{"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/revisiting-scene-text-recognition-a-data","title":"Revisiting Scene Text Recognition: A Data Perspective","arxiv_id":"2307.08723","date":"2023-07-17","proceeding":"ICCV 2023 1","authors":["Qing Jiang","Jiapeng Wang","Dezhi Peng","Chongyu Liu","Lianwen Jin"],"abstract":"This paper aims to re-assess scene text recognition (STR) from a data-oriented perspective. We begin by revisiting the six commonly used benchmarks in STR and observe a trend of performance saturation, whereby only 2.91% of the benchmark images cannot be accurately recognized by an ensemble of 13 representative models. While these results are impressive and suggest that STR could be considered solved, however, we argue that this is primarily due to the less challenging nature of the common benchmarks, thus concealing the underlying issues that STR faces. To this end, we consolidate a large-scale real STR dataset, namely Union14M, which comprises 4 million labeled images and 10 million unlabeled images, to assess the performance of STR models in more complex real-world scenarios. Our experiments demonstrate that the 13 models can only achieve an average accuracy of 66.53% on the 4 million labeled images, indicating that STR still faces numerous challenges in the real world. By analyzing the error patterns of the 13 models, we identify seven open challenges in STR and develop a challenge-driven benchmark consisting of eight distinct subsets to facilitate further progress in the field. Our exploration demonstrates that STR is far from being solved and leveraging data may be a promising solution. In this regard, we find that utilizing the 10 million unlabeled images through self-supervised pre-training can significantly improve the robustness of STR model in real-world scenarios and leads to state-of-the-art performance.","url_abs":"https://arxiv.org/abs/2307.08723v2","url_pdf":"https://arxiv.org/pdf/2307.08723v2.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":"revisiting-scene-text-recognition-a-data","repo_url":"https://github.com/Mountchicken/Union14M","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"revisiting-scene-text-recognition-a-data","repo_url":"https://github.com/topdu/openocr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"scene-text-recognition","task_name":"Scene Text Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2307.08723","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.08723"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/Mountchicken/Union14M","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/topdu/openocr","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":"a59668c0d279887a","entry":"unpatchify","repo":"Mountchicken/Union14M","repo_kind":"official","path":"mae/visualize.py","file_url":"https://github.com/Mountchicken/Union14M/blob/HEAD/mae/visualize.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a59668c0d279887a"}},{"code_sha256_prefix":"5f77844c9cc8cf57","entry":"visualize_tensor","repo":"Mountchicken/Union14M","repo_kind":"official","path":"mae/visualize.py","file_url":"https://github.com/Mountchicken/Union14M/blob/HEAD/mae/visualize.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5f77844c9cc8cf57"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}