 The paper proposes a novel Siamese-based Spatial Temporal Attention Neural Network for Remote Sensing Image Change Detection, CD. The proposed method models the spatial temporal relationships between pixels in two coregistered images taken at different times, which improves the performance of CD methods. The self-attention module calculates attention weights between any two pixels at different times and positions to generate more discriminative features. The proposed method is partitioned into multi-scale subregions to capture spatial temporal dependencies at various scales. Experimental results show that the proposed method outperforms several state-of-the-art methods on a public remote sensing image CD dataset. This article was authored by Hao Chen and Zhen Weishu. We are article.tv. Links in the description below.