Multiple level visual semantic fusion method for image re-ranking

Shuhan Qi, Fanglin Wang, Xuan Wang, Yue Guan, Jia Wei, Jian Guan

Abstract

Mid-level semantic attributes have obtained some success in image retrieval and re-ranking. However, due to the semantic gap between the low-level feature and intermediate semantic concept, information loss is considerable in the process of converting the low-level feature to semantic concept. To tackle this problem, we tried to bridge the semantic gap by looking for the complementary of different mid-level features. In this paper, a framework is proposed to improve image re-ranking by fusing multiple mid-level features together. The framework contains three mid-level features (DCNN-ImageNet attributes, Fisher vector, sparse coding spatial pyramid matching) and a semi-supervised multigraph-based model that combines these features together. In addition, our framework can be easily extended to utilize arbitrary number of features for image re-ranking. The experiments are conducted on the a-Pascal dataset, and our approach that fuses different features together is able to boost performance of image re-ranking efficiently.
BibTeX
@inproceedings{qi2017multiple,
  author = {Shuhan Qi and Fanglin Wang and Xuan Wang and Yue Guan and Jia Wei and Jian Guan},
  title = {{Multiple level visual semantic fusion method for image re-ranking}},
  booktitle = {Multim. Syst},
  year = {2017},
  url = {https://openreview.net/forum?id=obtJZ2lg68},
}

Loading related content...

Figure