{"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/generating-images-from-captions-with","title":"Generating Images from Captions with Attention","arxiv_id":"1511.02793","date":"2015-11-09","proceeding":null,"authors":["Elman Mansimov","Emilio Parisotto","Jimmy Lei Ba","Ruslan Salakhutdinov"],"abstract":"Motivated by the recent progress in generative models, we introduce a model\nthat generates images from natural language descriptions. The proposed model\niteratively draws patches on a canvas, while attending to the relevant words in\nthe description. After training on Microsoft COCO, we compare our model with\nseveral baseline generative models on image generation and retrieval tasks. We\ndemonstrate that our model produces higher quality samples than other\napproaches and generates images with novel scene compositions corresponding to\npreviously unseen captions in the dataset.","url_abs":"http://arxiv.org/abs/1511.02793v2","url_pdf":"http://arxiv.org/pdf/1511.02793v2.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":[{"paper_slug":"generating-images-from-captions-with","repo_url":"https://github.com/emansim/text2image","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"generating-images-from-captions-with","repo_url":"https://github.com/mansimov/text2image","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1511.02793","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.02793"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/emansim/text2image","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mansimov/text2image","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"2eddcec50e27c45d","entry":"create_reverse_dictionary","repo":"emansim/text2image","repo_kind":"official","path":"mnist-captions/create-captions.py","file_url":"https://github.com/emansim/text2image/blob/HEAD/mnist-captions/create-captions.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2eddcec50e27c45d"}},{"code_sha256_prefix":"62e5ccfbe18626ed","entry":"matrix2sent","repo":"emansim/text2image","repo_kind":"official","path":"mnist-captions/create-captions.py","file_url":"https://github.com/emansim/text2image/blob/HEAD/mnist-captions/create-captions.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"62e5ccfbe18626ed"}},{"code_sha256_prefix":"be981e13dd331905","entry":"sent2matrix","repo":"emansim/text2image","repo_kind":"official","path":"mnist-captions/create-captions.py","file_url":"https://github.com/emansim/text2image/blob/HEAD/mnist-captions/create-captions.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"be981e13dd331905"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}