Echo: Generating cross-modal features for unseen classes in zero-shot remote sensing image captioning

Kangda Cheng, Jinlong Liu, Rui Mao 0010, Zhilu Wu, Erik Cambria. Echo: Generating cross-modal features for unseen classes in zero-shot remote sensing image captioning. Information Fusion, 128:103952, 2026. [doi]

Abstract

Abstract is missing.