• Computer Science
  • Published in ICCV 2019

nocaps: novel object captioning at scale

@article{Agrawal2019nocapsNO,
  title={nocaps: novel object captioning at scale},
  author={Harsh Agrawal and Karan Desai and Yufei Wang and Rishabh Jain and Xinlei Chen and Dhruv Batra and Mark S Johnson and Devi Parikh and Peter Anderson and Stefan Lee},
  journal={International Conference on Computer Vision},
  year={2019},
  volume={abs/1812.08658}
}
Image captioning models have achieved impressive results on datasets containing limited visual concepts and large amounts of paired image-caption training data. However, if these models are to ever function in the wild, a much larger variety of visual concepts must be learned, ideally from less supervision. To encourage the development of image captioning models that can learn visual concepts from alternative data sources, such as object detection datasets, we present the first large-scale… CONTINUE READING

References

Publications referenced by this paper.
SHOWING 1-10 OF 52 REFERENCES

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

VIEW 12 EXCERPTS
HIGHLY INFLUENTIAL

Deep contextualized word representations

VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Openimages: A public dataset for large-scale multilabel and multi-class image classification

  • Ivan Krasin, Tom Duerig, +16 authors Kevin Murphy
  • Dataset available from https://github.com/openimages,
  • 2017
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Microsoft COCO Captions: Data Collection and Evaluation Server

VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

CIDEr: Consensus-based image description evaluation

VIEW 9 EXCERPTS

Neural Baby Talk

VIEW 10 EXCERPTS

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

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL