{"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/neural-baby-talk","title":"Neural Baby Talk","arxiv_id":"1803.09845","date":"2018-03-27","proceeding":"CVPR 2018 6","authors":["Jiasen Lu","Jianwei Yang","Dhruv Batra","Devi Parikh"],"abstract":"We introduce a novel framework for image captioning that can produce natural\nlanguage explicitly grounded in entities that object detectors find in the\nimage. Our approach reconciles classical slot filling approaches (that are\ngenerally better grounded in images) with modern neural captioning approaches\n(that are generally more natural sounding and accurate). Our approach first\ngenerates a sentence `template' with slot locations explicitly tied to specific\nimage regions. These slots are then filled in by visual concepts identified in\nthe regions by object detectors. The entire architecture (sentence template\ngeneration and slot filling with object detectors) is end-to-end\ndifferentiable. We verify the effectiveness of our proposed model on different\nimage captioning tasks. On standard image captioning and novel object\ncaptioning, our model reaches state-of-the-art on both COCO and Flickr30k\ndatasets. We also demonstrate that our model has unique advantages when the\ntrain and test distributions of scene compositions -- and hence language priors\nof associated captions -- are different. Code has been made available at:\nhttps://github.com/jiasenlu/NeuralBabyTalk","url_abs":"http://arxiv.org/abs/1803.09845v1","url_pdf":"http://arxiv.org/pdf/1803.09845v1.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":"neural-baby-talk","repo_url":"https://github.com/jiasenlu/NeuralBabyTalk","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"object","task_name":"Object"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"slot-filling","task_name":"Slot Filling"},{"task_slug":"slot-filling-1","task_name":"slot-filling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.09845","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.09845"}},"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/jiasenlu/NeuralBabyTalk","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"official":{"samples":7,"ran":1,"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":"fac5364e2f53c6db","entry":"conv3x3","repo":"jiasenlu/NeuralBabyTalk","repo_kind":"official","path":"misc/resnet.py","file_url":"https://github.com/jiasenlu/NeuralBabyTalk/blob/HEAD/misc/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"c40b904771c8885b","entry":"bbox_transform","repo":"jiasenlu/NeuralBabyTalk","repo_kind":"official","path":"misc/bbox_transform.py","file_url":"https://github.com/jiasenlu/NeuralBabyTalk/blob/HEAD/misc/bbox_transform.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":"c40b904771c8885b"}},{"code_sha256_prefix":"a7445d60b800441b","entry":"bbox_transform_batch","repo":"jiasenlu/NeuralBabyTalk","repo_kind":"official","path":"misc/bbox_transform.py","file_url":"https://github.com/jiasenlu/NeuralBabyTalk/blob/HEAD/misc/bbox_transform.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":"a7445d60b800441b"}},{"code_sha256_prefix":"826e6d34ae25c870","entry":"bbox_transform_inv","repo":"jiasenlu/NeuralBabyTalk","repo_kind":"official","path":"misc/bbox_transform.py","file_url":"https://github.com/jiasenlu/NeuralBabyTalk/blob/HEAD/misc/bbox_transform.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":"826e6d34ae25c870"}},{"code_sha256_prefix":"5b9a79b23faa9bb1","entry":"language_eval","repo":"jiasenlu/NeuralBabyTalk","repo_kind":"official","path":"misc/eval_utils.py","file_url":"https://github.com/jiasenlu/NeuralBabyTalk/blob/HEAD/misc/eval_utils.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":"5b9a79b23faa9bb1"}},{"code_sha256_prefix":"6fbbfc8d57192c2c","entry":"resnet18","repo":"jiasenlu/NeuralBabyTalk","repo_kind":"official","path":"misc/resnet.py","file_url":"https://github.com/jiasenlu/NeuralBabyTalk/blob/HEAD/misc/resnet.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":"6fbbfc8d57192c2c"}},{"code_sha256_prefix":"100ec7cb24c5c7c1","entry":"resnet34","repo":"jiasenlu/NeuralBabyTalk","repo_kind":"official","path":"misc/resnet.py","file_url":"https://github.com/jiasenlu/NeuralBabyTalk/blob/HEAD/misc/resnet.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":"100ec7cb24c5c7c1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}