{"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/show-attend-and-read-a-simple-and-strong","title":"Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition","arxiv_id":"1811.00751","date":"2018-11-02","proceeding":null,"authors":["Hui Li","Peng Wang","Chunhua Shen","Guyu Zhang"],"abstract":"Recognizing irregular text in natural scene images is challenging due to the\nlarge variance in text appearance, such as curvature, orientation and\ndistortion. Most existing approaches rely heavily on sophisticated model\ndesigns and/or extra fine-grained annotations, which, to some extent, increase\nthe difficulty in algorithm implementation and data collection. In this work,\nwe propose an easy-to-implement strong baseline for irregular scene text\nrecognition, using off-the-shelf neural network components and only word-level\nannotations. It is composed of a $31$-layer ResNet, an LSTM-based\nencoder-decoder framework and a 2-dimensional attention module. Despite its\nsimplicity, the proposed method is robust and achieves state-of-the-art\nperformance on both regular and irregular scene text recognition benchmarks.\nCode is available at: https://tinyurl.com/ShowAttendRead","url_abs":"http://arxiv.org/abs/1811.00751v2","url_pdf":"http://arxiv.org/pdf/1811.00751v2.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":"show-attend-and-read-a-simple-and-strong","repo_url":"https://github.com/Pay20Y/SAR_TF","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"show-attend-and-read-a-simple-and-strong","repo_url":"https://github.com/liuch37/sar-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"show-attend-and-read-a-simple-and-strong","repo_url":"https://github.com/mindee/doctr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"show-attend-and-read-a-simple-and-strong","repo_url":"https://github.com/phantrdat/cvpr20-scatter-text-recognizer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"show-attend-and-read-a-simple-and-strong","repo_url":"https://github.com/tobiasvanderwerff/MetaHTR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"show-attend-and-read-a-simple-and-strong","repo_url":"https://github.com/PaddlePaddle/PaddleOCR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"show-attend-and-read-a-simple-and-strong","repo_url":"https://github.com/open-mmlab/mmocr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"show-attend-and-read-a-simple-and-strong","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":"decoder","task_name":"Decoder"},{"task_slug":"irregular-text-recognition","task_name":"Irregular Text Recognition"},{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition (OCR)"},{"task_slug":"scene-text-recognition","task_name":"Scene Text Recognition"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/scene-text-recognition-on-icdar2013","task":"Scene Text Recognition","dataset":"ICDAR2013","model":"SAR","rank_in_archive_order":34,"of":38,"metrics":{"Accuracy":"91.0"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-recognition-on-icdar2015","task":"Scene Text Recognition","dataset":"ICDAR2015","model":"SAR","rank_in_archive_order":27,"of":27,"metrics":{"Accuracy":"69.2"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-recognition-on-svt","task":"Scene Text Recognition","dataset":"SVT","model":"SAR","rank_in_archive_order":33,"of":37,"metrics":{"Accuracy":"84.5"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1811.00751","atlas_url":"https://app.syntology.ai/?focus=1811.00751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.00751"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PaddlePaddle/PaddleOCR","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/liuch37/sar-pytorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Pay20Y/SAR_TF","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/phantrdat/cvpr20-scatter-text-recognizer","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mindee/doctr","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/topdu/openocr","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tobiasvanderwerff/MetaHTR","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/open-mmlab/mmocr","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":8},"by_repo_kind":{"listed":{"samples":8,"ran":0,"repositories":3}},"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":"deda6831eb0cc4f0","entry":"attention_map","repo":"liuch37/sar-pytorch","repo_kind":"listed","path":"utils/attention_map.py","file_url":"https://github.com/liuch37/sar-pytorch/blob/HEAD/utils/attention_map.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"deda6831eb0cc4f0"}},{"code_sha256_prefix":"c7b92e1633b0d2da","entry":"checkImageIsValid","repo":"phantrdat/cvpr20-scatter-text-recognizer","repo_kind":"listed","path":"create_lmdb_dataset.py","file_url":"https://github.com/phantrdat/cvpr20-scatter-text-recognizer/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":"73cdf16e24a09a8c","entry":"copy_hyperparameters_to_logging_dir","repo":"tobiasvanderwerff/MetaHTR","repo_kind":"listed","path":"metahtr/util.py","file_url":"https://github.com/tobiasvanderwerff/MetaHTR/blob/HEAD/metahtr/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"73cdf16e24a09a8c"}},{"code_sha256_prefix":"d00e42d99ad77876","entry":"dictionary_generator","repo":"liuch37/sar-pytorch","repo_kind":"listed","path":"dataset/dataset.py","file_url":"https://github.com/liuch37/sar-pytorch/blob/HEAD/dataset/dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d00e42d99ad77876"}},{"code_sha256_prefix":"432c3464425adb58","entry":"end_cut","repo":"liuch37/sar-pytorch","repo_kind":"listed","path":"dataset/dataset.py","file_url":"https://github.com/liuch37/sar-pytorch/blob/HEAD/dataset/dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"432c3464425adb58"}},{"code_sha256_prefix":"7110cd886f2674e9","entry":"get_pl_tb_logger","repo":"tobiasvanderwerff/MetaHTR","repo_kind":"listed","path":"metahtr/util.py","file_url":"https://github.com/tobiasvanderwerff/MetaHTR/blob/HEAD/metahtr/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7110cd886f2674e9"}},{"code_sha256_prefix":"df31f55edb95b761","entry":"svt_xml_extractor","repo":"liuch37/sar-pytorch","repo_kind":"listed","path":"dataset/dataset.py","file_url":"https://github.com/liuch37/sar-pytorch/blob/HEAD/dataset/dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"df31f55edb95b761"}},{"code_sha256_prefix":"b78e81e855133e45","entry":"tensor2im","repo":"phantrdat/cvpr20-scatter-text-recognizer","repo_kind":"listed","path":"dataset.py","file_url":"https://github.com/phantrdat/cvpr20-scatter-text-recognizer/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}