Research map / Vision-language and multimodal / Multimodal LLMs
Learning Knowledge-Based Prompts for Robust 3D Mask Presentation Attack Detection
Fangling Jiang, Qi Li, Bing Liu, Weining Wang, Caifeng Shan, Zhenan Sun, Ming-Hsuan Yang
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 visual-specific knowledge graph prompt (ablation) | Ours · HiFiMask to 3DMAD (cross-dataset) | HTER: 9.39 -> 1.04 | Improved |
| add visual-specific entity prompt (ablation) | Ours · HiFiMask to 3DMAD (cross-dataset) | HTER: 5.68 -> 1.04 | Improved |
| add fine-grained description prompt (ablation) | Ours · HiFiMask to 3DMAD (cross-dataset) | HTER: 4.30 -> 1.04 | Improved |
| add knowledge filter on entities (ablation) | Ours · HiFiMask to 3DMAD (cross-dataset) | HTER: 3.69 -> 1.04 | Improved |
| add knowledge filter on descriptions (ablation) | Ours · HiFiMask to 3DMAD (cross-dataset) | HTER: 6.37 -> 1.04 | Improved |
| add spurious correlation elimination regularization (ablation) | Ours · HiFiMask to 3DMAD (cross-dataset) | HTER: 2.41 -> 1.04 | Improved |
| add spurious correlation elimination regularization (ablation) | Ours · HiFiMask to 3DMAD (cross-dataset) | EER: 1.76 -> 1.76 | No clear effect |
| use knowledge-based prompts instead of CoOp learnable prompts | Ours · HiFiMask to 3DMAD (cross-dataset) | HTER: 12.39 -> 1.04 | Improved |
| use knowledge-based prompts instead of fine-tuned FLIP | Ours · HiFiMask to 3DMAD (cross-dataset) | HTER: 4.77 -> 1.04 | Improved |
| learn prompts instead of fixed 'A photo of' prompt | CoOp · HiFiMask to 3DMAD (cross-dataset) | HTER: 18.10 -> 12.39 | Improved |
| scale backbone from CLIP ViT-B/16 to ViT-L/14 | Ours · HiFiMask to 3DMAD (cross-dataset) | HTER: 1.04 -> 0.77 | Improved |
| use SigLIP ViT-B/16 backbone instead of CLIP ViT-B/16 | Ours · HiFiMask to 3DMAD (cross-dataset) | HTER: 1.04 -> 0.86 | Improved |
Closest papers by meaning
- Multi-Domain Incremental Learning for Face Presentation Attack Detection (AAAI 2024 · similarity 0.85)
- FaceShield: Explainable Face Anti-Spoofing with Multimodal Large Language Models (AAAI 2026 · similarity 0.85)
- FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation Learning (CVPR 2025 · similarity 0.85)
- Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment (CVPR 2024 · similarity 0.84)
- SAM-Guided Masked Token Prediction for 3D Scene Understanding (NeurIPS 2024 · similarity 0.84)
- Harnessing Chain-of-Thought Reasoning in Multimodal Large Language Models for Face Anti-Spoofing (CVPR 2026 · 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.
