{"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/a-hierarchical-approach-for-generating","title":"A Hierarchical Approach for Generating Descriptive Image Paragraphs","arxiv_id":"1611.06607","date":"2016-11-20","proceeding":"CVPR 2017 7","authors":["Jonathan Krause","Justin Johnson","Ranjay Krishna","Li Fei-Fei"],"abstract":"Recent progress on image captioning has made it possible to generate novel\nsentences describing images in natural language, but compressing an image into\na single sentence can describe visual content in only coarse detail. While one\nnew captioning approach, dense captioning, can potentially describe images in\nfiner levels of detail by captioning many regions within an image, it in turn\nis unable to produce a coherent story for an image. In this paper we overcome\nthese limitations by generating entire paragraphs for describing images, which\ncan tell detailed, unified stories. We develop a model that decomposes both\nimages and paragraphs into their constituent parts, detecting semantic regions\nin images and using a hierarchical recurrent neural network to reason about\nlanguage. Linguistic analysis confirms the complexity of the paragraph\ngeneration task, and thorough experiments on a new dataset of image and\nparagraph pairs demonstrate the effectiveness of our approach.","url_abs":"http://arxiv.org/abs/1611.06607v2","url_pdf":"http://arxiv.org/pdf/1611.06607v2.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":"a-hierarchical-approach-for-generating","repo_url":"https://github.com/spider101/visual-semantic-alignments","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"a-hierarchical-approach-for-generating","repo_url":"https://github.com/InnerPeace-Wu/im2p-tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-hierarchical-approach-for-generating","repo_url":"https://github.com/chenxinpeng/im2p","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"dense-captioning","task_name":"Dense Captioning"},{"task_slug":"descriptive","task_name":"Descriptive"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"image-paragraph-captioning","task_name":"Image Paragraph Captioning"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[{"slug":"image-paragraph-captioning","name":"Image Paragraph Captioning","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-paragraph-captioning-on-image-paragraph","task":"Image Paragraph Captioning","dataset":"Image Paragraph Captioning","model":"Regions-Hierarchical (ours)","rank_in_archive_order":7,"of":10,"metrics":{"BLEU-4":"8.69","CIDEr":"13.52","METEOR":"15.95"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.06607","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.06607"}},"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/InnerPeace-Wu/im2p-tensorflow","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/spider101/visual-semantic-alignments","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chenxinpeng/im2p","reach":{"status":"ok"}}],"summary":{"unverified":9},"by_repo_kind":{"listed":{"samples":9,"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":"84dcf978d5570762","entry":"bbox_transform","repo":"InnerPeace-Wu/im2p-tensorflow","repo_kind":"listed","path":"lib/fast_rcnn/bbox_transform.py","file_url":"https://github.com/InnerPeace-Wu/im2p-tensorflow/blob/HEAD/lib/fast_rcnn/bbox_transform.py","link_basis":"harvester_set","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":"84dcf978d5570762"}},{"code_sha256_prefix":"6b2ace662cea2a36","entry":"bbox_transform_inv","repo":"InnerPeace-Wu/im2p-tensorflow","repo_kind":"listed","path":"lib/fast_rcnn/bbox_transform.py","file_url":"https://github.com/InnerPeace-Wu/im2p-tensorflow/blob/HEAD/lib/fast_rcnn/bbox_transform.py","link_basis":"harvester_set","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":"6b2ace662cea2a36"}},{"code_sha256_prefix":"76b2a70a88afbf78","entry":"box2xywh","repo":"InnerPeace-Wu/im2p-tensorflow","repo_kind":"listed","path":"lib/dense_cap/vis_whtml.py","file_url":"https://github.com/InnerPeace-Wu/im2p-tensorflow/blob/HEAD/lib/dense_cap/vis_whtml.py","link_basis":"harvester_set","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":"76b2a70a88afbf78"}},{"code_sha256_prefix":"d24c99284beca7a6","entry":"clip_boxes","repo":"InnerPeace-Wu/im2p-tensorflow","repo_kind":"listed","path":"lib/fast_rcnn/bbox_transform.py","file_url":"https://github.com/InnerPeace-Wu/im2p-tensorflow/blob/HEAD/lib/fast_rcnn/bbox_transform.py","link_basis":"harvester_set","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":"d24c99284beca7a6"}},{"code_sha256_prefix":"9f3cea1708a8a9db","entry":"get_imdb","repo":"InnerPeace-Wu/im2p-tensorflow","repo_kind":"listed","path":"lib/datasets/factory.py","file_url":"https://github.com/InnerPeace-Wu/im2p-tensorflow/blob/HEAD/lib/datasets/factory.py","link_basis":"harvester_set","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":"9f3cea1708a8a9db"}},{"code_sha256_prefix":"4786edbc775d299d","entry":"get_output_dir","repo":"InnerPeace-Wu/im2p-tensorflow","repo_kind":"listed","path":"lib/config.py","file_url":"https://github.com/InnerPeace-Wu/im2p-tensorflow/blob/HEAD/lib/config.py","link_basis":"harvester_set","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":"4786edbc775d299d"}},{"code_sha256_prefix":"97f5f6cd7eab1c78","entry":"get_output_tb_dir","repo":"InnerPeace-Wu/im2p-tensorflow","repo_kind":"listed","path":"lib/config.py","file_url":"https://github.com/InnerPeace-Wu/im2p-tensorflow/blob/HEAD/lib/config.py","link_basis":"harvester_set","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":"97f5f6cd7eab1c78"}},{"code_sha256_prefix":"9292d54e38364142","entry":"initialize_vocabulary","repo":"InnerPeace-Wu/im2p-tensorflow","repo_kind":"listed","path":"lib/pre_glove.py","file_url":"https://github.com/InnerPeace-Wu/im2p-tensorflow/blob/HEAD/lib/pre_glove.py","link_basis":"harvester_set","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":"9292d54e38364142"}},{"code_sha256_prefix":"1ea786fdfcc714c3","entry":"vis_whtml","repo":"InnerPeace-Wu/im2p-tensorflow","repo_kind":"listed","path":"lib/dense_cap/vis_whtml.py","file_url":"https://github.com/InnerPeace-Wu/im2p-tensorflow/blob/HEAD/lib/dense_cap/vis_whtml.py","link_basis":"harvester_set","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":"1ea786fdfcc714c3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}