Research map / Vision-language and multimodal / CLIP and zero-shot
Multimodal Prompt Alignment for Facial Expression Recognition
Fuyan Ma, Yiran He, Bin Sun, Shutao Li
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 prompts to frozen CLIP image encoder (ablation) | CoOp baseline · RAF-DB | accuracy: 86.15 -> 88.47 | Improved |
| add prototype-guided visual feature alignment (ablation) | CoOp + visual prompts · RAF-DB | accuracy: 88.47 -> 89.42 | Improved |
| add soft-hard prompt alignment (ablation) | MPA-FER · RAF-DB | accuracy: 89.42 -> 91.18 | Improved |
| add cross-modal global-local alignment (ablation) | MPA-FER · AffectNet-7 | accuracy: 66.58 -> 67.85 | Improved |
| use LLM-generated class descriptions in hard prompts versus generic template (ablation) | MPA-FER · RAF-DB | accuracy: 89.60 -> 91.01 | Improved |
| add soft-hard prompt alignment on LLM-description prompt (ablation) | MPA-FER · RAF-DB | accuracy: 91.01 -> 92.51 | Improved |
| increase training images per class for prototypes from 1 to full (ablation) | MPA-FER · FERPlus | accuracy: 89.87 -> 91.15 | Improved |
| increase prototype data from 64 images to full dataset (ablation) | MPA-FER · FERPlus | accuracy: 91.11 -> 91.15 | No clear effect |
| scale CLIP backbone from ViT-B/16 to ViT-L/14 (ablation) | MPA-FER · RAF-DB | accuracy: 92.51 -> 93.74 | Improved |
Closest papers by meaning
- Amend to Alignment: Decoupled Prompt Tuning for Mitigating Spurious Correlation in Vision-Language Models (ICML 2024 · similarity 0.87)
- Facial-R1: Aligning Reasoning and Recognition for Facial Emotion Analysis (AAAI 2026 · similarity 0.87)
- ExpCLIP: Bridging Text and Facial Expressions via Semantic Alignment (AAAI 2024 · similarity 0.86)
- Hugging Visual Prompt and Segmentation Tokens: Consistency Learning for Fine-Grained Visual Understanding in MLLMs (CVPR 2026 · similarity 0.86)
- MmAP: Multi-Modal Alignment Prompt for Cross-Domain Multi-Task Learning (AAAI 2024 · similarity 0.86)
- CoPL: Contextual Prompt Learning for Vision-Language Understanding (AAAI 2024 · similarity 0.86)
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.
