DisasterTD: Disaster Toponym Disambiguation Using Multimodal LLMs and Cross-View Geolocalization
DisasterTD:使用多模态大语言模型和跨视角地理定位的灾害地名消歧
机构 * College of Geodesy and Geomatics, Shandong University of Science and Technology(山东科技大学测绘与地理信息学院) ; School of Environmental Science and Spatial Informatics, China University of Mining and Technology(中国矿业大学环境与测绘学院) ; State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University(武汉大学测绘遥感信息工程国家重点实验室) ; Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院) ; School of Automation, Southeast University(东南大学自动化学院) ; Department of Geography, National University of Singapore(新加坡国立大学地理系)
专题命中 视觉推理 :MLLM(abstract,abstract_cn);multimodal large language model(abstract);分类 cs.CV、cs.AI
AI总结 研究针对社交媒体图像地理参考模糊问题,提出DisasterTD框架,集成多模态大语言模型语义推理与跨视角地理定位,在飓风哈维数据集上评估,该方法优于基线,能有效进行细粒度灾害地理定位,提升不同距离下的定位准确率并减少误差。