Distinctive-Attribute Extraction for Image Captioning

Abstract

Image captioning has evolved with the progress of deep neural networks. However, generating qualitatively detailed and distinctive captions is still an open issue. In previous works, a caption involving semantic description can be generated by applying additional information into the RNNs. In this approach, we propose a distinctive-attribute extraction (DaE) method that extracts attributes which explicitly encourage RNNs to generate an accurate caption. We evaluate the proposed method with a challenge data and verify that this method improves the performance, describing images in more detail. The method can be plugged into various models to improve their performance.

Cite

Text

Kim et al. "Distinctive-Attribute Extraction for Image Captioning." European Conference on Computer Vision Workshops, 2018. doi:10.1007/978-3-030-11018-5_12

Markdown

[Kim et al. "Distinctive-Attribute Extraction for Image Captioning." European Conference on Computer Vision Workshops, 2018.](https://mlanthology.org/eccvw/2018/kim2018eccvw-distinctiveattribute/) doi:10.1007/978-3-030-11018-5_12

BibTeX

@inproceedings{kim2018eccvw-distinctiveattribute,
  title     = {{Distinctive-Attribute Extraction for Image Captioning}},
  author    = {Kim, Boeun and Lee, Young Han and Jung, Hyedong and Cho, Choong Sang},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2018},
  pages     = {133-144},
  doi       = {10.1007/978-3-030-11018-5_12},
  url       = {https://mlanthology.org/eccvw/2018/kim2018eccvw-distinctiveattribute/}
}