Author name: Ting Han, Fengjiao Li, Chunsong Chen, Haoling Huang, Yiping Chen, Meiliu Wu

arXiv:2604.04357v1 Announce Type: new
Abstract: This paper proposes Spatially-Weighted CLIP (SW-CLIP), a novel framework for street-view geo-localization that explicitly incorporates spatial autocorrelation into vision-language contrastive learning. U…