{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T02:22:10Z","timestamp":1771467730411,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,29]],"date-time":"2023-10-29T00:00:00Z","timestamp":1698537600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,2]]},"DOI":"10.1145\/3606040.3617444","type":"proceedings-article","created":{"date-parts":[[2023,10,25]],"date-time":"2023-10-25T00:03:15Z","timestamp":1698192195000},"page":"11-18","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["TC-OCR: TableCraft OCR for Efficient Detection & Recognition of Table Structure & Content"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2479-0342","authenticated-orcid":false,"given":"Avinash","family":"Anand","sequence":"first","affiliation":[{"name":"Indraprastha Institute of Information Technology, Delhi, Delhi, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5044-1409","authenticated-orcid":false,"given":"Raj","family":"Jaiswal","sequence":"additional","affiliation":[{"name":"Indraprastha Institute of Information Technology, Delhi, Delhi, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2132-0882","authenticated-orcid":false,"given":"Pijush","family":"Bhuyan","sequence":"additional","affiliation":[{"name":"Indraprastha Institute of Information Technology, Delhi, Delhi, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8528-5169","authenticated-orcid":false,"given":"Mohit","family":"Gupta","sequence":"additional","affiliation":[{"name":"Indraprastha Institute of Information Technology, Delhi, Delhi, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4349-0196","authenticated-orcid":false,"given":"Siddhesh","family":"Bangar","sequence":"additional","affiliation":[{"name":"Indraprastha Institute of Information Technology, Delhi, Delhi, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8145-6574","authenticated-orcid":false,"given":"Md. Modassir","family":"Imam","sequence":"additional","affiliation":[{"name":"Indraprastha Institute of Information Technology, Delhi, Delhi, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1028-9373","authenticated-orcid":false,"given":"Rajiv Ratn","family":"Shah","sequence":"additional","affiliation":[{"name":"Indraprastha Institute of Information Technology, Delhi, Delhi, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6995-6447","authenticated-orcid":false,"given":"Shin'ichi","family":"Satoh","sequence":"additional","affiliation":[{"name":"National Institute of Informatics, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,29]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3087865"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00638"},{"key":"e_1_3_2_1_3_1","volume-title":"End-to-End Object Detection with Transformers\". In: arXiv preprint","author":"Nicolas Carion","year":"2020","unstructured":"Nicolas Carion et al. \" End-to-End Object Detection with Transformers\". In: arXiv preprint ( 2020 ). eprint: 2005.12872. url: https:\/\/arxiv.org\/pdf\/2005.12872. pdf. Nicolas Carion et al. \"End-to-End Object Detection with Transformers\". In: arXiv preprint (2020). eprint: 2005.12872. url: https:\/\/arxiv.org\/pdf\/2005.12872. pdf."},{"key":"e_1_3_2_1_4_1","first-page":"199","volume-title":"International workshop on document analysis systems. Springer.","author":"The \u00c1ngela","year":"2020","unstructured":"\u00c1ngela Casado-Garc\"a et al. \" The benefits of close-domain fine-tuning for table detection in document images \". In: International workshop on document analysis systems. Springer. 2020 , pp. 199 -- 215 . \u00c1ngela Casado-Garc\"a et al. \"The benefits of close-domain fine-tuning for table detection in document images\". In: International workshop on document analysis systems. Springer. 2020, pp. 199--215."},{"key":"e_1_3_2_1_5_1","volume-title":"PP-LCNet: A Lightweight CPU Convolutional Neural Network\". In: arXiv preprint","author":"Cheng Cui","year":"2021","unstructured":"Cheng Cui et al. \" PP-LCNet: A Lightweight CPU Convolutional Neural Network\". In: arXiv preprint ( 2021 ). eprint: 2101.05759. url: https:\/\/arxiv.org\/pdf\/ 2101.05759.pdf. Cheng Cui et al. \"PP-LCNet: A Lightweight CPU Convolutional Neural Network\". In: arXiv preprint (2021). eprint: 2101.05759. url: https:\/\/arxiv.org\/pdf\/ 2101.05759.pdf."},{"key":"e_1_3_2_1_6_1","volume-title":"ICDAR 2019 Competition on Table Detection and Recognition (cTDaR)","author":"Herv\u00e9","year":"2019","unstructured":"Herv\u00e9 D\u00e9jean et al . ICDAR 2019 Competition on Table Detection and Recognition (cTDaR) , April 2019 . Herv\u00e9 D\u00e9jean et al. ICDAR 2019 Competition on Table Detection and Recognition (cTDaR), April 2019."},{"key":"e_1_3_2_1_7_1","volume-title":"PP-OCRv2: Bag of Tricks for Ultra Lightweight OCR System","author":"Yuning Du","year":"2021","unstructured":"Yuning Du et al. \" PP-OCRv2: Bag of Tricks for Ultra Lightweight OCR System \". In : Baidu Inc . ( 2021 ). Yuning Du et al. \"PP-OCRv2: Bag of Tricks for Ultra Lightweight OCR System\". In: Baidu Inc. (2021)."},{"key":"e_1_3_2_1_8_1","first-page":"771","volume-title":"2017 14th IAPR international conference on document analysis and recognition (ICDAR).","volume":"1","author":"Azka","year":"2017","unstructured":"Azka Gilani et al. \"Table detection using deep learning \". In: 2017 14th IAPR international conference on document analysis and recognition (ICDAR). Vol. 1 . IEEE. 2017 , pp. 771 -- 776 . Azka Gilani et al. \"Table detection using deep learning\". In: 2017 14th IAPR international conference on document analysis and recognition (ICDAR). Vol. 1. IEEE. 2017, pp. 771--776."},{"key":"e_1_3_2_1_9_1","first-page":"1449","volume-title":"2013 12th International Conference on Document Analysis and Recognition. IEEE.","author":"Max","year":"2013","unstructured":"Max G\u00f6bel et al. \"ICDAR 2013 table competition \". In: 2013 12th International Conference on Document Analysis and Recognition. IEEE. 2013 , pp. 1449 -- 1453 . Max G\u00f6bel et al. \"ICDAR 2013 table competition\". In: 2013 12th International Conference on Document Analysis and Recognition. IEEE. 2013, pp. 1449--1453."},{"key":"e_1_3_2_1_10_1","first-page":"287","volume-title":"2016 12th IAPR Workshop on Document Analysis Systems (DAS). IEEE.","author":"Leipeng","year":"2016","unstructured":"Leipeng Hao et al. \"A table detection method for pdf documents based on convolutional neural networks \". In: 2016 12th IAPR Workshop on Document Analysis Systems (DAS). IEEE. 2016 , pp. 287 -- 292 . Leipeng Hao et al. \"A table detection method for pdf documents based on convolutional neural networks\". In: 2016 12th IAPR Workshop on Document Analysis Systems (DAS). IEEE. 2016, pp. 287--292."},{"key":"e_1_3_2_1_11_1","volume-title":"ArXiv abs\/2105.01846","author":"Yelin He","year":"2021","unstructured":"Yelin He et al. \" PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Table Image Recognition to Latex \". In: ArXiv abs\/2105.01846 ( 2021 ). Yelin He et al. \"PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Table Image Recognition to Latex\". In: ArXiv abs\/2105.01846 (2021)."},{"key":"e_1_3_2_1_12_1","first-page":"158","volume-title":"2019 International Conference on Document Analysis and Recognition Workshops (ICDARW).","volume":"5","author":"Table Martin","year":"2019","unstructured":"Martin Hole\"ek et al. \" Table understanding in structured documents \". In: 2019 International Conference on Document Analysis and Recognition Workshops (ICDARW). Vol. 5 . IEEE. 2019 , pp. 158 -- 164 . Martin Hole\"ek et al. \"Table understanding in structured documents\". In: 2019 International Conference on Document Analysis and Recognition Workshops (ICDARW). Vol. 5. IEEE. 2019, pp. 158--164."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.1993.395625"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2020.103551"},{"key":"e_1_3_2_1_15_1","first-page":"754","volume-title":"ICDAR 2021 competition on scientific table image recognition to LaTeX","author":"Pratik Kayal","year":"2021","unstructured":"Pratik Kayal et al. \" ICDAR 2021 competition on scientific table image recognition to LaTeX \". In : Document Analysis and Recognition--ICDAR 2021 : 16th International Conference, Lausanne, Switzerland, September 5--10, 2021, Proceedings, Part IV 16. Springer . 2021, pp. 754 -- 766 . Pratik Kayal et al. \"ICDAR 2021 competition on scientific table image recognition to LaTeX\". In: Document Analysis and Recognition--ICDAR 2021: 16th International Conference, Lausanne, Switzerland, September 5--10, 2021, Proceedings, Part IV 16. Springer. 2021, pp. 754--766."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1117\/12.304642","volume-title":"Document Recognition V.","author":"Kieninger Thomas G","year":"1998","unstructured":"Thomas G Kieninger . \" Table structure recognition based on robust block segmentation\". In: Document Recognition V. Vol. 3305 . SPIE. 1998 , pp. 22 -- 32 . Thomas G Kieninger. \"Table structure recognition based on robust block segmentation\". In: Document Recognition V. Vol. 3305. SPIE. 1998, pp. 22--32."},{"key":"e_1_3_2_1_17_1","volume-title":"arXiv preprint arXiv:2108.04049","author":"Bogdan","year":"2021","unstructured":"Bogdan Kosti\", Julian Risch , and Timo M\u00f6ller . \"Multi-modal retrieval of tables and texts using tri-encoder models\". In: arXiv preprint arXiv:2108.04049 ( 2021 ). Bogdan Kosti\", Julian Risch, and Timo M\u00f6ller. \"Multi-modal retrieval of tables and texts using tri-encoder models\". In: arXiv preprint arXiv:2108.04049 (2021)."},{"key":"e_1_3_2_1_18_1","volume-title":"TableBank: A Benchmark Dataset for Table Detection and Recognition","author":"Minghao Li","year":"2019","unstructured":"Minghao Li et al. TableBank: A Benchmark Dataset for Table Detection and Recognition . 2019 . arXiv: 1903.01949 [cs.CV]. Minghao Li et al. TableBank: A Benchmark Dataset for Table Detection and Recognition. 2019. arXiv: 1903.01949 [cs.CV]."},{"key":"e_1_3_2_1_19_1","volume-title":"Shape robust text detection with progressive scale expansion network\". In: arXiv preprint arXiv:1806.02559","author":"Xiang Li","year":"2018","unstructured":"Xiang Li et al. \" Shape robust text detection with progressive scale expansion network\". In: arXiv preprint arXiv:1806.02559 ( 2018 ). Xiang Li et al. \"Shape robust text detection with progressive scale expansion network\". In: arXiv preprint arXiv:1806.02559 (2018)."},{"key":"e_1_3_2_1_20_1","volume-title":"MASTER: Multi-Aspect Non-local Network for Scene Text Recognition","author":"Ning Lu","year":"2021","unstructured":"Ning Lu et al. \" MASTER: Multi-Aspect Non-local Network for Scene Text Recognition \". In : Pattern Recognition ( 2021 ). Ning Lu et al. \"MASTER: Multi-Aspect Non-local Network for Scene Text Recognition\". In: Pattern Recognition (2021)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107980"},{"key":"e_1_3_2_1_22_1","volume-title":"Rethinking Image-based Table Recognition Using Weakly Supervised Methods\". In: arXiv preprint arXiv:2303.07641","author":"Ly Nam Tuan","year":"2023","unstructured":"Nam Tuan Ly \" Rethinking Image-based Table Recognition Using Weakly Supervised Methods\". In: arXiv preprint arXiv:2303.07641 ( 2023 ). Nam Tuan Ly et al. \"Rethinking Image-based Table Recognition Using Weakly Supervised Methods\". In: arXiv preprint arXiv:2303.07641 (2023)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1117\/12.476326"},{"key":"e_1_3_2_1_24_1","volume-title":"TableFormer: table structure understanding with transformers. CoRR abs\/2203.01017","author":"A Nassar","year":"2022","unstructured":"A Nassar et al. TableFormer: table structure understanding with transformers. CoRR abs\/2203.01017 ( 2022 ). A Nassar et al. TableFormer: table structure understanding with transformers. CoRR abs\/2203.01017 (2022)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-021-00390-4"},{"key":"e_1_3_2_1_26_1","volume-title":"CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documents","author":"Devashish Prasad","year":"2020","unstructured":"Devashish Prasad et al. CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documents . 2020 . arXiv: 2004.12629 [cs.CV]. Devashish Prasad et al. CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documents. 2020. arXiv: 2004.12629 [cs.CV]."},{"key":"e_1_3_2_1_27_1","first-page":"70","volume-title":"Proceedings, Part XXVIII 16","author":"Raja Sachin","year":"2020","unstructured":"Sachin Raja , Ajoy Mondal , and CV Jawahar . \"Table structure recognition using top-down and bottom-up cues\". In: Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020 , Proceedings, Part XXVIII 16 . Springer. 2020 , pp. 70 -- 86 . Sachin Raja, Ajoy Mondal, and CV Jawahar. \"Table structure recognition using top-down and bottom-up cues\". In: Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XXVIII 16. Springer. 2020, pp. 70--86."},{"key":"e_1_3_2_1_28_1","first-page":"649","volume-title":"European Conference on Computer Vision. Springer","author":"Mausoom","year":"2020","unstructured":"Mausoom Sarkar et al. \"Document Structure Extraction using Prior-based HighResolution Hierarchical Semantic Segmentation \". In: European Conference on Computer Vision. Springer , 2020 , pp. 649 -- 666 . Mausoom Sarkar et al. \"Document Structure Extraction using Prior-based HighResolution Hierarchical Semantic Segmentation\". In: European Conference on Computer Vision. Springer, 2020, pp. 649--666."},{"key":"e_1_3_2_1_29_1","first-page":"1162","volume-title":"2017 14th IAPR international conference on document analysis and recognition (ICDAR).","volume":"1","author":"Sebastian","year":"2017","unstructured":"Sebastian Schreiber et al. \"Deepdesrt: Deep learning for detection and structure recognition of tables in document images \". In: 2017 14th IAPR international conference on document analysis and recognition (ICDAR). Vol. 1 . IEEE. 2017 , pp. 1162 -- 1167 . Sebastian Schreiber et al. \"Deepdesrt: Deep learning for detection and structure recognition of tables in document images\". In: 2017 14th IAPR international conference on document analysis and recognition (ICDAR). Vol. 1. IEEE. 2017, pp. 1162--1167."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2880211"},{"key":"e_1_3_2_1_31_1","unstructured":"Brandon Smock and Rohith Pesala. Table Transformer. Version 1.0.0. June 2021. url: https:\/\/github.com\/microsoft\/table-transformer.  Brandon Smock and Rohith Pesala. Table Transformer. Version 1.0.0. June 2021. url: https:\/\/github.com\/microsoft\/table-transformer."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.5392\/IJoC.2015.11.4.077"},{"key":"e_1_3_2_1_33_1","first-page":"1","volume-title":"2019 IEEE Symposium on Computers and Communications (ISCC). IEEE.","author":"Mark","year":"2019","unstructured":"Mark Traquair et al. \"Deep learning for the detection of tabular information from electronic component datasheets \". In: 2019 IEEE Symposium on Computers and Communications (ISCC). IEEE. 2019 , pp. 1 -- 6 . Mark Traquair et al. \"Deep learning for the detection of tabular information from electronic component datasheets\". In: 2019 IEEE Symposium on Computers and Communications (ISCC). IEEE. 2019, pp. 1--6."},{"key":"e_1_3_2_1_34_1","volume-title":"Attention Is All You Need\". In: arXiv preprint","author":"Ashish Vaswani","year":"2017","unstructured":"Ashish Vaswani et al. \" Attention Is All You Need\". In: arXiv preprint ( 2017 ). eprint: 1706.03762. url: https:\/\/arxiv.org\/pdf\/1706.03762.pdf. Ashish Vaswani et al. \"Attention Is All You Need\". In: arXiv preprint (2017). eprint: 1706.03762. url: https:\/\/arxiv.org\/pdf\/1706.03762.pdf."},{"key":"e_1_3_2_1_35_1","first-page":"6961","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE","author":"Jingdong","year":"2019","unstructured":"Jingdong Wang et al. \"Deep High-Resolution Representation Learning for Visual Recognition \". In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE . Long Beach, CA, USA , 2019 , pp. 6961 -- 6969 . doi: 10.1109\/ CVPR.2019.00707. Jingdong Wang et al. \"Deep High-Resolution Representation Learning for Visual Recognition\". In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE. Long Beach, CA, USA, 2019, pp. 6961--6969. doi: 10.1109\/ CVPR.2019.00707."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2004.01"},{"key":"e_1_3_2_1_37_1","volume-title":"PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Literature Parsing Task B: Table Recognition to HTML\". In: arXiv preprint arXiv:2105.01848","author":"Jiaquan Ye","year":"2021","unstructured":"Jiaquan Ye et al. \" PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Literature Parsing Task B: Table Recognition to HTML\". In: arXiv preprint arXiv:2105.01848 ( 2021 ). Jiaquan Ye et al. \"PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Literature Parsing Task B: Table Recognition to HTML\". In: arXiv preprint arXiv:2105.01848 (2021)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-022-00400-z"},{"key":"e_1_3_2_1_39_1","volume-title":"Winter Conference for Applications in Computer Vision (WACV)","author":"Xinyi","year":"2021","unstructured":"Xinyi Zheng et al. \"Global Table Extractor (GTE): A Framework for Joint Table Identification and Cell Structure Recognition Using Visual Context \". In: Winter Conference for Applications in Computer Vision (WACV) ( 2021 ). Xinyi Zheng et al. \"Global Table Extractor (GTE): A Framework for Joint Table Identification and Cell Structure Recognition Using Visual Context\". In: Winter Conference for Applications in Computer Vision (WACV) (2021)."},{"key":"e_1_3_2_1_40_1","unstructured":"Xu Zhong Elaheh ShafieiBavani and Antonio Jimeno Yepes. \"Image-based table recognit  Xu Zhong Elaheh ShafieiBavani and Antonio Jimeno Yepes. \"Image-based table recognit"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 1st International Workshop on Deep Multimodal Learning for Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3606040.3617444","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3606040.3617444","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:36:20Z","timestamp":1750178180000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3606040.3617444"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,29]]},"references-count":40,"alternative-id":["10.1145\/3606040.3617444","10.1145\/3606040"],"URL":"https:\/\/doi.org\/10.1145\/3606040.3617444","relation":{},"subject":[],"published":{"date-parts":[[2023,10,29]]},"assertion":[{"value":"2023-10-29","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}