{"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/coo-comic-onomatopoeia-dataset-for","title":"COO: Comic Onomatopoeia Dataset for Recognizing Arbitrary or Truncated Texts","arxiv_id":"2207.04675","date":"2022-07-11","proceeding":null,"authors":["Jeonghun Baek","Yusuke Matsui","Kiyoharu Aizawa"],"abstract":"Recognizing irregular texts has been a challenging topic in text recognition. To encourage research on this topic, we provide a novel comic onomatopoeia dataset (COO), which consists of onomatopoeia texts in Japanese comics. COO has many arbitrary texts, such as extremely curved, partially shrunk texts, or arbitrarily placed texts. Furthermore, some texts are separated into several parts. Each part is a truncated text and is not meaningful by itself. These parts should be linked to represent the intended meaning. Thus, we propose a novel task that predicts the link between truncated texts. We conduct three tasks to detect the onomatopoeia region and capture its intended meaning: text detection, text recognition, and link prediction. Through extensive experiments, we analyze the characteristics of the COO. Our data and code are available at \\url{https://github.com/ku21fan/COO-Comic-Onomatopoeia}.","url_abs":"https://arxiv.org/abs/2207.04675v1","url_pdf":"https://arxiv.org/pdf/2207.04675v1.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":"coo-comic-onomatopoeia-dataset-for","repo_url":"https://github.com/ku21fan/coo-comic-onomatopoeia","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"text-detection","task_name":"Text Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2207.04675","atlas_url":"https://app.syntology.ai/?focus=2207.04675","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.04675"}},"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":"deterministic:regex_extraction","url":"https://github.com/facebookresearch/mmf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/clovaai/deep-text-recognition-benchmark","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ku21fan/coo-comic-onomatopoeia","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/aim-uofa/AdelaiDet","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/MhLiao/MaskTextSpotterV3","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/ku21fan/COO-Comic-Onomatopoeia","reach":{"status":"ok"}}],"summary":{"unverified":2},"by_repo_kind":{"found_in_text":{"samples":2,"ran":0,"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":"c7b92e1633b0d2da","entry":"checkImageIsValid","repo":"clovaai/deep-text-recognition-benchmark","repo_kind":"found_in_text","path":"create_lmdb_dataset.py","file_url":"https://github.com/clovaai/deep-text-recognition-benchmark/blob/HEAD/create_lmdb_dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c7b92e1633b0d2da"}},{"code_sha256_prefix":"b78e81e855133e45","entry":"tensor2im","repo":"clovaai/deep-text-recognition-benchmark","repo_kind":"found_in_text","path":"dataset.py","file_url":"https://github.com/clovaai/deep-text-recognition-benchmark/blob/HEAD/dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b78e81e855133e45"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}