Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
CityToolVQA: Tool-Augmented Visual Question Answering for 3D Spatial Cognition in Urban Low-Altitude Environments
Boao Yu, Yingzhen Nie, Yue Hu +2
CityToolVQA addresses the weak performance of Vision-Language Models (VLMs) on quantitative tasks in urban low-altitude visual question answering. We divide the seven tasks into qu…
cs.CV2026
Towards Embodied Air-Ground Cooperative Object Search: Benchmark, Dataset and Agentic Method
Boao Yu, Zimo Chen, Junreng Rao +4
Air-Ground Object Search (AGOS) in urban environments is a challenging embodied task, which requires an Unmanned Aerial Vehicle (UAV) and an Unmanned Ground Vehicle (UGV) to jointl…