DetectiumFire：连接视觉与语言以理解火灾的综合多模态数据集
DetectiumFire: A Comprehensive Multi-modal Dataset Bridging Vision and Language for Fire Understanding
AI总结：
本文提出大规模多模态数据集DetectiumFire，包含2.25万张火灾图像和2.5千个视频，结合视觉标签与文本提示，支持目标检测、图像生成及视觉语言推理等任务，推动火灾智能安全系统研究。
摘要：
多模态模型的最新进展在图像生成和推理等任务中展现出强大性能。然而，由于缺乏带有高质量火灾领域标注的公开数据集，将这些模型应用于火灾领域仍具挑战。为填补这一空白，我们引入了DetectiumFire，这是一个大规模多模态数据集，包含2.25万张高分辨率火灾相关图像和2.5千个真实世界火灾相关视频，涵盖多种火灾类型、环境和风险等级。数据标注了传统计算机视觉标签（如边界框）和描述场景的详细文本提示，支持合成数据生成和火灾风险推理等应用。DetectiumFire在规模、多样性和数据质量上优于现有基准，显著减少冗余并增强真实世界场景的覆盖。我们在目标检测、基于扩散的图像生成和视觉语言推理等多个任务上验证了DetectiumFire的实用性。结果表明该数据集有望推动火灾相关研究并支持智能安全系统的开发。我们发布DetectiumFire以促进AI社区对火灾理解的更广泛探索。数据集获取地址：https://kaggle.com/datasets/38b79c344bdfc55d1eed3d22fbaa9c31fad45e27edbbe9e3c529d6e5c4f93890
英文摘要：
Recent advances in multi-modal models have demonstrated strong performance in tasks such as image generation and reasoning. However, applying these models to the fire domain remains challenging due to the lack of publicly available datasets with high-quality fire domain annotations. To address this gap, we introduce DetectiumFire, a large-scale, multi-modal dataset comprising of 22.5k high-resolution fire-related images and 2.5k real-world fire-related videos covering a wide range of fire types, environments, and risk levels. The data are annotated with both traditional computer vision labels (e.g., bounding boxes) and detailed textual prompts describing the scene, enabling applications such as synthetic data generation and fire risk reasoning. DetectiumFire offers clear advantages over existing benchmarks in scale, diversity, and data quality, significantly reducing redundancy and enhancing coverage of real-world scenarios. We validate the utility of DetectiumFire across multiple tasks, including object detection, diffusion-based image generation, and vision-language reasoning. Our results highlight the potential of this dataset to advance fire-related research and support the development of intelligent safety systems. We release DetectiumFire to promote broader exploration of fire understanding in the AI community. The dataset is available at https://kaggle.com/datasets/38b79c344bdfc55d1eed3d22fbaa9c31fad45e27edbbe9e3c529d6e5c4f93890
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。
