通过关键词组对比奖励细粒度图像描述

Ye 等人（周四，）研究了该问题。

www.synapsesocial.com/papers/69a75d68c6e9836116a276f5 — DOI: https://doi.org/10.1016/j.eswa.2026.131405

Also consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

1. Efficiently Gluing Pre-Trained Language and Vision Models for Image Captioning· 2024 · 9 citations
2. Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations· 2017 · 5,147 citations
3. SAMT-generator: A second-attention for image captioning based on multi-stage transformer network· 2024 · 48 citations
4. Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning