Research map / Video / Video segmentation and tracking
Deception Detection in Videos
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Fuse IDT, predicted micro-expression scores, MFCC, and transcript features | Automated deception detection system · Real-life Trial Deception Database | AUC: 0.8596 -> 0.8773 | Helped |
| Add MFCC audio features to IDT and predicted micro-expression scores | Automated deception detection system · Real-life Trial Deception Database | AUC: 0.8347 -> 0.8596 | Helped |
| Add transcript features to IDT and predicted micro-expression scores | Automated deception detection system · Real-life Trial Deception Database | AUC: 0.8347 -> 0.8347 | No clear effect |
| Combine IDT with predicted micro-expression scores | Automated deception detection system · Real-life Trial Deception Database | AUC: 0.7731 -> 0.8347 | Helped |
| Use predicted micro-expression scores instead of IDT alone | Automated deception detection system · Real-life Trial Deception Database | AUC: 0.7731 -> 0.8064 | Mixed |
| Use MFCC audio features alone rather than IDT features alone | Automated deception detection system · Real-life Trial Deception Database | AUC: 0.7731 -> 0.8171 | Helped |
| Add IDT features to ground-truth micro-expression annotations | Ground-truth micro-expression system · Real-life Trial Deception Database | AUC: 0.8325 -> 0.8988 | Helped |
| Add MFCC and transcript features to ground-truth micro-expressions and IDT | Ground-truth micro-expression system · Real-life Trial Deception Database | AUC: 0.8988 -> 0.9221 | Helped |
| Replace predicted micro-expression scores with ground-truth annotations | Deception detection system · Real-life Trial Deception Database | AUC: 0.8773 -> 0.9221 | Helped |
| Use transcript features alone | Automated deception detection system · Real-life Trial Deception Database | AUC: 0.7731 -> 0.6625 | Hurt |
| Use off-the-shelf CNN features instead of IDT for micro-expression classification | Micro-expression detectors · Micro-expression detection | AUC | Hurt |
Closest papers by meaning
- AFFAKT: A Hierarchical Optimal Transport Based Method for Affective Facial Knowledge Transfer in Video Deception Detection (AAAI 2025 · similarity 0.84)
- TriDF: Evaluating Perception, Detection, and Hallucination for Interpretable DeepFake Detection (CVPR 2026 · similarity 0.83)
- Debate with Images: Detecting Deceptive Behaviors in Multimodal Large Language Models (ICML 2026 · similarity 0.82)
- Identity-Aware Vision-Language Model for Explainable Face Forgery Detection (AAAI 2026 · similarity 0.81)
- SpeechForensics: Audio-Visual Speech Representation Learning for Face Forgery Detection (NeurIPS 2024 · similarity 0.81)
- Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detection (AAAI 2024 · similarity 0.81)
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.