ReCap：结合文章检索与语义高斯归一化的事件感知图像描述生成
ReCap: Event-Aware Image Captioning with Article Retrieval and Semantic Gaussian Normalization
AI总结：
针对现有图像描述缺失事件级语义的问题，提出融合文章上下文的ReCap流水线，含两阶段检索、上下文提取与带语义高斯归一化的生成模块，在EVENTA 2025挑战赛私有测试集获第2名。
摘要：
图像描述生成系统通常会输出泛化性描述，无法捕捉事件层面的语义信息，而这类语义对新闻报道、数字归档等应用至关重要。我们提出ReCap，一种用于事件增强型图像检索与描述生成的新型流水线，它融合相关文章中的更广泛上下文信息，生成叙事丰富、基于事实的描述。我们的方法解决了标准视觉语言模型的局限性——这类模型通常聚焦可见内容，却缺失时间、社会与历史上下文。ReCap包含三个集成组件：（1）鲁棒的两阶段文章检索系统，使用DINOv2嵌入，先通过全局特征相似度进行初始候选筛选，再通过块级互近邻相似度重排序；（2）上下文提取框架，整合文章摘要、通用描述与原始源元数据中的信息；（3）基于大语言模型的描述生成系统，搭配语义高斯归一化以提升流畅度与相关性。在EVENTA 2025挑战赛赛道1的OpenEvents V1数据集上评估，ReCap取得了0.54666的优异总分，在私有测试集上排名第2。这些结果凸显了ReCap在衔接视觉感知与现实世界知识方面的有效性，为高风险领域的上下文感知图像理解提供了实用解决方案。代码可在https://github.com/Noridom1/EVENTA2025-Event-Enriched-Image-Captioning获取。
英文摘要：
Image captioning systems often produce generic descriptions that fail to capture event-level semantics which are crucial for applications like news reporting and digital archiving. We present ReCap, a novel pipeline for event-enriched image retrieval and captioning that incorporates broader contextual information from relevant articles to generate narrative-rich, factually grounded captions. Our approach addresses the limitations of standard vision-language models that typically focus on visible content while missing temporal, social, and historical contexts. ReCap comprises three integrated components: (1) a robust two-stage article retrieval system using DINOv2 embeddings with global feature similarity for initial candidate selection followed by patch-level mutual nearest neighbor similarity re-ranking; (2) a context extraction framework that synthesizes information from article summaries, generic captions, and original source metadata; and (3) a large language model-based caption generation system with Semantic Gaussian Normalization to enhance fluency and relevance. Evaluated on the OpenEvents V1 dataset as part of Track 1 in the EVENTA 2025 Grand Challenge, ReCap achieved a strong overall score of 0.54666, ranking 2nd on the private test set. These results highlight ReCap's effectiveness in bridging visual perception with real-world knowledge, offering a practical solution for context-aware image understanding in high-stakes domains. The code is available at https://github.com/Noridom1/EVENTA2025-Event-Enriched-Image-Captioning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
