Event-enriched image captioning describes not only visible content but also the broader context of events, including timing, location, and participants, capabilities missing in most pixel-bound models. We propose the Contextual Image-Article Narrator (CIAN), a multi-stage framework that enriches captions with external narratives. CIAN retrieves relevant articles using SigLIP, summarizes them to guide a Narrative Generation stage with a LoRA-fine-tuned Qwen model, and applies N-Gram-based Refinement for fluency and coherence. On the OpenEvents-V1 benchmark, CIAN achieves high retrieval performance (mAP 0.979) and improves caption quality, increasing CIDEr from 0.030 to 0.094. These results highlight the effectiveness of retrieval-augmented reasoning combined with linguistic refinement for generating context-aware, human-like captions.

翻译：事件增强图像描述不仅描述可见内容，还涵盖事件更广泛的上下文信息，包括时间、地点和参与者——这些能力是多数基于像素的模型所缺失的。我们提出上下文图像-文章叙述器（CIAN），一种通过外部叙事丰富描述内容的多阶段框架。CIAN 利用 SigLIP 检索相关文章，对其进行摘要以指导基于 LoRA 微调 Qwen 模型的叙事生成阶段，并采用基于 N-Gram 的精炼方法提升流畅性与连贯性。在 OpenEvents-V1 基准上，CIAN 实现了高检索性能（mAP 0.979），同时将 CIDEr 从 0.030 提升至 0.094，显著改善了描述质量。这些结果凸显了结合语言精炼的检索增强推理在生成上下文感知、类人描述方面的有效性。