Research map / Vision-language and multimodal / Cross-modal learning
MoMCE: Mixture of Modality and Cue Experts for Multimodal Deception Detection
Dongliang Zhu, Ruimin Hu, Zitong Yu, Xiaobao Guo, Mei Wang, Shuo Ye, Fei Ma, Xiaochun Cao
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 |
|---|---|---|---|
| add cue expert diversity loss (CEDL) (ablation) | MoMCE · DOLOS | accuracy: 75.65 -> 79.10 | Improved |
| add CEDL (ablation) | MoMCE · Bag-of-Lies | F1: 33.81 -> 52.91 | Improved |
| add CEDL (ablation) | MoMCE · MU3D | F1: 43.01 -> 60.35 | Improved |
| add consistency-aware expert weight loss (CEWL) (ablation) | MoMCE · DOLOS | accuracy: 76.52 -> 79.10 | Improved |
| add CEWL (ablation) | MoMCE · Bag-of-Lies | F1: 46.87 -> 52.91 | Improved |
| add CEWL (ablation) | MoMCE · MU3D | F1: 49.26 -> 60.35 | Improved |
| add the second module (MoME or MoCE) to a single-module variant (ablation) | MoMCE · DOLOS | accuracy: 61.73 -> 79.10 | Improved |
| add the second module to the other single-module variant (ablation) | MoMCE · DOLOS | accuracy: 65.62 -> 79.10 | Improved |
| add the second module to single-module variant (ablation) | MoMCE · Bag-of-Lies | F1: 41.94 -> 52.91 | Improved |
| add the second module to single-module variant (ablation) | MoMCE · MU3D | accuracy: 57.50 -> 58.58 | Improved |
| add the second module to the other single-module variant (ablation) | MoMCE · MU3D | F1: 54.64 -> 60.35 | Improved |
| vary lambda_aux, lambda_div, c_th, M, T_e, T_g (ablation) | MoMCE · DOLOS, BOL, MU3D (average) | ACC/F1/AUC | No clear effect |
Closest papers by meaning
- Debate with Images: Detecting Deceptive Behaviors in Multimodal Large Language Models (ICML 2026 · similarity 0.86)
- [Re] Boosting the Visual Interpretability of CLIP via Adversarial Fine-Tuning (NeurIPS 2026 · similarity 0.84)
- AFFAKT: A Hierarchical Optimal Transport Based Method for Affective Facial Knowledge Transfer in Video Deception Detection (AAAI 2025 · similarity 0.84)
- XFeat Revisited: Reproducibility and Evaluation of a Lightweight Image Matcher (NeurIPS 2026 · similarity 0.84)
- Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detector (CVPR 2025 · similarity 0.83)
- How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions (ICLR 2024 · similarity 0.83)
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.
