🏢 Department of Computer Science and Engineering, Washington University in St. Louis
GOMAA-Geo: GOal Modality Agnostic Active Geo-localization
·3664 words·18 mins·
loading
·
loading
Multimodal Learning
Vision-Language Models
🏢 Department of Computer Science and Engineering, Washington University in St. Louis
GOMAA-Geo, a novel framework, enables efficient and accurate goal localization using aerial imagery, regardless of goal description modality (text or images), demonstrating impressive zero-shot genera…