Corpus ID: 216080825

Visual Commonsense Graphs: Reasoning about the Dynamic Context of a Still Image

@article{Park2020VisualCG,
  title={Visual Commonsense Graphs: Reasoning about the Dynamic Context of a Still Image},
  author={Jae Sung Park and Chandra Bhagavatula and Roozbeh Mottaghi and Ali Farhadi and Yejin Choi},
  journal={ArXiv},
  year={2020},
  volume={abs/2004.10796}
}
  • Jae Sung Park, Chandra Bhagavatula, +2 authors Yejin Choi
  • Published 2020
  • Computer Science
  • ArXiv
  • Even from a single frame of a still image, people can reason about the dynamic story of the image before, after, and beyond the frame. For example, given an image of a man struggling to stay afloat in water, we can reason that the man fell into the water sometime in the past, the intent of that man at the moment is to stay alive, and he will need help in the near future or else he will get washed away. We propose VisualComet, the novel framework of visual commonsense reasoning tasks to predict… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 55 REFERENCES

    From Recognition to Cognition: Visual Commonsense Reasoning

    VIEW 6 EXCERPTS

    Learning Common Sense through Visual Abstraction

    VIEW 1 EXCERPT

    Visual Dialog

    VIEW 1 EXCERPT

    VQA: Visual Question Answering

    VIEW 1 EXCERPT

    OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge

    VIEW 1 EXCERPT

    Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models

    VIEW 1 EXCERPT

    Show and tell: A neural image caption generator

    VIEW 1 EXCERPT

    Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering

    VIEW 2 EXCERPTS