Visual Madlibs: Fill in the Blank Description Generation and Question Answering

@article{Yu2015VisualMF,
  title={Visual Madlibs: Fill in the Blank Description Generation and Question Answering},
  author={Licheng Yu and Eunbyung Park and Alexander C. Berg and Tamara L. Berg},
  journal={2015 IEEE International Conference on Computer Vision (ICCV)},
  year={2015},
  pages={2461-2469}
}
In this paper, we introduce a new dataset consisting of 360,001 focused natural language descriptions for 10,738 images. This dataset, the Visual Madlibs dataset, is collected using automatically produced fill-in-the-blank templates designed to gather targeted descriptions about: people and objects, their appearances, activities, and interactions, as well… CONTINUE READING

11 Figures & Tables

Topics

Statistics

020402015201620172018
Citations per Year

64 Citations

Semantic Scholar estimates that this publication has 64 citations based on the available data.

See our FAQ for additional information.