Image automatic annotation via multi-view deep representation

Yang Yang, Wensheng Zhang, Yuan Xie

Abstract

Highlights•A deep neural network is used as a directed supervised classification for mapping image features to keywords.•Stacked auto-encoder is modified by sigmoid predictor and iteration algorithm.•Tag frequencies and properties should be paid attention to during tagging process.•Image sematic features will improve the image annotation performance.•Each keyword has been assigned to the appropriate visual descriptor.
BibTeX
@article{yang2015image,
  author = {Yang Yang and Wensheng Zhang and Yuan Xie},
  title = {{Image automatic annotation via multi-view deep representation}},
  journal = {J. Vis. Commun. Image Represent.},
  year = {2015},
  url = {https://openreview.net/forum?id=YpTp3YlIGR},
}

Loading related content...

Figure