{"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/on-recognizing-texts-of-arbitrary-shapes-with","title":"On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention","arxiv_id":"1910.04396","date":"2019-10-10","proceeding":null,"authors":["Junyeop Lee","Sungrae Park","Jeonghun Baek","Seong Joon Oh","Seonghyeon Kim","Hwalsuk Lee"],"abstract":"Scene text recognition (STR) is the task of recognizing character sequences in natural scenes. While there have been great advances in STR methods, current methods still fail to recognize texts in arbitrary shapes, such as heavily curved or rotated texts, which are abundant in daily life (e.g. restaurant signs, product labels, company logos, etc). This paper introduces a novel architecture to recognizing texts of arbitrary shapes, named Self-Attention Text Recognition Network (SATRN), which is inspired by the Transformer. SATRN utilizes the self-attention mechanism to describe two-dimensional (2D) spatial dependencies of characters in a scene text image. Exploiting the full-graph propagation of self-attention, SATRN can recognize texts with arbitrary arrangements and large inter-character spacing. As a result, SATRN outperforms existing STR models by a large margin of 5.7 pp on average in \"irregular text\" benchmarks. We provide empirical analyses that illustrate the inner mechanisms and the extent to which the model is applicable (e.g. rotated and multi-line text). We will open-source the code.","url_abs":"https://arxiv.org/abs/1910.04396v1","url_pdf":"https://arxiv.org/pdf/1910.04396v1.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":"on-recognizing-texts-of-arbitrary-shapes-with","repo_url":"https://github.com/Media-Smart/vedastr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"on-recognizing-texts-of-arbitrary-shapes-with","repo_url":"https://github.com/clovaai/SATRN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"scene-text-recognition","task_name":"Scene Text Recognition"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/scene-text-recognition-on-icdar-2003","task":"Scene Text Recognition","dataset":"ICDAR 2003","model":"SATRN","rank_in_archive_order":3,"of":12,"metrics":{"Accuracy":"96.7"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-recognition-on-icdar2013","task":"Scene Text Recognition","dataset":"ICDAR2013","model":"SATRN","rank_in_archive_order":24,"of":38,"metrics":{"Accuracy":"94.1"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-recognition-on-icdar2015","task":"Scene Text Recognition","dataset":"ICDAR2015","model":"SATRN","rank_in_archive_order":20,"of":27,"metrics":{"Accuracy":"79.0"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-recognition-on-svt","task":"Scene Text Recognition","dataset":"SVT","model":"SATRN","rank_in_archive_order":23,"of":37,"metrics":{"Accuracy":"91.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1910.04396","atlas_url":"https://app.syntology.ai/?focus=1910.04396","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":"1910.04396"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1910.04396\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1910.04396"},"call":"get_concepts_for_paper(arxiv_id=\"1910.04396\")"}],"by_repo":[{"repo":"Media-Smart/vedastr","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"clovaai/SATRN","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":"eba7fc98f5abf18bf58f6c4a94d76218dabac65053b19bf64f4203cb88f4f868","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}