Papers › GLAMI-1M: A Multilingual Image-Text Fashion Dataset
GLAMI-1M: A Multilingual Image-Text Fashion Dataset
Vaclav Kosar, Antonín Hoskovec, Milan Šulc, Radek Bartyzal
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
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Datasets
Introduced by this paper, per the archive.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Multilingual Image-Text Classification | GLAMI-1M | EmbraceNet (image+text) | Top 1 Accuracy % | 69.7 | #1 of 2 | Archive leaderboard | report |
| Multilingual Image-Text Classification | GLAMI-1M | EmbraceNet (image+text) | Top 5 Accuracy % | 94.0 | #1 of 2 | Archive leaderboard | report |
| Multilingual Image-Text Classification | GLAMI-1M | CLIP (zero-shot image+text) | Top 1 Accuracy % | 32.3 | #2 of 2 | Archive leaderboard | report |
| Multilingual Image-Text Classification | GLAMI-1M | CLIP (zero-shot image+text) | Top 5 Accuracy % | 74.5 | #2 of 2 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections