SCIENCE@home

BITCC: A Bidirectional Image–Text Interaction Method for High-Resolution Remote Sensing Image Change Captioning

Yingjie Tang,Shou Feng,Yongqi Chen,Jinghe Zhang,Nan Su,Chunhui Zhao

Published 2025 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

ABSTRACT

High-resolution remote sensing image change captioning (RSICC) aims to understand the change content in bitemporal high-resolution remote sensing images and generate corresponding descriptive captions. By presenting change information in the form of natural language, it makes the information more intuitive and easier to communicate, which has garnered widespread attention. However, there are still two challenges in RSICC: First, most existing methods adopt a unidirectional interaction from images to text, resulting in insufficient semantic alignment between images and text, which limits method's performance. Second, in remote sensing images, there are interfering factors such as illumination and climate, leading to overall differences between bitemporal images, which affect the recognition of change information. To address the aforementioned challenges, this article proposes a bidirectional image–text interaction method for high-resolution RSICC (BITCC). BITCC first introduces the image-to-text interaction component based on reconstruction. This approach along with the caption generation component, forms a bidirectional interaction to enhance the semantic correlation between the local change information of the images and the textual information. To address the issue of global discrepancies between bitemporal images, a noise-based change extractor is designed, which reduces the model's focus on irrelevant factors by adding noise. Finally, the images-and-text interaction component constrains the global representations of both modalities through contrastive alignment, enhancing the global semantic consistency between the image and text in the high-level representation. Experiments on two public datasets show that our method outperforms the current state-of-the-art methods.

PUBLICATION RECORD

  • Publication year

    2025

  • Venue

    IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

  • Publication date

    Unknown publication date

  • Fields of study

    Computer Science, Environmental Science

  • Identifiers
    DOI 10.1109/JSTARS.2025.3629158
  • External record

    Open on Semantic Scholar

  • Source metadata

    Semantic Scholar

CITATION MAP

EXTRACTION MAP

CLAIMS

  • No claims are published for this paper.

CONCEPTS

  • No concepts are published for this paper.

REFERENCES

Showing 1-53 of 53 references · Page 1 of 1

CITED BY

  • No citing papers are available for this paper.

Showing 0-0 of 0 citing papers · Page 1 of 1