Corpus ID: 220713307

Comprehensive Image Captioning via Scene Graph Decomposition

@article{Zhong2020ComprehensiveIC,
  title={Comprehensive Image Captioning via Scene Graph Decomposition},
  author={Yiwu Zhong and Liwei Wang and J. Chen and Dong Yu and Yanchao Li},
  journal={ArXiv},
  year={2020},
  volume={abs/2007.11731}
}
  • Yiwu Zhong, Liwei Wang, +2 authors Yanchao Li
  • Published 2020
  • Computer Science
  • ArXiv
  • We address the challenging problem of image captioning by revisiting the representation of image scene graph. At the core of our method lies the decomposition of a scene graph into a set of subgraphs, with each sub-graph capturing a semantic component of the input image. We design a deep model to select important sub-graphs, and to decode each selected sub-graph into a single target sentence. By using sub-graphs, our model is able to attend to different components of the image. Our method thus… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Explore Further: Topics Discussed in This Paper

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 67 REFERENCES
    Scene Graph Generation from Objects, Phrases and Region Captions
    168
    Auto-Encoding Scene Graphs for Image Captioning
    87
    Exploring Visual Relationship for Image Captioning
    185
    Dense Captioning with Joint Inference and Visual Context
    50
    Obj2Text: Generating Visually Descriptive Language from Object Layouts
    26
    DenseCap: Fully Convolutional Localization Networks for Dense Captioning
    679
    Dense Relational Captioning: Triple-Stream Networks for Relationship-Based Captioning
    11
    Fast, Diverse and Accurate Image Captioning Guided by Part-Of-Speech
    21
    A Comprehensive Survey of Deep Learning for Image Captioning
    93