 |
Conference papers
Cross-modal classification by completing unimodal representations
Abstract : We argue that cross-modal classification, where models are trained on data from one modality (e.g. text) and applied to data from another (e.g. image), is a relevant problem in multimedia retrieval. We propose a method that addresses this specific problem, related to but different from cross-modal retrieval and bimodal classification. This method relies on a common latent space where both modalities have comparable representations and on an auxiliary dataset from which we build a more complete bimodal representation of any unimodal data. Evaluations on Pascal VOC07 and NUS-WIDE show that the novel representation method significantly improves the results compared to the use of a latent space alone. The level of performance achieved makes cross-modal classification a convincing choice for real applications.
Cited literature [24 references]
https://hal-cea.archives-ouvertes.fr/cea-01840417
Contributor : Léna Le Roy <>
Submitted on : Friday, January 10, 2020 - 4:29:25 PM
Last modification on : Friday, June 25, 2021 - 9:48:07 AM
Contributor : Léna Le Roy <>
Submitted on : Friday, January 10, 2020 - 4:29:25 PM
Last modification on : Friday, June 25, 2021 - 9:48:07 AM
File
ivlm08-tranA.pdf
Files produced by the author(s)