EUVIMEDEUVIMED entdecken
Crossref

Adaptive Scale-Aware Semantic Memory Network for Remote Sensing Image Captioning

Cheng Zhang, Zhongle Ren, Biao Hou, Changhui Xu, Jianhua Meng, Weibin Li, Licheng Jiao

IEEE Transactions on Geoscience and Remote Sensing · 2025 · 63 · 1-18

DOI: 10.1109/tgrs.2025.3636596 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Geoscience and Remote Sensing, 2025. Verfasst von Cheng Zhang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 86 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Key Technology Research Program in Shaanxi Province of China, “Scientists + Engineers” Project of Qin Chuangyuan in Shaanxi Province of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Remote sensing image captioning between visual images and natural language remains a long-standing challenge in the remote sensing community. Due to the wide coverage and large amount of information in remote sensing images, existing methods struggle to effectively utilize the relevant semantic information about objects and their attributes at different scales across samples to generate descriptions. To address these issues, the article proposes a novel adaptive scale-aware semantic memory network (ASSMN) for remote sensing image captioning. First, to fully extract the semantic information in remote sensing images, multilevel feature enhancement is constructed to improve the feature representation extracted from the contrastive language-image pretraining (CLIP) pretraining model. Subsequently, a scale-aware attention aggregator (SAA) is introduced to further integrate the enhanced multiscale image features into the high-level semantics of remote sensing images. Then, to fully exploit the semantic information of the joint observed samples, a semantic memory reinforcement (SMR) is designed to strengthen the semantic representation of the current scene through the relevant semantics obtained from other training samples. Finally, a captioning decoder is performed to generate a comprehensive scene caption with accurate objects and attributes. In the experiments, the performance of the proposed ASSMN on three remote sensing image captioning datasets is evaluated and compared with well-designed baselines and state-of-the-art methods, and the superiority of the proposed method is demonstrated by ablating the role of each proposed component. The code will be available at https://github.com/zcsisiyao/ASSMN

Förderung

  • National Natural Science Foundation of China
  • Key Technology Research Program in Shaanxi Province of China
  • “Scientists + Engineers” Project of Qin Chuangyuan in Shaanxi Province of China

Zitieren

APA

Zhang, C., Ren, Z., Hou, B., Xu, C., Meng, J., Li, W., & Jiao, L. (2025). Adaptive Scale-Aware Semantic Memory Network for Remote Sensing Image Captioning. IEEE Transactions on Geoscience and Remote Sensing, 63, 1-18. https://doi.org/10.1109/tgrs.2025.3636596

Vancouver

Zhang C, Ren Z, Hou B, Xu C, Meng J, Li W, et al. Adaptive Scale-Aware Semantic Memory Network for Remote Sensing Image Captioning. IEEE Transactions on Geoscience and Remote Sensing. 2025;63:1-18. doi:10.1109/tgrs.2025.3636596

BibTeX
@article{Zhang2025,
  author = {Zhang, Cheng and Ren, Zhongle and Hou, Biao and Xu, Changhui and Meng, Jianhua and Li, Weibin and Jiao, Licheng},
  title = {Adaptive Scale-Aware Semantic Memory Network for Remote Sensing Image Captioning},
  journal = {IEEE Transactions on Geoscience and Remote Sensing},
  year = {2025},
  volume = {63},
  pages = {1--18},
  doi = {10.1109/tgrs.2025.3636596}
}
Kostenlos starten →