Research map / Video / Video segmentation and tracking
Face-Focused Cross-Stream Network for Deception Detection in Videos
Check 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 |
|---|---|---|---|
| Combine face and motion branches (ablation) | FFCSN · Real-Life Dataset | ACC: 84.33 -> 88.21 | Helped |
| Add cross-stream correlation learning (ablation) | Face+Motion · Real-Life Dataset | ACC: 88.21 -> 89.16 | Helped |
| Add meta learning (ablation) | Face+Motion+CL · Real-Life Dataset | ACC: 89.16 -> 92.33 | Helped |
| Add adversarial learning (ablation) | Face+Motion+CL+ML · Real-Life Dataset | ACC: 92.33 -> 93.16 | Helped |
| Add acoustic and verbal modalities | FFCSN · Real-Life Dataset | ACC: 93.16 -> 97.00 | Helped |
| Use FFCSN visual features rather than the strongest listed multimodal baseline | FFCSN · YouTube-8 | ACC: 52.6 -> 57.8 | Helped |
| Use task size 5 for meta-learning pairwise comparisons (ablation) | FFCSN meta-learning module · Real-Life Dataset | ACC | Mixed |
| Use pairwise comparison instead of conventional non-pairwise loss (ablation) | FFCSN meta-learning module · Real-Life Dataset | ACC | Helped |
| Use the proposed pairwise loss instead of Siamese or triplet loss (ablation) | FFCSN meta-learning module · Real-Life Dataset | ACC | Helped |
| Add face detection to the spatial stream (ablation) | TSN · Real-Life Dataset | ACC | Helped |
| Add cross-stream correlation learning (ablation) | TSN+FD · Real-Life Dataset | ACC | Helped |
Closest papers by meaning
- AFFAKT: A Hierarchical Optimal Transport Based Method for Affective Facial Knowledge Transfer in Video Deception Detection (AAAI 2025 · similarity 0.85)
- Face Forensics in the Wild (CVPR 2021 · similarity 0.84)
- QCS:Feature Refining from Quadruplet Cross Similarity for Facial Expression Recognition (AAAI 2025 · similarity 0.82)
- FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation Learning (CVPR 2025 · similarity 0.82)
- Face Forgery Video Detection via Temporal Forgery Cue Unraveling (CVPR 2025 · similarity 0.82)
- Towards a Universal Synthetic Video Detector: From Face or Background Manipulations to Fully AI-Generated Content (CVPR 2025 · 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.