{"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/semantic-compositional-networks-for-visual","title":"Semantic Compositional Networks for Visual Captioning","arxiv_id":"1611.08002","date":"2016-11-23","proceeding":"CVPR 2017 7","authors":["Zhe Gan","Chuang Gan","Xiaodong He","Yunchen Pu","Kenneth Tran","Jianfeng Gao","Lawrence Carin","Li Deng"],"abstract":"A Semantic Compositional Network (SCN) is developed for image captioning, in\nwhich semantic concepts (i.e., tags) are detected from the image, and the\nprobability of each tag is used to compose the parameters in a long short-term\nmemory (LSTM) network. The SCN extends each weight matrix of the LSTM to an\nensemble of tag-dependent weight matrices. The degree to which each member of\nthe ensemble is used to generate an image caption is tied to the\nimage-dependent probability of the corresponding tag. In addition to captioning\nimages, we also extend the SCN to generate captions for video clips. We\nqualitatively analyze semantic composition in SCNs, and quantitatively evaluate\nthe algorithm on three benchmark datasets: COCO, Flickr30k, and Youtube2Text.\nExperimental results show that the proposed method significantly outperforms\nprior state-of-the-art approaches, across multiple evaluation metrics.","url_abs":"http://arxiv.org/abs/1611.08002v2","url_pdf":"http://arxiv.org/pdf/1611.08002v2.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":"semantic-compositional-networks-for-visual","repo_url":"https://github.com/zhegan27/Semantic_Compositional_Nets","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"semantic-composition","task_name":"Semantic Composition"},{"task_slug":"tag","task_name":"TAG"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1611.08002","atlas_url":"https://app.syntology.ai/?focus=1611.08002","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":"1611.08002"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1611.08002\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1611.08002"},"call":"get_concepts_for_paper(arxiv_id=\"1611.08002\")"}],"by_repo":[{"repo":"zhegan27/Semantic_Compositional_Nets","kind":"official","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":"de59ba16e47d1393290e8019b56ca293f0f7b4f311d57d9749b1ba9846145455","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}