Learning Like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of Images

@article{Mao2015LearningLA,
  title={Learning Like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of Images},
  author={Junhua Mao and Xu Wei and Yi Yang and Jiang Wang and Zhiheng Huang and Alan L. Yuille},
  journal={2015 IEEE International Conference on Computer Vision (ICCV)},
  year={2015},
  pages={2533-2541}
}
  • Junhua Mao, Xu Wei, +3 authors Alan L. Yuille
  • Published 2015
  • Computer Science
  • 2015 IEEE International Conference on Computer Vision (ICCV)
  • In this paper, we address the task of learning novel visual concepts, and their interactions with other concepts, from a few images with sentence descriptions. Using linguistic context and visual features, our method is able to efficiently hypothesize the semantic meaning of new words and add them to its word dictionary so that they can be used to describe images which contain these novel concepts. Our method has an image captioning module based on with several improvements. In particular, we… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Paper Mentions

    BLOG POST

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 111 CITATIONS, ESTIMATED 92% COVERAGE

    Image-Text Surgery: Efficient Concept Learning in Image Captioning by Generating Pseudopairs

    Deep Compositional Captioning: Describing Novel Object Categories without Paired Training Data

    VIEW 8 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Image Captioning With Visual-Semantic Double Attention

    VIEW 2 EXCERPTS
    CITES METHODS

    Captioning Images with Diverse Objects

    VIEW 6 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Pointing Novel Objects in Image Captioning

    VIEW 2 EXCERPTS
    CITES BACKGROUND

    A Semi-supervised Framework for Image Captioning

    VIEW 2 EXCERPTS
    CITES METHODS & BACKGROUND

    Decoupled Novel Object Captioner

    VIEW 1 EXCERPT
    CITES BACKGROUND

    FILTER CITATIONS BY YEAR

    2015
    2020

    CITATION STATISTICS

    • 9 Highly Influenced Citations

    • Averaged 23 Citations per year from 2018 through 2020

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 75 REFERENCES

    From captions to visual concepts and back

    VIEW 1 EXCERPT

    DeViSE: A Deep Visual-Semantic Embedding Model

    Show and tell: A neural image caption generator

    VIEW 3 EXCERPTS

    Deep Visual-Semantic Alignments for Generating Image Descriptions

    VIEW 1 EXCERPT