{"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/master-multi-aspect-non-local-network-for","title":"MASTER: Multi-Aspect Non-local Network for Scene Text Recognition","arxiv_id":"1910.02562","date":"2019-10-07","proceeding":null,"authors":["Ning Lu","Wenwen Yu","Xianbiao Qi","Yihao Chen","Ping Gong","Rong Xiao","Xiang Bai"],"abstract":"Attention-based scene text recognizers have gained huge success, which leverages a more compact intermediate representation to learn 1d- or 2d- attention by a RNN-based encoder-decoder architecture. However, such methods suffer from attention-drift problem because high similarity among encoded features leads to attention confusion under the RNN-based local attention mechanism. Moreover, RNN-based methods have low efficiency due to poor parallelization. To overcome these problems, we propose the MASTER, a self-attention based scene text recognizer that (1) not only encodes the input-output attention but also learns self-attention which encodes feature-feature and target-target relationships inside the encoder and decoder and (2) learns a more powerful and robust intermediate representation to spatial distortion, and (3) owns a great training efficiency because of high training parallelization and a high-speed inference because of an efficient memory-cache mechanism. Extensive experiments on various benchmarks demonstrate the superior performance of our MASTER on both regular and irregular scene text. Pytorch code can be found at https://github.com/wenwenyu/MASTER-pytorch, and Tensorflow code can be found at https://github.com/jiangxiluning/MASTER-TF.","url_abs":"https://arxiv.org/abs/1910.02562v3","url_pdf":"https://arxiv.org/pdf/1910.02562v3.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":"master-multi-aspect-non-local-network-for","repo_url":"https://github.com/jiangxiluning/MASTER-TF","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"master-multi-aspect-non-local-network-for","repo_url":"https://github.com/wenwenyu/MASTER-pytorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"master-multi-aspect-non-local-network-for","repo_url":"https://github.com/JiaquanYe/TableMASTER-mmocr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"master-multi-aspect-non-local-network-for","repo_url":"https://github.com/S-HuaBomb/MASTER-paddle","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"paddle","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"master-multi-aspect-non-local-network-for","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":"master-multi-aspect-non-local-network-for","repo_url":"https://github.com/open-mmlab/mmocr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"master-multi-aspect-non-local-network-for","repo_url":"https://github.com/mindspore-lab/mindocr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"scene-text-recognition","task_name":"Scene Text Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1910.02562","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.02562"}},"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":"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/wenwenyu/MASTER-pytorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mindspore-lab/mindocr","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jiangxiluning/MASTER-TF","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JiaquanYe/TableMASTER-mmocr","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/open-mmlab/mmocr","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/S-HuaBomb/MASTER-paddle","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"ran_honours":3,"unverified":6},"by_repo_kind":{"official":{"samples":9,"ran":4,"repositories":1},"listed":{"samples":1,"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":"2271c8526c9dce4e","entry":"clones","repo":"jiangxiluning/MASTER-TF","repo_kind":"official","path":"src/model/transformer.py","file_url":"https://github.com/jiangxiluning/MASTER-TF/blob/HEAD/src/model/transformer.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2271c8526c9dce4e"}},{"code_sha256_prefix":"7816c6d65ab55d8f","entry":"get_angles","repo":"jiangxiluning/MASTER-TF","repo_kind":"official","path":"src/model/transformer.py","file_url":"https://github.com/jiangxiluning/MASTER-TF/blob/HEAD/src/model/transformer.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7816c6d65ab55d8f"}},{"code_sha256_prefix":"29af386f64351dae","entry":"positional_encoding","repo":"jiangxiluning/MASTER-TF","repo_kind":"official","path":"src/model/transformer_tf.py","file_url":"https://github.com/jiangxiluning/MASTER-TF/blob/HEAD/src/model/transformer_tf.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"29af386f64351dae"}},{"code_sha256_prefix":"70fe09020aeba7f4","entry":"positional_encoding","repo":"jiangxiluning/MASTER-TF","repo_kind":"official","path":"src/model/transformer.py","file_url":"https://github.com/jiangxiluning/MASTER-TF/blob/HEAD/src/model/transformer.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"70fe09020aeba7f4"}},{"code_sha256_prefix":"5c1510caf3cf76cb","entry":"calculate_gain","repo":"S-HuaBomb/MASTER-paddle","repo_kind":"listed","path":"model/initializers.py","file_url":"https://github.com/S-HuaBomb/MASTER-paddle/blob/HEAD/model/initializers.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":"5c1510caf3cf76cb"}},{"code_sha256_prefix":"39161ed30377ac7c","entry":"conv33","repo":"jiangxiluning/MASTER-TF","repo_kind":"official","path":"src/model/backbone.py","file_url":"https://github.com/jiangxiluning/MASTER-TF/blob/HEAD/src/model/backbone.py","link_basis":"first_harvest_node","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":"39161ed30377ac7c"}},{"code_sha256_prefix":"436719c2595f1c54","entry":"create_padding_mask","repo":"jiangxiluning/MASTER-TF","repo_kind":"official","path":"src/model/transformer_tf.py","file_url":"https://github.com/jiangxiluning/MASTER-TF/blob/HEAD/src/model/transformer_tf.py","link_basis":"first_harvest_node","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":"436719c2595f1c54"}},{"code_sha256_prefix":"a7852c913c2d2af2","entry":"get_vocabulary","repo":"jiangxiluning/MASTER-TF","repo_kind":"official","path":"src/dataset/utils.py","file_url":"https://github.com/jiangxiluning/MASTER-TF/blob/HEAD/src/dataset/utils.py","link_basis":"first_harvest_node","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":"a7852c913c2d2af2"}},{"code_sha256_prefix":"bf79ed7abc99e5ee","entry":"resize_width","repo":"jiangxiluning/MASTER-TF","repo_kind":"official","path":"src/dataset/utils.py","file_url":"https://github.com/jiangxiluning/MASTER-TF/blob/HEAD/src/dataset/utils.py","link_basis":"first_harvest_node","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":"bf79ed7abc99e5ee"}},{"code_sha256_prefix":"e72bcd44ddf201b9","entry":"rotate_img","repo":"jiangxiluning/MASTER-TF","repo_kind":"official","path":"src/dataset/utils.py","file_url":"https://github.com/jiangxiluning/MASTER-TF/blob/HEAD/src/dataset/utils.py","link_basis":"first_harvest_node","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":"e72bcd44ddf201b9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}