AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Learnable Retrieval Enhanced Visual-Text Alignment and Fusion for Radiology Report Generation

Qin Zhou, Guoyan Liang, Xindi Li, Jingyuan Chen, Zhe Wang, Chang Yao, Sai Wu

ICCV 2025 · Vision-language and multimodal › Cross-modal learning · approach: Probabilistic embeddings for cross-modal retrieval · 6 citations (OpenAlex)

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 changedWhereMeasuredEffect
add Learnable Retrieval Enhancer (LRE) to baseline (ablation)REVTAF · MIMIC-CXRAvg: 0.369 -> 0.384Improved
add FVTAF module to baseline (ablation)REVTAF · MIMIC-CXRAvg: 0.369 -> 0.383Improved
add both LRE and FVTAF to baseline (ablation)REVTAF · MIMIC-CXRAvg: 0.369 -> 0.397Improved
add FVTAF on top of LRE (ablation)REVTAF · MIMIC-CXRAvg: 0.384 -> 0.397Improved
add LRE on top of FVTAF (ablation)REVTAF · MIMIC-CXRAvg: 0.383 -> 0.397Improved
add LRE and FVTAF (ablation)REVTAF · MIMIC-CXRBLEU-4: 0.159 -> 0.182Improved
add LRE and FVTAF (ablation)REVTAF · MIMIC-CXRCE F1: 0.562 -> 0.592Improved
use REVTAF instead of EKAGenREVTAF · MIMIC-CXRAvg: 0.323 -> 0.397Improved
use REVTAF instead of PromptMRGREVTAF · IU X-RayAvg: 0.222 -> 0.251Improved
use REVTAF instead of GPT-4REVTAF · MIMIC-CXR (16 samples)Avg: 0.192 -> 0.347Improved
use REVTAF instead of GPT-4.5 for inference timeREVTAF · MIMIC-CXR (16 samples)inference time (s): 18.72 -> 3.36Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy