PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

A Neural Network to Retrieve Images from Text Queries
David Grangier and Samy Bengio
In: International Conference on Artificial Neural Networks (ICANN), Sept 2006, Athens, Greece.


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.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
Information Retrieval & Textual Information Access
ID Code:2487
Deposited By:David Grangier
Deposited On:22 November 2006