{"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-diagram-is-worth-a-dozen-images","title":"A Diagram Is Worth A Dozen Images","arxiv_id":"1603.07396","date":"2016-03-24","proceeding":null,"authors":["Aniruddha Kembhavi","Mike Salvato","Eric Kolve","Minjoon Seo","Hannaneh Hajishirzi","Ali Farhadi"],"abstract":"Diagrams are common tools for representing complex concepts, relationships\nand events, often when it would be difficult to portray the same information\nwith natural images. Understanding natural images has been extensively studied\nin computer vision, while diagram understanding has received little attention.\nIn this paper, we study the problem of diagram interpretation and reasoning,\nthe challenging task of identifying the structure of a diagram and the\nsemantics of its constituents and their relationships. We introduce Diagram\nParse Graphs (DPG) as our representation to model the structure of diagrams. We\ndefine syntactic parsing of diagrams as learning to infer DPGs for diagrams and\nstudy semantic interpretation and reasoning of diagrams in the context of\ndiagram question answering. We devise an LSTM-based method for syntactic\nparsing of diagrams and introduce a DPG-based attention model for diagram\nquestion answering. We compile a new dataset of diagrams with exhaustive\nannotations of constituents and relationships for over 5,000 diagrams and\n15,000 questions and answers. Our results show the significance of our models\nfor syntactic parsing and question answering in diagrams using DPGs.","url_abs":"http://arxiv.org/abs/1603.07396v1","url_pdf":"http://arxiv.org/pdf/1603.07396v1.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-diagram-is-worth-a-dozen-images","repo_url":"https://github.com/allenai/dqa-net","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[],"datasets_introduced":[{"slug":"ai2d","name":"AI2D","full_name":"AI2 Diagrams"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1603.07396","atlas_url":"https://app.syntology.ai/?focus=1603.07396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1603.07396"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/allenai/dqa-net","reach":null}],"summary":{"ran_draft_wrong":2,"ran_fixture":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":"c70da098fa5d857d","entry":"anno2rels","repo":"allenai/dqa-net","repo_kind":"official","path":"prepro/p05.py","file_url":"https://github.com/allenai/dqa-net/blob/HEAD/prepro/p05.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c70da098fa5d857d"}},{"code_sha256_prefix":"f1d5c3466f0df405","entry":"qa2hypo","repo":"allenai/dqa-net","repo_kind":"official","path":"prepro/p05.py","file_url":"https://github.com/allenai/dqa-net/blob/HEAD/prepro/p05.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f1d5c3466f0df405"}},{"code_sha256_prefix":"166293f0580d3160","entry":"rel2text","repo":"allenai/dqa-net","repo_kind":"official","path":"prepro/p05.py","file_url":"https://github.com/allenai/dqa-net/blob/HEAD/prepro/p05.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"166293f0580d3160"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}