Skip to content

UFPE-Essex-UNED at ImageCLEFmed Caption 2026: Training-Free Multimodal RAG for Medical Image Captioning

2026 · Conference and Labs of the Evaluation Forum · pp. 3816-3828 · 1 citation · 23 references
Computer Science

TL;DR

The experimental results highlight the effectiveness of retrieval augmentation and prompt alignment for medical image captioning, even in fully training-free settings.

View source

Similar papers

2026

UIT_NEWRON at ImageCLEFmed MEDVQA-GI 2026: Canonical Post-Processing for Gastrointestinal Visual Question Answering

A replicable two-stage pipeline for clinical GI VQA combining parameter-efficient fine-tuning with deterministic output normalisation is proposed and an empirical characterisation of branch-ordering sensitivity and context-gate fragility in rule-based post-processors under distribution shift is characterised.

Tan N. Nguyen, Bao N. Huynh-Dang, Thien B. Nguyen-Tat · 1 citation
2026

UIT_HighDefinition at ImageCLEFmedical Caption 2026: Soft CUI-Guided Qwen3-VL Captioning

Large vision-language models can produce useful medical image captions when combined with soft concept-level guidance and careful output validation, however, the gap between high semantic similarity and lower MedCAT/alignment scores indicates that exact biomedical grounding remains challenging.

D. Nguyen, Han Thi Quynh Nguyen, T. M. Nguyen et al. · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.