Difference-Aware Multi-Grained Feature Learning With Memory-Attended Joint Interaction Transformer for Image Difference Captioning.
Image Difference Captioning (IDC) aims to describe semantic changes between a pair of similar images using natural language. Most existing approaches rely on off-the-shelf visual backbones to extract features from image pairs. However, these backbones, pre-trained for single-image understanding, often struggle to captu...