{"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/stack-captioning-coarse-to-fine-learning-for","title":"Stack-Captioning: Coarse-to-Fine Learning for Image Captioning","arxiv_id":"1709.03376","date":"2017-09-11","proceeding":null,"authors":["Jiuxiang Gu","Jianfei Cai","Gang Wang","Tsuhan Chen"],"abstract":"The existing image captioning approaches typically train a one-stage sentence\ndecoder, which is difficult to generate rich fine-grained descriptions. On the\nother hand, multi-stage image caption model is hard to train due to the\nvanishing gradient problem. In this paper, we propose a coarse-to-fine\nmulti-stage prediction framework for image captioning, composed of multiple\ndecoders each of which operates on the output of the previous stage, producing\nincreasingly refined image descriptions. Our proposed learning approach\naddresses the difficulty of vanishing gradients during training by providing a\nlearning objective function that enforces intermediate supervisions.\nParticularly, we optimize our model with a reinforcement learning approach\nwhich utilizes the output of each intermediate decoder's test-time inference\nalgorithm as well as the output of its preceding decoder to normalize the\nrewards, which simultaneously solves the well-known exposure bias problem and\nthe loss-evaluation mismatch problem. We extensively evaluate the proposed\napproach on MSCOCO and show that our approach can achieve the state-of-the-art\nperformance.","url_abs":"http://arxiv.org/abs/1709.03376v3","url_pdf":"http://arxiv.org/pdf/1709.03376v3.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":"stack-captioning-coarse-to-fine-learning-for","repo_url":"https://github.com/showkeyjar/chinese_im2text.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1709.03376","atlas_url":"https://app.syntology.ai/?focus=1709.03376","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":"1709.03376"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1709.03376\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1709.03376"},"call":"get_concepts_for_paper(arxiv_id=\"1709.03376\")"}],"by_repo":[{"repo":"showkeyjar/chinese_im2text.pytorch","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":"5a9bc401a37512b104e57dcc06b62dc20dfb82a4b0ae50edc6a81abb11cc7413","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}