{"url":"/dataset/recipe1m-1","name":"Recipe1M+","full_name":"Recipe1M+","description_markdown":"**Recipe1M+** is a dataset which contains one million structured cooking recipes with 13M associated images.\r\n\r\nSource: [Recipe1M+: A Dataset for Learning Cross-Modal Embeddings for Cooking Recipes and Food Images](http://im2recipe.csail.mit.edu/)\r\nImage Source: [http://im2recipe.csail.mit.edu/](http://im2recipe.csail.mit.edu/)","description_withheld":null,"homepage":"http://im2recipe.csail.mit.edu/","introduced_date":"2018-10-14","introduced_date_note":null,"introduced_by":{"paper":"/paper/recipe1m-a-dataset-for-learning-cross-modal","title":"Recipe1M+: A Dataset for Learning Cross-Modal Embeddings for Cooking Recipes and Food Images","first_author":"Javier Marin","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Image Generation","url":"/task/image-generation","datasets_with_task":"/datasets/task/image-generation"},{"name":"Cross-Modal Retrieval","url":"/task/cross-modal-retrieval","datasets_with_task":"/datasets/task/cross-modal-retrieval"},{"name":"Recipe Generation","url":"/task/recipe-generation","datasets_with_task":"/datasets/task/recipe-generation"},{"name":"Food Recognition","url":"/task/food-recognition","datasets_with_task":"/datasets/task/food-recognition"}],"languages":[],"variants":["Recipe1M","Recipe1M+"],"data_loaders":[{"repo":"https://github.com/reneelu0314/Project","url":"https://github.com/reneelu0314/Project","frameworks":["tf","pytorch"]}],"num_papers_in_archive":68,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/cross-modal-retrieval-on-recipe1m","task":"Cross-Modal Retrieval","dataset_variant":"Recipe1M","rows":9,"metrics":["Image-to-text R@1","Text-to-image R@1"],"first_row_in_archive_order":{"model":"VLPCook (R1M+)","paper":"/paper/structured-vision-language-pretraining-for","metrics":{"Image-to-text R@1":"74.9","Text-to-image R@1":"75.6"},"code_links":[{"title":"mshukor/vlpcook","url":"https://github.com/mshukor/vlpcook"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/cross-modal-retrieval-on-recipe1m-1","task":"Cross-Modal Retrieval","dataset_variant":"Recipe1M+","rows":2,"metrics":["Image-to-text R@1","Text-to-image R@1"],"first_row_in_archive_order":{"model":"VLPCook","paper":"/paper/structured-vision-language-pretraining-for","metrics":{"Image-to-text R@1":"45.2","Text-to-image R@1":"47.3"},"code_links":[{"title":"mshukor/vlpcook","url":"https://github.com/mshukor/vlpcook"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/recipe-generation-on-recipe1m","task":"Recipe Generation","dataset_variant":"Recipe1M","rows":1,"metrics":["F1","Mean IoU"],"first_row_in_archive_order":{"model":"Set Transformer","paper":"/paper/inverse-cooking-recipe-generation-from-food","metrics":{"F1":"48.61","Mean IoU":"32.11"},"code_links":[{"title":"facebookresearch/inversecooking","url":"https://github.com/facebookresearch/inversecooking"},{"title":"ritvikmath/nlp-recipe-project","url":"https://github.com/ritvikmath/nlp-recipe-project"},{"title":"krutikabapat/Inverse_Cooking_recipe_Generation_from_food_images","url":"https://github.com/krutikabapat/Inverse_Cooking_recipe_Generation_from_food_images"},{"title":"rishi00789/Food-AI","url":"https://github.com/rishi00789/Food-AI"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/structured-vision-language-pretraining-for","title":"Vision and Structured-Language Pretraining for Cross-Modal Food Retrieval","date":"2022-12-08","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/transformer-decoders-with-multimodal","title":"Transformer Decoders with MultiModal Regularization for Cross-Modal Food Retrieval","date":"2022-04-20","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/revamping-cross-modal-recipe-retrieval-with","title":"Revamping Cross-Modal Recipe Retrieval with Hierarchical Transformers and Self-supervised Learning","date":"2021-03-24","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":3,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/cross-modal-retrieval-and-synthesis-x-mrs","title":"Cross-Modal Retrieval and Synthesis (X-MRS): Closing the Modality Gap in Shared Representation Learning","date":"2020-12-02","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/cross-modal-food-retrieval-learning-a-joint","title":"Cross-Modal Food Retrieval: Learning a Joint Embedding of Food Images and Recipes with Semantic Consistency and Attention Mechanism","date":"2020-03-09","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-cross-modal-embeddings-with","title":"Learning Cross-Modal Embeddings with Adversarial Networks for Cooking Recipes and Food Images","date":"2019-05-03","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/inverse-cooking-recipe-generation-from-food","title":"Inverse Cooking: Recipe Generation from Food Images","date":"2018-12-14","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/recipe1m-a-dataset-for-learning-cross-modal","title":"Recipe1M+: A Dataset for Learning Cross-Modal Embeddings for Cooking Recipes and Food Images","date":"2018-10-14","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/cross-modal-retrieval-in-the-cooking-context","title":"Cross-Modal Retrieval in the Cooking Context: Learning Semantic Text-Image Embeddings","date":"2018-04-30","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":4,"samples_ran":3,"samples_unverified":1,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}