miscellaneous-3
Multilingual Image-Text Classification
3260 papers • 126 benchmarks • 313 datasets
This task has no description! Would you like to contribute one?
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in multilingual-image-text-classification-3
Trend
Dataset
Best Model
Actions
GLAMI-1M
GLAMI-1M
Libraries
iUse these libraries to find multilingual-image-text-classification-3 models and implementations
Datasets
Subtasks
No subtasks available.
Most implemented papers
GLAMI-1M: A Multilingual Image-Text Fashion Dataset
Milan Šulc, Vaclav Kosar, A. Hoskovec, Radek Bartyzal•Wed Nov 16 2022
We introduce GLAMI-1M: the largest multilingual image-text classification dataset and benchmark. The dataset contains images of fashion products with item descriptions, each in 1 of 13 languages. Categorization into 191 classes has high-quality annotations: all 100k images in the test set and 75% of the 1M training set were human-labeled. The paper presents baselines for image-text classification showing that the dataset presents a challenging fine-grained classification problem: The best scoring EmbraceNet model using both visual and textual features achieves 69.7% accuracy. Experiments with a modified Imagen model show the dataset is also suitable for image generation conditioned on text. The dataset, source code and model checkpoints are published at https://github.com/glami/glami-1m