DVGBench: Implicit-to-Explicit Visual Grounding Benchmark in UAV Imagery with Large Vision-Language Models
DVGBench: 面向无人机影像的隐式到显式视觉 grounding 评估基准
机构 * Hinton STAI Institute(Hinton STAI研究所) ; Key Laboratory of Geographic Information Science (Ministry of Education), East China Normal University(地理信息科学重点实验室(教育部)) ; School of Geospatial Artificial Intelligence, East China Normal University(地理空间人工智能学院) ; Zhejiang University(浙江大学) ; Shanghai Jiao Tong University(上海交通大学) ; Information Engineering University(信息工程大学)
专题命中 视觉定位与Grounding :vision-language model(title,abstract);grounding(title,abstract);分类 cs.CV
AI总结 DVGBench 是一个面向无人机影像的隐式到显式视觉 grounding 评估基准,通过设计 DroneVG-R1 模型提升 LVLM 的推理能力。
Comments 20 pages, 17 figures