{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/recipe1m-a-dataset-for-learning-cross-modal","title":"Recipe1M+: A Dataset for Learning Cross-Modal Embeddings for Cooking Recipes and Food Images","arxiv_id":"1810.06553","date":"2018-10-14","proceeding":null,"authors":["Javier Marin","Aritro Biswas","Ferda Ofli","Nicholas Hynes","Amaia Salvador","Yusuf Aytar","Ingmar Weber","Antonio Torralba"],"abstract":"In this paper, we introduce Recipe1M+, a new large-scale, structured corpus of over one million cooking recipes and 13 million food images. As the largest publicly available collection of recipe data, Recipe1M+ affords the ability to train high-capacity modelson aligned, multimodal data. Using these data, we train a neural network to learn a joint embedding of recipes and images that yields impressive results on an image-recipe retrieval task. Moreover, we demonstrate that regularization via the addition of a high-level classification objective both improves retrieval performance to rival that of humans and enables semantic vector arithmetic. We postulate that these embeddings will provide a basis for further exploration of the Recipe1M+ dataset and food and cooking in general. Code, data and models are publicly available.","url_abs":"https://arxiv.org/abs/1810.06553v2","url_pdf":"https://arxiv.org/pdf/1810.06553v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"cross-modal-retrieval","task_name":"Cross-Modal Retrieval"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[{"slug":"recipe1m-1","name":"Recipe1M+","full_name":"Recipe1M+"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/cross-modal-retrieval-on-recipe1m-1","task":"Cross-Modal Retrieval","dataset":"Recipe1M+","model":"Marin et al.","rank_in_archive_order":2,"of":2,"metrics":{"Image-to-text R@1":"17","Text-to-image R@1":"21"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1810.06553","atlas_url":"https://app.syntology.ai/?focus=1810.06553","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}