Research map / Vision-language and multimodal / Human and embodied modeling
Visual-Textual Attentive Semantic Consistency for Medical Report Generation
Yi Zhou, Lei Huang, Tao Zhou, Huazhu Fu, Ling Shao
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 multi-modality semantic attention (ablation) | Ours · MIMIC-CXR | CIDEr: 0.909 -> 1.121 | Improved |
| add description pattern labels to image encoder training (ablation) | Ours · MIMIC-CXR | nKTD: 0.170 -> 0.106 | Improved |
| add clinical features (ablation) | Ours · MIMIC-CXR | nKTD: 0.117 -> 0.106 | Improved |
| add clinical features (CIDEr and BLEU) (ablation) | Ours · MIMIC-CXR | CIDEr: 1.125 vs 1.121 | No clear effect |
| add image-sentence matching loss (ablation) | Ours · MIMIC-CXR | CIDEr: 0.954 -> 1.121 | Improved |
| add description accuracy loss (ablation) | Ours · MIMIC-CXR | CIDEr: 1.029 -> 1.121 | Improved |
| add multi-modality semantic attention (ablation) | Ours · IU X-Ray | CIDEr: 0.320 -> 0.339 | Improved |
| add image-sentence matching loss (ablation) | Ours · IU X-Ray | nKTD: 0.130 -> 0.097 | Improved |
| add description accuracy loss (ablation) | Ours · IU X-Ray | nKTD: 0.116 -> 0.097 | Improved |
| add clinical features (ablation) | Ours · IU X-Ray | nKTD: 0.104 -> 0.097 | Improved |
| add self-attention on regional visual features (ablation) | image encoder · MIMIC disease prediction | mean AUC: 0.841 -> 0.849 | Improved |
| add report embedding supervision (ablation) | image encoder · MIMIC disease prediction | mean AUC: 0.838 -> 0.849 | Improved |
Closest papers by meaning
- DAMPER: A Dual-Stage Medical Report Generation Framework with Coarse-Grained MeSH Alignment and Fine-Grained Hypergraph Matching (AAAI 2025 · similarity 0.90)
- DART: Disease-aware Image-Text Alignment and Self-correcting Re-alignment for Trustworthy Radiology Report Generation (CVPR 2025 · similarity 0.89)
- Automatic Radiology Reports Generation via Memory Alignment Network (AAAI 2024 · similarity 0.89)
- AHIVE: Anatomy-aware Hierarchical Vision Encoding for Interactive Radiology Report Retrieval (CVPR 2024 · similarity 0.88)
- Bootstrapping Large Language Models for Radiology Report Generation (AAAI 2024 · similarity 0.88)
- Image-aware Evaluation of Generated Medical Reports (NeurIPS 2024 · similarity 0.87)
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.
