Joint Image and Word Sense Discrimination for Image Retrieval
Abstract
We study the task of learning to rank images given a text query, a problem that is complicated by the issue of multiple senses. That is, the senses of interest are typically the visually distinct concepts that a user wishes to retrieve. In this paper, we propose to learn a ranking function that optimizes the ranking cost of interest and simultaneously discovers the disambiguated senses of the query that are optimal for the supervised task. Note that no supervised information is given about the senses. Experiments performed on web images and the ImageNet dataset show that using our approach leads to a clear gain in performance.
Cite
Text
Lucchi and Weston. "Joint Image and Word Sense Discrimination for Image Retrieval." European Conference on Computer Vision, 2012. doi:10.1007/978-3-642-33718-5_10Markdown
[Lucchi and Weston. "Joint Image and Word Sense Discrimination for Image Retrieval." European Conference on Computer Vision, 2012.](https://mlanthology.org/eccv/2012/lucchi2012eccv-joint/) doi:10.1007/978-3-642-33718-5_10BibTeX
@inproceedings{lucchi2012eccv-joint,
title = {{Joint Image and Word Sense Discrimination for Image Retrieval}},
author = {Lucchi, Aurélien and Weston, Jason},
booktitle = {European Conference on Computer Vision},
year = {2012},
pages = {130-143},
doi = {10.1007/978-3-642-33718-5_10},
url = {https://mlanthology.org/eccv/2012/lucchi2012eccv-joint/}
}