibo | accuracy: 0.899 -> 0.918 | Improved |
| Use BMR instead of CMC | multimodal fake news detection · GossipCop | accuracy: 0.893 -> 0.895 | Improved |
| Use BMR instead of CAFE | multimodal fake news detection · Weibo-21 | accuracy: 0.882 -> 0.929 | Improved |
| Remove image semantics, image pattern, text, and fusion views, keeping only image pattern (ablation) | BMR · Weibo | accuracy: 0.789 -> 0.918 | Hurt |
| Keep only the image semantics view (ablation) | BMR · Weibo | accuracy: 0.838 -> 0.918 | Hurt |
| Keep image semantics and image pattern views only (ablation) | BMR · Weibo | accuracy: 0.857 -> 0.918 | Hurt |
| Keep only the text view (ablation) | BMR · Weibo | accuracy: 0.870 -> 0.918 | Hurt |
| Keep image pattern and text views only (ablation) | BMR · Weibo | accuracy: 0.878 -> 0.918 | Hurt |
| Keep image semantics and text views only (ablation) | BMR · Weibo | accuracy: 0.881 -> 0.918 | Hurt |
| Bootstrap three unimodal views without the fusion branch (ablation) | BMR · Weibo | accuracy: 0.886 -> 0.918 | Hurt |
| Reweight multi-view features using the cross-modal consistency score (ablation) | BMR · Weibo | accuracy: 0.864 -> 0.918 | Hurt |
| Remove feature reweighting (ablation) | BMR · Weibo | accuracy: 0.887 -> 0.918 | Hurt |
Closest papers by meaning
- DAMMFND: Domain-Aware Multimodal Multi-view Fake News Detection (AAAI 2025 · similarity 0.88)
- External Reliable Information-enhanced Multimodal Contrastive Learning for Fake News Detection (AAAI 2025 · similarity 0.87)
- Reinforced Adaptive Knowledge Learning for Multimodal Fake News Detection (AAAI 2024 · similarity 0.87)
- RaCMC: Residual-Aware Compensation Network with Multi-Granularity Constraints for Fake News Detection (AAAI 2025 · similarity 0.87)
- Learning Complex Heterogeneous Multimodal Fake News via Social Latent Network Inference (AAAI 2025 · similarity 0.86)
- 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.
