Image search using multilingual texts: a cross-modal learning approach between image and text

Abstract : Multilingual (or cross-lingual) embeddings represent several languages in a unique vector space. Using a common embedding space enables for a shared semantic between words from different languages. In this paper, we propose to embed images and texts into a unique distributional vector space, enabling to search images by using text queries expressing information needs related to the (visual) content of images, as well as using image similarity. Our framework forces the representation of an image to be similar to the representation of the text that describes it. Moreover, by using multilingual embeddings we ensure that words from two different languages have close descriptors and thus are attached to similar images. We provide experimental evidence of the efficiency of our approach by experimenting it on two datasets: Common Objects in COntext (COCO) [19] and Multi30K [7].
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-02077556
Contributor : Maxime Portaz <>
Submitted on : Monday, March 25, 2019 - 2:34:00 PM
Last modification on : Friday, February 14, 2020 - 12:24:20 PM
Long-term archiving on: Wednesday, June 26, 2019 - 12:37:30 PM

Files

egpaper_for_review.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02077556, version 1
  • ARXIV : 1903.11299

Citation

Maxime Portaz, Hicham Randrianarivo, Adrien Nivaggioli, Estelle Maudet, Christophe Servan, et al.. Image search using multilingual texts: a cross-modal learning approach between image and text. [Research Report] qwant research. 2019. ⟨hal-02077556⟩

Share

Metrics

Record views

163

Files downloads

201