Research map / Vision-language and multimodal / Visual question answering
Exploiting Sentence Embedding for Medical Question Answering
Yu Hao, Xien Liu, Ji Wu, Ping Lv
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 |
|---|---|---|---|
| use CAMSE instead of the strongest listed baseline, SeaReader | MedicalQA#1 (NMLEC) · MedicalQA#1 (NMLEC) | accuracy: 71.8 -> 73.6 | Improved |
| use CAMSE instead of the strongest listed baseline, R-Net or SeaReader | MedicalQA#2 (CD-EMR) · MedicalQA#2 (CD-EMR) | accuracy: 82.4 -> 84.3 | Improved |
| add the contextual unit to the self-attention layer (ablation) | CAMSE · MedicalQA#1 (NMLEC) and MedicalQA#2 (CD-EMR) | accuracy: 69.7 -> 73.6; 83.2 -> 84.3 | Improved |
| use multiple convolution scales rather than only scale 1 (ablation) | CAMSE · MedicalQA#1 (NMLEC) and MedicalQA#2 (CD-EMR) | accuracy: 72.1 -> 73.6; 83.9 -> 84.3 | Improved |
| add convolution scale 3 to scales 1 and 2 (ablation) | CAMSE · MedicalQA#1 (NMLEC) and MedicalQA#2 (CD-EMR) | accuracy: 73.1 -> 73.6; 84.1 -> 84.3 | Improved |
| add SMS to SAS (ablation) | CAMSE scoring · MedicalQA#1 (NMLEC) and MedicalQA#2 (CD-EMR) | accuracy: 70.8 -> 73.6; 83.6 -> 84.3 | Improved |
| add SAS to SMS (ablation) | CAMSE scoring · MedicalQA#1 (NMLEC) and MedicalQA#2 (CD-EMR) | accuracy: 71.3 -> 73.6; 82.8 -> 84.3 | Improved |
Closest papers by meaning
- SMMILE: An expert-driven benchmark for multimodal medical in-context learning (NeurIPS 2025 · similarity 0.86)
- Alignment, Mining and Fusion: Representation Alignment with Hard Negative Mining and Selective Knowledge Fusion for Medical Visual Question Answering (CVPR 2025 · similarity 0.86)
- A General Framework for Producing Interpretable Semantic Text Embeddings (ICLR 2025 · similarity 0.85)
- DiN: Diffusion Model for Robust Medical VQA with Semantic Noisy Labels (CVPR 2025 · similarity 0.85)
- Uni-Med: A Unified Medical Generalist Foundation Model For Multi-Task Learning Via Connector-MoE (NeurIPS 2024 · similarity 0.85)
- Detecting Any instruction-to-answer interaction relationship:Universal Instruction-to-Answer Navigator for Med-VQA (ICML 2024 · similarity 0.84)
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.
