{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:57:21Z","timestamp":1783439841672,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"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":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611961","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"7747-7757","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["GridFormer: Towards Accurate Table Structure Recognition via Grid Prediction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3153-8519","authenticated-orcid":false,"given":"Pengyuan","family":"Lyu","sequence":"first","affiliation":[{"name":"VIS, Baidu Inc., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2252-3856","authenticated-orcid":false,"given":"Weihong","family":"Ma","sequence":"additional","affiliation":[{"name":"VIS, Baidu Inc., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5403-1449","authenticated-orcid":false,"given":"Hongyi","family":"Wang","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9842-3360","authenticated-orcid":false,"given":"Yuechen","family":"Yu","sequence":"additional","affiliation":[{"name":"VIS, Baidu Inc., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8254-5773","authenticated-orcid":false,"given":"Chengquan","family":"Zhang","sequence":"additional","affiliation":[{"name":"VIS, Baidu Inc., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7155-4076","authenticated-orcid":false,"given":"Kun","family":"Yao","sequence":"additional","affiliation":[{"name":"VIS, Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1947-4957","authenticated-orcid":false,"given":"Yang","family":"Xue","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4888-4445","authenticated-orcid":false,"given":"Jingdong","family":"Wang","sequence":"additional","affiliation":[{"name":"VIS, Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"213","article-title":"End-to-End Object Detection with Transformers","volume":"12346","author":"Carion Nicolas","year":"2020","unstructured":"Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, and Sergey Zagoruyko. 2020. End-to-End Object Detection with Transformers. In ECCV, Vol. 12346. 213--229.","journal-title":"ECCV"},{"key":"e_1_3_2_1_2_1","volume-title":"Complicated table structure recognition. CoRR","author":"Chi Zewen","year":"2019","unstructured":"Zewen Chi, Heyan Huang, Heng-Da Xu, Houjin Yu, Wanxuan Yin, and Xian-Ling Mao. 2019. Complicated table structure recognition. CoRR (2019)."},{"key":"e_1_3_2_1_3_1","unstructured":"TAL Contributors. 2021. TAL_OCR_TABLE: A Scene Table Structure Recognition Benchmark. https:\/\/ai.100tal.com\/dataset."},{"key":"e_1_3_2_1_4_1","volume-title":"Document ai: Benchmarks, models and applications. CoRR","author":"Cui Lei","year":"2021","unstructured":"Lei Cui, Yiheng Xu, Tengchao Lv, and Furu Wei. 2021. Document ai: Benchmarks, models and applications. CoRR (2021)."},{"key":"e_1_3_2_1_5_1","volume-title":"Challenges in end-to-end neural scientific table recognition","author":"Deng Yuntian","unstructured":"Yuntian Deng, David Rosenberg, and Gideon Mann. 2019. Challenges in end-to-end neural scientific table recognition. In ICDAR. IEEE, 894--901."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Iyad Abu Doush and Enrico Pontelli. 2010. Detecting and recognizing tables in spreadsheets. In DAS. 471--478.","DOI":"10.1145\/1815330.1815391"},{"key":"e_1_3_2_1_7_1","volume-title":"ICDAR 2013 Table Competition. In ICDAR.","author":"Gobel Max","year":"2013","unstructured":"Max Gobel, Tamir Hassan, Ermelinda Oro, and Giorgio Orsi. 2013. ICDAR 2013 Table Competition. In ICDAR."},{"key":"e_1_3_2_1_8_1","volume-title":"TRUST: An Accurate and End-to-End Table structure Recognizer Using Splitting-based Transformers. CoRR","author":"Guo Zengyuan","year":"2022","unstructured":"Zengyuan Guo, Yuechen Yu, Pengyuan Lv, Chengquan Zhang, Haojie Li, Zhihui Wang, Kun Yao, Jingtuo Liu, and Jingdong Wang. 2022. TRUST: An Accurate and End-to-End Table structure Recognizer Using Splitting-based Transformers. CoRR, Vol. abs\/2208.14687 (2022)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR. 770--778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_10_1","volume-title":"Xie","author":"Huang Yongshuai","year":"2023","unstructured":"Yongshuai Huang, Ning Lu, Dapeng Chen, Yibo Li, and Zecheng et al. Xie. 2023. Improving Table Structure Recognition with Visual-Alignment Sequential Coordinate Modeling. In CVPR. 11134--11143."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Yupan Huang Tengchao Lv Lei Cui Yutong Lu and Furu Wei. 2022. LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking. In ACMMM. 4083--4091.","DOI":"10.1145\/3503161.3548112"},{"key":"e_1_3_2_1_12_1","volume-title":"Table structure recognition based on textblock arrangement and ruled line position","author":"Itonori Katsuhiko","unstructured":"Katsuhiko Itonori. 1993. Table structure recognition based on textblock arrangement and ruled line position. In ICDAR. IEEE, 765--768."},{"key":"e_1_3_2_1_13_1","volume-title":"Tables to LaTeX: structure and content extraction from scientific tables. CoRR","author":"Kayal Pratik","year":"2022","unstructured":"Pratik Kayal, Mrinal Anand, Harsh Desai, and Mayank Singh. 2022. Tables to LaTeX: structure and content extraction from scientific tables. CoRR, Vol. abs\/2210.17246 (2022)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1117\/12.304642"},{"key":"e_1_3_2_1_15_1","volume-title":"Table recognition in spreadsheets via a graph representation","author":"Koci Elvis","unstructured":"Elvis Koci, Maik Thiele, Wolfgang Lehner, and Oscar Romero. 2018. Table recognition in spreadsheets via a graph representation. In DAS. IEEE, 139--144."},{"key":"e_1_3_2_1_16_1","volume-title":"Adaptive scaling for archival table structure recognition","author":"Li Xiao-Hui","unstructured":"Xiao-Hui Li, Fei Yin, Xu-Yao Zhang, and Cheng-Lin Liu. 2021b. Adaptive scaling for archival table structure recognition. In ICDAR. Springer, 80--95."},{"key":"e_1_3_2_1_17_1","volume-title":"GFTE: graph-based financial table extraction","author":"Li Yiren","unstructured":"Yiren Li, Zheng Huang, Junchi Yan, Yi Zhou, Fan Ye, and Xianhui Liu. 2021a. GFTE: graph-based financial table extraction. In ICPR. Springer, 644--658."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Zaisheng Li Yi Li Qiao Liang Pengfei Li Zhanzhan Cheng Yi Niu Shiliang Pu and Xi Li. 2022. End-to-End Compound Table Understanding with Multi-Modal Modeling. In ACMMM. 4112--4121.","DOI":"10.1145\/3503161.3547885"},{"key":"e_1_3_2_1_19_1","unstructured":"Tsung-Yi Lin Priya Goyal Ross B. Girshick Kaiming He and Piotr Doll\u00e1r. 2017. Focal Loss for Dense Object Detection. In ICCV. 2999--3007."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Weihong Lin Zheng Sun Chixiang Ma Mingze Li Jiawei Wang Lei Sun and Qiang Huo. 2022. TSRFormer: Table Structure Recognition with Transformers. In ACMMM. 6473--6482.","DOI":"10.1145\/3503161.3548038"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Hao Liu Xin Li Bing Liu Deqiang Jiang Yinsong Liu and Bo Ren. 2022. Neural Collaborative Graph Machines for Table Structure Recognition. In CVPR. 4523--4532.","DOI":"10.1109\/CVPR52688.2022.00449"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Hao Liu Xin Li Bing Liu Deqiang Jiang Yinsong Liu Bo Ren and Rongrong Ji. 2021. Show Read and Reason: Table Structure Recognition with Flexible Context Aggregator. In ACMMM. 1084--1092.","DOI":"10.1145\/3474085.3481534"},{"key":"e_1_3_2_1_23_1","volume-title":"Improving the table boundary detection in pdfs by fixing the sequence error of the sparse lines","author":"Liu Ying","unstructured":"Ying Liu, Kun Bai, Prasenjit Mitra, and C Lee Giles. 2009. Improving the table boundary detection in pdfs by fixing the sequence error of the sparse lines. In ICDAR. IEEE, 1006--1010."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Ying Liu Prasenjit Mitra and C Lee Giles. 2008. Identifying table boundaries in digital documents via sparse line detection. In CIKM. 1311--1320.","DOI":"10.1145\/1458082.1458255"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Rujiao Long Wen Wang Nan Xue Feiyu Gao Zhibo Yang Yongpan Wang and Gui-Song Xia. 2021. Parsing Table Structures in the Wild. In ICCV. 924--932.","DOI":"10.1109\/ICCV48922.2021.00098"},{"key":"e_1_3_2_1_26_1","first-page":"107980","article-title":"Master: Multi-aspect non-local network for scene text recognition","volume":"117","author":"Lu Ning","year":"2021","unstructured":"Ning Lu, Wenwen Yu, Xianbiao Qi, Yihao Chen, Ping Gong, Rong Xiao, and Xiang Bai. 2021. Master: Multi-aspect non-local network for scene text recognition. PR, Vol. 117 (2021), 107980.","journal-title":"PR"},{"key":"e_1_3_2_1_27_1","first-page":"109006","article-title":"Robust Table Detection and Structure Recognition from Heterogeneous Document Images","volume":"133","author":"Ma Chixiang","year":"2023","unstructured":"Chixiang Ma, Weihong Lin, Lei Sun, and Qiang Huo. 2023. Robust Table Detection and Structure Recognition from Heterogeneous Document Images. PR, Vol. 133 (2023), 109006.","journal-title":"PR"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Minesh Mathew Dimosthenis Karatzas and C. V. Jawahar. 2021. DocVQA: A Dataset for VQA on Document Images. In WACV. IEEE 2199--2208.","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Ahmed Nassar Nikolaos Livathinos Maksym Lysak and Peter Staar. 2022. TableFormer: Table structure understanding with transformers. In CVPR. 4614--4623.","DOI":"10.1109\/CVPR52688.2022.00457"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.3115\/1034678.1034746"},{"key":"e_1_3_2_1_31_1","volume-title":"Tablenet: Deep learning model for end-to-end table detection and tabular data extraction from scanned document images","author":"Paliwal Shubham Singh","year":"2019","unstructured":"Shubham Singh Paliwal, D Vishwanath, Rohit Rahul, Monika Sharma, and Lovekesh Vig. 2019. Tablenet: Deep learning model for end-to-end table detection and tabular data extraction from scanned document images. In ICDAR. IEEE, 128--133."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00294"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Shah Rukh Qasim Hassan Mahmood and Faisal Shafait. 2019a. Rethinking Table Recognition using Graph Neural Networks. In ICDAR. 142--147.","DOI":"10.1109\/ICDAR.2019.00031"},{"key":"e_1_3_2_1_34_1","volume-title":"Rethinking table recognition using graph neural networks","author":"Qasim Shah Rukh","unstructured":"Shah Rukh Qasim, Hassan Mahmood, and Faisal Shafait. 2019b. Rethinking table recognition using graph neural networks. In ICDAR. IEEE, 142--147."},{"key":"e_1_3_2_1_35_1","volume-title":"LGPMA: Complicated Table Structure Recognition with Local and Global Pyramid Mask Alignment. In ICDAR. 99--114.","author":"Qiao Liang","year":"2021","unstructured":"Liang Qiao, Zaisheng Li, Zhanzhan Cheng, Peng Zhang, Shiliang Pu, Yi Niu, Wenqi Ren, Wenming Tan, and Fei Wu. 2021. LGPMA: Complicated Table Structure Recognition with Local and Global Pyramid Mask Alignment. In ICDAR. 99--114."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Sachin Raja Ajoy Mondal and C. V. Jawahar. 2020. Table Structure Recognition Using Top-Down and Bottom-Up Cues. In ECCV. 70--86.","DOI":"10.1007\/978-3-030-58604-1_5"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Hamid Rezatofighi Nathan Tsoi JunYoung Gwak Amir Sadeghian Ian D. Reid and Silvio Savarese. 2019. Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression. In CVPR. 658--666.","DOI":"10.1109\/CVPR.2019.00075"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"Sebastian Schreiber Stefan Agne Ivo Wolf Andreas Dengel and Sheraz Ahmed. 2017. DeepDeSRT: Deep Learning for Detection and Structure Recognition of Tables in Document Images. In ICDAR. 1162--1167.","DOI":"10.1109\/ICDAR.2017.192"},{"key":"e_1_3_2_1_39_1","volume-title":"Martinez","author":"Tensmeyer Chris","year":"2019","unstructured":"Chris Tensmeyer, Vlad I. Morariu, Brian L. Price, Scott Cohen, and Tony R. Martinez. 2019. Deep Splitting and Merging for Table Structure Decomposition. In ICDAR. 114--121."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Wenhai Wang Enze Xie Xiang Li Wenbo Hou Tong Lu Gang Yu and Shuai Shao. 2019. Shape robust text detection with progressive scale expansion network. In CVPR. 9336--9345.","DOI":"10.1109\/CVPR.2019.00956"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2004.01.012"},{"key":"e_1_3_2_1_42_1","volume-title":"ReS2TIM: Reconstruct syntactic structures from table images","author":"Xue Wenyuan","unstructured":"Wenyuan Xue, Qingyong Li, and Dacheng Tao. 2019. ReS2TIM: Reconstruct syntactic structures from table images. In ICDAR. IEEE, 749--755."},{"key":"e_1_3_2_1_43_1","unstructured":"Wenyuan Xue Baosheng Yu Wen Wang Dacheng Tao and Qingyong Li. 2021. TGRNet: A table graph reconstruction network for table structure recognition. In ICCV. 1295--1304."},{"key":"e_1_3_2_1_44_1","volume-title":"PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Literature Parsing Task B: Table Recognition to HTML. CoRR","author":"Ye Jiaquan","year":"1848","unstructured":"Jiaquan Ye, Xianbiao Qi, Yelin He, Yihao Chen, Dengyi Gu, Peng Gao, and Rong Xiao. 2021. PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Literature Parsing Task B: Table Recognition to HTML. CoRR, Vol. abs\/2105.01848 (2021)."},{"key":"e_1_3_2_1_45_1","unstructured":"Yuechen Yu Yulin Li Chengquan Zhang Xiaoqiang Zhang Zengyuan Guo Xiameng Qin Kun Yao Junyu Han Errui Ding and Jingdong Wang. 2023. StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training. In ICLR."},{"key":"e_1_3_2_1_46_1","first-page":"108565","article-title":"Split, Embed and Merge: An accurate table structure recognizer","volume":"126","author":"Zhang Zhenrong","year":"2022","unstructured":"Zhenrong Zhang, Jianshu Zhang, Jun Du, and Fengren Wang. 2022. Split, Embed and Merge: An accurate table structure recognizer. PR, Vol. 126 (2022), 108565.","journal-title":"PR"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"Xinyi Zheng Douglas Burdick Lucian Popa Xu Zhong and Nancy Xin Ru Wang. 2021. Global table extractor (gte): A framework for joint table identification and cell structure recognition using visual context. In WACV. 697--706.","DOI":"10.1109\/WACV48630.2021.00074"},{"key":"e_1_3_2_1_48_1","volume-title":"Image-Based Table Recognition: Data, Model, and Evaluation","author":"Zhong Xu","unstructured":"Xu Zhong, Elaheh ShafieiBavani, and Antonio Jimeno-Yepes. 2020a. Image-Based Table Recognition: Data, Model, and Evaluation. In ECCV, Andrea Vedaldi, Horst Bischof, Thomas Brox, and Jan-Michael Frahm (Eds.), Vol. 12366. 564--580."},{"key":"e_1_3_2_1_49_1","volume-title":"Image-based table recognition: data, model, and evaluation","author":"Zhong Xu","unstructured":"Xu Zhong, Elaheh ShafieiBavani, and Antonio Jimeno Yepes. 2020b. Image-based table recognition: data, model, and evaluation. In ECCV. Springer, 564--580."},{"key":"e_1_3_2_1_50_1","volume-title":"Objects as Points. CoRR","author":"Zhou Xingyi","year":"2019","unstructured":"Xingyi Zhou, Dequan Wang, and Philipp Kr\u00e4henb\u00fchl. 2019. Objects as Points. CoRR, Vol. abs\/1904.07850 (2019)."},{"key":"e_1_3_2_1_51_1","unstructured":"Xizhou Zhu Weijie Su Lewei Lu Bin Li Xiaogang Wang and Jifeng Dai. 2021. Deformable DETR: Deformable Transformers for End-to-End Object Detection. In ICLR."}],"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 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611961","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611961","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:07:19Z","timestamp":1755821239000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611961"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":51,"alternative-id":["10.1145\/3581783.3611961","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611961","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}