{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":9,"of":9,"counts":{"papers_with_a_benchmark_row":9,"with_a_code_link":6,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":9,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/structured-vision-language-pretraining-for","slug":"structured-vision-language-pretraining-for","title":"Vision and Structured-Language Pretraining for Cross-Modal Food Retrieval","date":"2022-12-08","arxiv_id":"2212.04267","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/transformer-decoders-with-multimodal","slug":"transformer-decoders-with-multimodal","title":"Transformer Decoders with MultiModal Regularization for Cross-Modal Food Retrieval","date":"2022-04-20","arxiv_id":"2204.09730","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/revamping-cross-modal-recipe-retrieval-with","slug":"revamping-cross-modal-recipe-retrieval-with","title":"Revamping Cross-Modal Recipe Retrieval with Hierarchical Transformers and Self-supervised Learning","date":"2021-03-24","arxiv_id":"2103.13061","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":3,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["amzn/image-to-recipe-transformers"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/revamping-cross-modal-recipe-retrieval-with#ran","syntology_url":"https://syntology.ai/paper/2103.13061","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.13061"}}}},{"paper":"/paper/cross-modal-retrieval-and-synthesis-x-mrs","slug":"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","arxiv_id":"2012.01345","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/cross-modal-food-retrieval-learning-a-joint","slug":"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","arxiv_id":"2003.03955","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-cross-modal-embeddings-with","slug":"learning-cross-modal-embeddings-with","title":"Learning Cross-Modal Embeddings with Adversarial Networks for Cooking Recipes and Food Images","date":"2019-05-03","arxiv_id":"1905.01273","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/inverse-cooking-recipe-generation-from-food","slug":"inverse-cooking-recipe-generation-from-food","title":"Inverse Cooking: Recipe Generation from Food Images","date":"2018-12-14","arxiv_id":"1812.06164","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/recipe1m-a-dataset-for-learning-cross-modal","slug":"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","arxiv_id":"1810.06553","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/cross-modal-retrieval-in-the-cooking-context","slug":"cross-modal-retrieval-in-the-cooking-context","title":"Cross-Modal Retrieval in the Cooking Context: Learning Semantic Text-Image Embeddings","date":"2018-04-30","arxiv_id":"1804.11146","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/structured-vision-language-pretraining-for","slug":"structured-vision-language-pretraining-for","title":"Vision and Structured-Language Pretraining for Cross-Modal Food Retrieval","date":"2022-12-08","arxiv_id":"2212.04267","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/transformer-decoders-with-multimodal","slug":"transformer-decoders-with-multimodal","title":"Transformer Decoders with MultiModal Regularization for Cross-Modal Food Retrieval","date":"2022-04-20","arxiv_id":"2204.09730","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/revamping-cross-modal-recipe-retrieval-with","slug":"revamping-cross-modal-recipe-retrieval-with","title":"Revamping Cross-Modal Recipe Retrieval with Hierarchical Transformers and Self-supervised Learning","date":"2021-03-24","arxiv_id":"2103.13061","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":3,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["amzn/image-to-recipe-transformers"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/revamping-cross-modal-recipe-retrieval-with#ran","syntology_url":"https://syntology.ai/paper/2103.13061","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.13061"}}}},{"paper":"/paper/cross-modal-retrieval-and-synthesis-x-mrs","slug":"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","arxiv_id":"2012.01345","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/cross-modal-food-retrieval-learning-a-joint","slug":"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","arxiv_id":"2003.03955","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-cross-modal-embeddings-with","slug":"learning-cross-modal-embeddings-with","title":"Learning Cross-Modal Embeddings with Adversarial Networks for Cooking Recipes and Food Images","date":"2019-05-03","arxiv_id":"1905.01273","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/inverse-cooking-recipe-generation-from-food","slug":"inverse-cooking-recipe-generation-from-food","title":"Inverse Cooking: Recipe Generation from Food Images","date":"2018-12-14","arxiv_id":"1812.06164","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/recipe1m-a-dataset-for-learning-cross-modal","slug":"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","arxiv_id":"1810.06553","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/cross-modal-retrieval-in-the-cooking-context","slug":"cross-modal-retrieval-in-the-cooking-context","title":"Cross-Modal Retrieval in the Cooking Context: Learning Semantic Text-Image Embeddings","date":"2018-04-30","arxiv_id":"1804.11146","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"papers_where_code_ran":1,"papers_where_code_ran_first_page":"/dataset/recipe1m-1/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/recipe1m-1/papers/ran/1","json":"/dataset/recipe1m-1/papers/ran/1.json","rows":1}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":1,"samples_harvested":4,"samples_ran":3,"samples_constructed":3,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":1,"papers_with_a_run_with_no_instrument_failure":1,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"081b79fc1e213b6519b2ee006e9d1c1077a768477d65d45c5b275bfa1929b24f","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}