SD-RSIC: Summarization Driven Deep Remote Sensing Image Captioning

@article{Sumbul2020SDRSICSD,
  title={SD-RSIC: Summarization Driven Deep Remote Sensing Image Captioning},
  author={Gencer Sumbul and S. Nayak and B. Demir},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.08432}
}
  • Gencer Sumbul, S. Nayak, B. Demir
  • Published 2020
  • Computer Science
  • ArXiv
  • Deep neural networks (DNNs) have been recently found popular for image captioning problems in remote sensing (RS). Existing DNN based approaches rely on the availability of a training set made up of a high number of RS images with their captions. However, captions of training images may contain redundant information (they can be repetitive or semantically similar to each other), resulting in information deficiency while learning a mapping from image domain to language domain. To overcome this… CONTINUE READING

    Figures and Tables from this paper

    References

    SHOWING 1-10 OF 29 REFERENCES
    Can a Machine Generate Humanlike Language Descriptions for a Remote Sensing Image?
    • Z. Shi, Zhengxia Zou
    • Computer Science
    • IEEE Transactions on Geoscience and Remote Sensing
    • 2017
    • 53
    • PDF
    Exploring Models and Data for Remote Sensing Image Caption Generation
    • 113
    • Highly Influential
    • PDF
    Toward Remote Sensing Image Retrieval Under a Deep Image Captioning Perspective
    • 1
    • PDF
    Deep semantic understanding of high resolution remote sensing image
    • B. Qu, X. Li, D. Tao, Xiaoqiang Lu
    • Computer Science
    • 2016 International Conference on Computer, Information and Telecommunication Systems (CITS)
    • 2016
    • 40
    • Highly Influential
    Semantic Descriptions of High-Resolution Remote Sensing Images
    • 23
    A Comprehensive Survey of Deep Learning for Image Captioning
    • 154
    • PDF
    Topic-Oriented Image Captioning Based on Order-Embedding
    • 11
    Show and tell: A neural image caption generator
    • 3,690
    • Highly Influential
    • PDF
    Rethinking the Inception Architecture for Computer Vision
    • 10,219
    • Highly Influential
    • PDF
    DeViSE: A Deep Visual-Semantic Embedding Model
    • 1,531
    • PDF