{"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/pingan-vcgroup-s-solution-for-icdar-2021","title":"PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Literature Parsing Task B: Table Recognition to HTML","arxiv_id":"2105.01848","date":"2021-05-05","proceeding":null,"authors":["Jiaquan Ye","Xianbiao Qi","Yelin He","Yihao Chen","Dengyi Gu","Peng Gao","Rong Xiao"],"abstract":"This paper presents our solution for ICDAR 2021 competition on scientific literature parsing taskB: table recognition to HTML. In our method, we divide the table content recognition task into foursub-tasks: table structure recognition, text line detection, text line recognition, and box assignment.Our table structure recognition algorithm is customized based on MASTER [1], a robust image textrecognition algorithm. PSENet [2] is used to detect each text line in the table image. For text linerecognition, our model is also built on MASTER. Finally, in the box assignment phase, we associatedthe text boxes detected by PSENet with the structure item reconstructed by table structure prediction,and fill the recognized content of the text line into the corresponding item. Our proposed methodachieves a 96.84% TEDS score on 9,115 validation samples in the development phase, and a 96.32%TEDS score on 9,064 samples in the final evaluation phase.","url_abs":"https://arxiv.org/abs/2105.01848v1","url_pdf":"https://arxiv.org/pdf/2105.01848v1.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":"pingan-vcgroup-s-solution-for-icdar-2021","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":"pingan-vcgroup-s-solution-for-icdar-2021","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":"pingan-vcgroup-s-solution-for-icdar-2021","repo_url":"https://github.com/cycloneboy/pdf_table","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"line-detection","task_name":"Line Detection"},{"task_slug":"table-recognition","task_name":"Table Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/table-recognition-on-pubtabnet","task":"Table Recognition","dataset":"PubTabNet","model":"TableMaster","rank_in_archive_order":2,"of":13,"metrics":{"TEDS (all samples)":"96.76"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2105.01848","atlas_url":"https://app.syntology.ai/?focus=2105.01848","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.01848"}},"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/cycloneboy/pdf_table","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JiaquanYe/TableMASTER-mmocr","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":7,"unverified":4},"by_repo_kind":{"listed":{"samples":11,"ran":7,"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":"22f4f2f9b4dca7a7","entry":"cal_true_positive_char","repo":"JiaquanYe/TableMASTER-mmocr","repo_kind":"listed","path":"mmocr/core/evaluation/ocr_metric.py","file_url":"https://github.com/JiaquanYe/TableMASTER-mmocr/blob/HEAD/mmocr/core/evaluation/ocr_metric.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"22f4f2f9b4dca7a7"}},{"code_sha256_prefix":"ef7d24d42496c8cb","entry":"compute_f1_all","repo":"JiaquanYe/TableMASTER-mmocr","repo_kind":"listed","path":"mmocr/core/evaluation/ner_metric.py","file_url":"https://github.com/JiaquanYe/TableMASTER-mmocr/blob/HEAD/mmocr/core/evaluation/ner_metric.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ef7d24d42496c8cb"}},{"code_sha256_prefix":"aea4c67ed6d34617","entry":"compute_f1_score","repo":"JiaquanYe/TableMASTER-mmocr","repo_kind":"listed","path":"mmocr/core/evaluation/kie_metric.py","file_url":"https://github.com/JiaquanYe/TableMASTER-mmocr/blob/HEAD/mmocr/core/evaluation/kie_metric.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aea4c67ed6d34617"}},{"code_sha256_prefix":"5a69be89c2583352","entry":"compute_hmean","repo":"JiaquanYe/TableMASTER-mmocr","repo_kind":"listed","path":"mmocr/core/evaluation/utils.py","file_url":"https://github.com/JiaquanYe/TableMASTER-mmocr/blob/HEAD/mmocr/core/evaluation/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5a69be89c2583352"}},{"code_sha256_prefix":"e7fcd01e8fbd0259","entry":"disable_text_recog_aug_test","repo":"JiaquanYe/TableMASTER-mmocr","repo_kind":"listed","path":"mmocr/apis/inference.py","file_url":"https://github.com/JiaquanYe/TableMASTER-mmocr/blob/HEAD/mmocr/apis/inference.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e7fcd01e8fbd0259"}},{"code_sha256_prefix":"8922d6e16f03f0f5","entry":"eval_ner_f1","repo":"JiaquanYe/TableMASTER-mmocr","repo_kind":"listed","path":"mmocr/core/evaluation/ner_metric.py","file_url":"https://github.com/JiaquanYe/TableMASTER-mmocr/blob/HEAD/mmocr/core/evaluation/ner_metric.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8922d6e16f03f0f5"}},{"code_sha256_prefix":"59952ebc93508f68","entry":"gt_label2entity","repo":"JiaquanYe/TableMASTER-mmocr","repo_kind":"listed","path":"mmocr/core/evaluation/ner_metric.py","file_url":"https://github.com/JiaquanYe/TableMASTER-mmocr/blob/HEAD/mmocr/core/evaluation/ner_metric.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"59952ebc93508f68"}},{"code_sha256_prefix":"012f0abe5c1db28b","entry":"compute_recall_precision","repo":"JiaquanYe/TableMASTER-mmocr","repo_kind":"listed","path":"mmocr/core/evaluation/hmean_ic13.py","file_url":"https://github.com/JiaquanYe/TableMASTER-mmocr/blob/HEAD/mmocr/core/evaluation/hmean_ic13.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":"012f0abe5c1db28b"}},{"code_sha256_prefix":"51bc3232ec8e8744","entry":"overlay_mask_img","repo":"JiaquanYe/TableMASTER-mmocr","repo_kind":"listed","path":"mmocr/core/visualize.py","file_url":"https://github.com/JiaquanYe/TableMASTER-mmocr/blob/HEAD/mmocr/core/visualize.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":"51bc3232ec8e8744"}},{"code_sha256_prefix":"f9b4b952d392770f","entry":"points2boundary","repo":"JiaquanYe/TableMASTER-mmocr","repo_kind":"listed","path":"mmocr/core/mask.py","file_url":"https://github.com/JiaquanYe/TableMASTER-mmocr/blob/HEAD/mmocr/core/mask.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":"f9b4b952d392770f"}},{"code_sha256_prefix":"acefba8a62931b37","entry":"seg2boundary","repo":"JiaquanYe/TableMASTER-mmocr","repo_kind":"listed","path":"mmocr/core/mask.py","file_url":"https://github.com/JiaquanYe/TableMASTER-mmocr/blob/HEAD/mmocr/core/mask.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":"acefba8a62931b37"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}