{"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":"/paper/auto-encoding-scene-graphs-for-image","title":"Auto-Encoding Scene Graphs for Image Captioning","arxiv_id":"1812.02378","date":"2018-12-06","proceeding":"CVPR 2019 6","authors":["Xu Yang","Kaihua Tang","Hanwang Zhang","Jianfei Cai"],"abstract":"We propose Scene Graph Auto-Encoder (SGAE) that incorporates the language\ninductive bias into the encoder-decoder image captioning framework for more\nhuman-like captions. Intuitively, we humans use the inductive bias to compose\ncollocations and contextual inference in discourse. For example, when we see\nthe relation `person on bike', it is natural to replace `on' with `ride' and\ninfer `person riding bike on a road' even the `road' is not evident. Therefore,\nexploiting such bias as a language prior is expected to help the conventional\nencoder-decoder models less likely overfit to the dataset bias and focus on\nreasoning. Specifically, we use the scene graph --- a directed graph\n($\\mathcal{G}$) where an object node is connected by adjective nodes and\nrelationship nodes --- to represent the complex structural layout of both image\n($\\mathcal{I}$) and sentence ($\\mathcal{S}$). In the textual domain, we use\nSGAE to learn a dictionary ($\\mathcal{D}$) that helps to reconstruct sentences\nin the $\\mathcal{S}\\rightarrow \\mathcal{G} \\rightarrow \\mathcal{D} \\rightarrow\n\\mathcal{S}$ pipeline, where $\\mathcal{D}$ encodes the desired language prior;\nin the vision-language domain, we use the shared $\\mathcal{D}$ to guide the\nencoder-decoder in the $\\mathcal{I}\\rightarrow \\mathcal{G}\\rightarrow\n\\mathcal{D} \\rightarrow \\mathcal{S}$ pipeline. Thanks to the scene graph\nrepresentation and shared dictionary, the inductive bias is transferred across\ndomains in principle. We validate the effectiveness of SGAE on the challenging\nMS-COCO image captioning benchmark, e.g., our SGAE-based single-model achieves\na new state-of-the-art $127.8$ CIDEr-D on the Karpathy split, and a competitive\n$125.5$ CIDEr-D (c40) on the official server even compared to other ensemble\nmodels.","url_abs":"http://arxiv.org/abs/1812.02378v3","url_pdf":"http://arxiv.org/pdf/1812.02378v3.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":"auto-encoding-scene-graphs-for-image","repo_url":"https://github.com/yangxuntu/SGAE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"auto-encoding-scene-graphs-for-image","repo_url":"https://github.com/2023-MindSpore-1/ms-code-222/tree/main/SGAE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"inductive-bias","task_name":"Inductive Bias"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1812.02378","atlas_url":"https://app.syntology.ai/?focus=1812.02378","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1812.02378"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1812.02378\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1812.02378"},"call":"get_concepts_for_paper(arxiv_id=\"1812.02378\")"}],"by_repo":[{"repo":"yangxuntu/SGAE","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"2023-MindSpore-1/ms-code-222","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"714ea0c9f65ad5bef673cc5fae6d48ba8d92f216063a368ae775525f96bf56fe","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}