Wen et al. (2026) Semantic-Aware Remote Sensing Visual Question Answering via Segmentation-Guided Learning

Identification

• Journal: IEEE Transactions on Geoscience and Remote Sensing
• Year: 2026
• Date: 2026-01-01
• Authors: Shuyi Wen, Aihua Mao, Ran Yi, Yong-Jin Liu
• DOI: 10.1109/tgrs.2026.3663435

Research Groups

[Information not available from the provided text]

Short Summary

This paper introduces a semantic-aware approach for Visual Question Answering (VQA) in remote sensing, leveraging segmentation-guided learning to enhance the understanding and answering capabilities for remote sensing imagery.

Objective

• To develop a novel framework for remote sensing Visual Question Answering that integrates semantic awareness through segmentation-guided learning to improve the accuracy and relevance of answers.

Study Configuration

• Spatial Scale: Remote sensing imagery (e.g., satellite, aerial images).
• Temporal Scale: Not specified, likely static image analysis.

Methodology and Data

• Models used: Visual Question Answering (VQA) models, semantic segmentation models, and deep learning architectures designed for integrating image segmentation information into VQA tasks.
• Data sources: Remote sensing image datasets, potentially annotated with questions, answers, and semantic segmentation masks for training and evaluation.

Main Results

[Information not available from the provided text]

Contributions

[Information not available from the provided text]

Funding

[Information not available from the provided text]

Citation

@article{Wen2026SemanticAware,
  author = {Wen, Shuyi and Mao, Aihua and Yi, Ran and Liu, Yong-Jin},
  title = {Semantic-Aware Remote Sensing Visual Question Answering via Segmentation-Guided Learning},
  journal = {IEEE Transactions on Geoscience and Remote Sensing},
  year = {2026},
  doi = {10.1109/tgrs.2026.3663435},
  url = {https://doi.org/10.1109/tgrs.2026.3663435}
}