datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
polyvore-outfits
Polyvore Outfits Dataset
📄 Paper
💻 Code
📬 Contact
t-SNE visualization of item embeddings.
Outfit compatibility graph structure.
📌 Access Requirements
Access to this dataset is restricted and intended solely for academic and non-profit research purposes.
By requesting and downloading this dataset, you acknowledge and agree to the following:
Approval required: Access should be requested using an… See the full description on the dataset page: https://huggingface.co/datasets/mvasil/polyvore-outfits.polyvoreDisclaimer: We do not own this dataset. Polyvore dataset is a public dataset which can be accessed through its Github page.
This dataset was used to evaluate Marqo-FashionCLIP and Marqo-FashionSigLIP - see details below.
Marqo-FashionSigLIP Model Card
Marqo-FashionSigLIP leverages Generalised Contrastive Learning (GCL) which allows the model to be trained on not just text descriptions but also categories, style, colors, materials, keywords and fine-details to provide highly relevant… See the full description on the dataset page: https://huggingface.co/datasets/Marqo/polyvore.polyvore
📜 Citation & Original Work
This is a refactored version of the work by Vasileva et al. If you use this dataset, please cite the original paper:
@misc{vasileva2018learningtypeawareembeddingsfashion,
title={Learning Type-Aware Embeddings for Fashion Compatibility},
author={Mariya I. Vasileva and Bryan A. Plummer and Krishna Dusad and Shreya Rajpal and Ranjitha Kumar and David Forsyth},
year={2018},
eprint={1803.09196},
archivePrefix={arXiv}… See the full description on the dataset page: https://huggingface.co/datasets/owj0421/polyvore.polyvore1000=====================README====================
Polyvore-1000 Dataset
Welcome! I am Waly NGOM, PhD in Mathematics and passionate about Artificial Intelligence. This repository contains Polyvore-1000, a dataset designed for personalized recommendation in the fashion domain.
Polyvore-1000 builds upon the Polyvore-U splits introduced by Han et al. (2017) and benefits from the complementary work of Lu et al. (CVPR 2019), who proposed an innovative binary-code based approach for… See the full description on the dataset page: https://huggingface.co/datasets/codewaly/polyvore1000.Polyvore_images2polyvore-gift-conciergePolyvore_test_Fawaz