A Neural Network to Retrieve Images from Text Queries

David Grangier, Samy Bengio

Abstract

This work presents a neural network for the retrieval of images from text queries. The proposed network is composed of two main modules: the first one extracts a global picture representation from local block descriptors while the second one aims at solving the retrieval problem from the extracted representation. Both modules are trained jointly to minimize a loss related to the retrieval performance. This approach is shown to be advantageous when compared to previous models relying on unsupervised feature extraction: average precision over Corel queries reaches 26.2% for our model, which should be compared to 21.6% for PAMIR, the best alternative.
BibTeX
@inproceedings{grangier2006neural,
  author = {David Grangier and Samy Bengio},
  title = {{A Neural Network to Retrieve Images from Text Queries}},
  booktitle = {ICANN},
  year = {2006},
  doi = {10.1007/11840930\_3},
}

Loading related content...

Figure