Image Representations and New Domains in Neural Image Captioning

@inproceedings{Hessel2015ImageRA,
  title={Image Representations and New Domains in Neural Image Captioning},
  author={Jack Hessel and Nicolas Savva and Michael J. Wilber},
  booktitle={VL@EMNLP},
  year={2015}
}
We examine the possibility that recent promising results in automatic caption generation are due primarily to language models. By varying image representation quality produced by a convolutional neural network, we find that a state-of-the-art neural captioning algorithm is able to produce quality captions even when provided with surprisingly poor image representations. We replicate this result in a new, fine-grained, transfer learned captioning domain, consisting of 66K recipe image/title pairs… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-9 OF 9 CITATIONS

Being a Supercook: Joint Food Attributes and Multimodal Content Modeling for Recipe Retrieval and Exploration

  • IEEE Transactions on Multimedia
  • 2017
VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Coping with Overfitting Problems of Image Caption Models for Service Robotics Applications

  • 2019 IEEE International Conference on Industrial Cyber Physical Systems (ICPS)
  • 2019
VIEW 1 EXCERPT
CITES BACKGROUND

References

Publications referenced by this paper.
SHOWING 1-10 OF 29 REFERENCES

Microsoft COCO: Common Objects in Context

Tsung-Yi Lin, Michael Maire, +5 authors C. Lawrence Zitnick
  • ECCV
  • 2014
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Show and tell: A neural image caption generator

  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2014
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

CIDEr: Consensus-based image description evaluation

  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2014
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Deep visualsemantic alignments for generating image descriptions

Andrej Karpathy, Fei-Fei Li.
  • arXiv preprint arXiv:1412.2306.
  • 2014
VIEW 1 EXCERPT