Adaptive all-season image tag ranking by saliency-driven image pre-classification

Songhe Feng, Congyan Lang, Hongzhe Liu, Xiankai Huang

Abstract

Highlights•An all-season tag ranking framework is proposed to handle images with and without distinct objects.•A simple gray histogram descriptor is proposed to describe the saliency map for image pre-classification.•Sparse representation based neighbor voting strategy is proposed for tag relevance ranking.•Combining sparse representation driven MIL algorithm with visual attention model is proposed to fulfill tag saliency ranking.
BibTeX
@article{feng2013adaptive,
  author = {Songhe Feng and Congyan Lang and Hongzhe Liu and Xiankai Huang},
  title = {{Adaptive all-season image tag ranking by saliency-driven image pre-classification}},
  journal = {J. Vis. Commun. Image Represent.},
  year = {2013},
  doi = {10.1016/j.jvcir.2013.06.018},
}

Loading related content...

Figure