Our lab member Zeping Liu, 2nd year PhD student just publishes a paper named: “GAIR: Location-aware self-supervised contrastive pre-training with geo-aligned implicit representations” on ISPRS Journal of Photogrammetry and Remote Sensing.
This work introduces a novel multimodal geospatial representation learning framework that aligns remote sensing imagery, street-view images, and geographic location information—three modalities with fundamentally different characteristics and spatial scales—into a unified embedding space. By learning geo-aligned representations across these modalities, the framework enables more effective cross-modal understanding and transfer for a wide range of geospatial AI applications.
Congratulations to Zeping on this exciting achievement!