Multilingual visual semantic similarity
This work is the implementation of the paper : https://arxiv.org/abs/1903.11299 Image search using multilingual texts: a cross-modal learning approach between image and text Portaz et al. 2019
This can be used to reproduce every experiments in the paper.
With Multi30K dataset, to learn English, French, German and Czech.
This is a fork from : https://github.com/technicolor-research/dsve-loc
This code is written in python. All dependencies are in the Dockerfile. It will automatically install:
- Python 3.7
- Pytorch 1.0
- Ms Coco API (pycocotools)
An environment file for conda is available in the repository (environment.yml).
See notebooks for how to use it.