Loading...
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.
Loading...
Name
grangier_rr06-33.pdf
Access type
openaccess
Size
146.37 KB
Format
Adobe PDF
Checksum (MD5)
e54830bf112c1f289d83ee53999f4a67