{"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/oracle-performance-for-visual-captioning","title":"Oracle performance for visual captioning","arxiv_id":"1511.04590","date":"2015-11-14","proceeding":null,"authors":["Li Yao","Nicolas Ballas","Kyunghyun Cho","John R. Smith","Yoshua Bengio"],"abstract":"The task of associating images and videos with a natural language description\nhas attracted a great amount of attention recently. Rapid progress has been\nmade in terms of both developing novel algorithms and releasing new datasets.\nIndeed, the state-of-the-art results on some of the standard datasets have been\npushed into the regime where it has become more and more difficult to make\nsignificant improvements. Instead of proposing new models, this work\ninvestigates the possibility of empirically establishing performance upper\nbounds on various visual captioning datasets without extra data labelling\neffort or human evaluation. In particular, it is assumed that visual captioning\nis decomposed into two steps: from visual inputs to visual concepts, and from\nvisual concepts to natural language descriptions. One would be able to obtain\nan upper bound when assuming the first step is perfect and only requiring\ntraining a conditional language model for the second step. We demonstrate the\nconstruction of such bounds on MS-COCO, YouTube2Text and LSMDC (a combination\nof M-VAD and MPII-MD). Surprisingly, despite of the imperfect process we used\nfor visual concept extraction in the first step and the simplicity of the\nlanguage model for the second step, we show that current state-of-the-art\nmodels fall short when being compared with the learned upper bounds.\nFurthermore, with such a bound, we quantify several important factors\nconcerning image and video captioning: the number of visual concepts captured\nby different models, the trade-off between the amount of visual elements\ncaptured and their accuracy, and the intrinsic difficulty and blessing of\ndifferent datasets.","url_abs":"http://arxiv.org/abs/1511.04590v5","url_pdf":"http://arxiv.org/pdf/1511.04590v5.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":"oracle-performance-for-visual-captioning","repo_url":"https://github.com/yaoli/arctic-capgen-vid","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"video-captioning","task_name":"Video Captioning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"yaoli/arctic-capgen-vid","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":"9e7e1c45c0ff962e0c09c2063f4eb08f7a3b01dd07cb8874a4f62c51cebf70bf","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}