 |
Conference papers
Aggregating image and text quantized correlated components
Abstract : Cross-modal tasks occur naturally for multimedia content that can be described along two or more modalities like visual content and text. Such tasks require to "translate" information from one modality to another. Methods like kernelized canonical correlation analysis (KCCA) attempt to solve such tasks by finding aligned subspaces in the description spaces of different modalities. Since they favor correlations against modality-specific information, these methods have shown some success in both cross-modal and bi-modal tasks. However, we show that a direct use of the subspace alignment obtained by KCCA only leads to coarse translation abilities. To address this problem, we first put forward a new representation method that aggregates information provided by the projections of both modalities on their aligned subspaces. We further suggest a method relying on neighborhoods in these subspaces to complete uni-modal information. Our proposal exhibits state-of-the-art results for bi-modal classification on Pascal VOC07 and improves it by over 60% for cross-modal retrieval on FlickR 8K/30K.
Cited literature [30 references]
https://hal-cea.archives-ouvertes.fr/cea-01843176
Contributor : Léna Le Roy <>
Submitted on : Friday, January 10, 2020 - 4:25:38 PM
Last modification on : Friday, June 25, 2021 - 9:48:07 AM
Contributor : Léna Le Roy <>
Submitted on : Friday, January 10, 2020 - 4:25:38 PM
Last modification on : Friday, June 25, 2021 - 9:48:07 AM
File
Tran_Aggregating_Image_and_CVP...
Publisher files allowed on an open archive
Licence
Distributed under a Creative Commons Attribution 4.0 International License