{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:21:22Z","timestamp":1750220482481,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":20,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,9,24]],"date-time":"2021-09-24T00:00:00Z","timestamp":1632441600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Department of Education of Hubei Province of China","award":["D20181504"],"award-info":[{"award-number":["D20181504"]}]},{"name":"Department of Science and Technology of Hubei Province of China","award":["2019AAA045"],"award-info":[{"award-number":["2019AAA045"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,9,24]]},"DOI":"10.1145\/3488933.3489039","type":"proceedings-article","created":{"date-parts":[[2022,2,25]],"date-time":"2022-02-25T11:36:59Z","timestamp":1645789019000},"page":"511-517","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Multi-Scale Approach for Document Detection Based on the Cascade mask RCNN"],"prefix":"10.1145","author":[{"given":"Jiashan","family":"Tang","sequence":"first","affiliation":[{"name":"Hubei Key Laboratory of Intelligent Robot,School of Computer ScienceampEngineering, Wuhan Institute of Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tongwei","family":"Lu","sequence":"additional","affiliation":[{"name":"Hubei Key Laboratory of Intelligent Robot,School of Computer ScienceampEngineering, Wuhan Institute of Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jixin","family":"Wei","sequence":"additional","affiliation":[{"name":"Hubei Key Laboratory of Intelligent Robot,School of Computer ScienceampEngineering, Wuhan Institute of Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,2,25]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"3rd International Conference on Document Analysis and Recognition","author":"Single","year":"1995","unstructured":"A trainable, Single -pass Algorithm for Column Segmentation[C]\/\/The 3rd International Conference on Document Analysis and Recognition . Montreal, Canada , 1995 : 615-618. GAO L C, YI X H, JIANG Z R, ICDAR2017 A trainable, Single-pass Algorithm for Column Segmentation[C]\/\/The 3rd International Conference on Document Analysis and Recognition. Montreal, Canada, 1995:615-618. GAO L C, YI X H, JIANG Z R, ICDAR2017"},{"key":"e_1_3_2_1_2_1","volume-title":"Cascade R-CNN: high quality object detection and instance segmentation. CoRR,abs\/1906.09756","author":"Zhaowei Cai","year":"2019","unstructured":"Zhaowei Cai and Nuno Vasconcelos. Cascade R-CNN: high quality object detection and instance segmentation. CoRR,abs\/1906.09756 , 2019 Zhaowei Cai and Nuno Vasconcelos. Cascade R-CNN: high quality object detection and instance segmentation. CoRR,abs\/1906.09756, 2019"},{"key":"e_1_3_2_1_3_1","first-page":"615","volume-title":"3rd International Conference on Document Analysis and Recognition","author":"Sylwester D","year":"1995","unstructured":"Sylwester D , Seth S. A trainable, Single -pass Algorithm for Column Segmentation[C]\/\/The 3rd International Conference on Document Analysis and Recognition . Montreal, Canada , 1995 : 615 - 618 . Sylwester D, Seth S. A trainable, Single-pass Algorithm for Column Segmentation[C]\/\/The 3rd International Conference on Document Analysis and Recognition. Montreal, Canada, 1995:615-618."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_4_1","DOI":"10.1109\/34.221173"},{"key":"e_1_3_2_1_5_1","volume-title":"IEEE, 2011. Liu X , Zhang S , Huang Q , RAM: A Region-Aware Deep Model for Vehicle Re-Identification[C]\/\/ 2018 IEEE International Conference on Multimedia and Expo (ICME). IEEE","author":"Bukhari S S","year":"2018","unstructured":"Bukhari S S , Shafait F , Breuel T M . High Performance Layout Analysis of Arabic and Urdu Document Images[C]\/\/ International Conference on Document Analysis & Recognition . IEEE, 2011. Liu X , Zhang S , Huang Q , RAM: A Region-Aware Deep Model for Vehicle Re-Identification[C]\/\/ 2018 IEEE International Conference on Multimedia and Expo (ICME). IEEE , 2018 . Bukhari S S , Shafait F , Breuel T M . High Performance Layout Analysis of Arabic and Urdu Document Images[C]\/\/ International Conference on Document Analysis & Recognition. IEEE, 2011. Liu X , Zhang S , Huang Q , RAM: A Region-Aware Deep Model for Vehicle Re-Identification[C]\/\/ 2018 IEEE International Conference on Multimedia and Expo (ICME). IEEE, 2018."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_6_1","DOI":"10.1016\/S0031-3203(96)00165-3"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_7_1","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"e_1_3_2_1_8_1","first-page":"241","volume":"2009","author":"Smith R W","unstructured":"Smith R W . Hybrid Page Layout Analysis via Tab-Stop Detection[C]\/\/The 10th International Conference on Document Analysis and Recognition. Barcelona , Spain , 2009 : 241 - 245 . Smith R W. Hybrid Page Layout Analysis via Tab-Stop Detection[C]\/\/The 10th International Conference on Document Analysis and Recognition. Barcelona, Spain, 2009:241-245.","journal-title":"Spain"},{"volume-title":"R-FCN: Object Detection via Region-Based Fully Convolutional Networks [C]\/\/ Proceeding of the 30th Conference on Neural Information Processing Systems","year":"2016","unstructured":"DAI J F, LI Y, HE K M , R-FCN: Object Detection via Region-Based Fully Convolutional Networks [C]\/\/ Proceeding of the 30th Conference on Neural Information Processing Systems . California : Neural Information Processing Systems , 2016 DAI J F, LI Y, HE K M, R-FCN: Object Detection via Region-Based Fully Convolutional Networks [C]\/\/ Proceeding of the 30th Conference on Neural Information Processing Systems. California: Neural Information Processing Systems, 2016","key":"e_1_3_2_1_9_1"},{"volume-title":"USA","author":"Chen K","unstructured":"Chen K , Yin F , Liu C L . Hybrid Page Segmentation with Efficient Whitespace Rectangles Extraction and Grouping[C]\/\/The 12th International Conference on Document Analysis and Recognition. Washington DC , USA , 2013: 958\u2013962. Chen K, Yin F, Liu C L. Hybrid Page Segmentation with Efficient Whitespace Rectangles Extraction and Grouping[C]\/\/The 12th International Conference on Document Analysis and Recognition. Washington DC, USA, 2013:958\u2013962.","key":"e_1_3_2_1_10_1"},{"key":"e_1_3_2_1_11_1","volume-title":"ICDAR 2009","author":"Smith R W","year":"2009","unstructured":"Smith R W . Hybrid Page Layout Analysis via Tab-Stop Detection[C]\/\/ 10th International Conference on Document Analysis and Recognition , ICDAR 2009 , Barcelona, Spain , 26-29 July 2009 . IEEE, 2009. Smith R W . Hybrid Page Layout Analysis via Tab-Stop Detection[C]\/\/ 10th International Conference on Document Analysis and Recognition, ICDAR 2009, Barcelona, Spain, 26-29 July 2009. IEEE, 2009."},{"volume-title":"IEEE International Conference on Computer Vision. New York: IEEE, 1440-1448","author":"Fast","unstructured":"GIRSHICK R. Fast R-CNN [C]\/\/ IEEE International Conference on Computer Vision. New York: IEEE, 1440-1448 . GIRSHICK R. Fast R-CNN [C]\/\/ IEEE International Conference on Computer Vision. New York: IEEE, 1440-1448.","key":"e_1_3_2_1_12_1"},{"key":"e_1_3_2_1_13_1","volume-title":"IEEE","author":"Bukhari S S","year":"2011","unstructured":"Bukhari S S , Shafait F , Breuel T M . High Performance Layout Analysis of Arabic and Urdu Document Images[C]\/\/ International Conference on Document Analysis & Recognition . IEEE , 2011 . Bukhari S S , Shafait F , Breuel T M . High Performance Layout Analysis of Arabic and Urdu Document Images[C]\/\/ International Conference on Document Analysis & Recognition. IEEE, 2011."},{"key":"e_1_3_2_1_14_1","volume-title":"IEEE","author":"Singh V","year":"2014","unstructured":"Singh V , Kumar B . Document layout analysis for Indian newspapers using contour based symbiotic approach[C]\/\/ International Conference on Computer Communication & Informatics . IEEE , 2014 .. Singh V , Kumar B . Document layout analysis for Indian newspapers using contour based symbiotic approach[C]\/\/ International Conference on Computer Communication & Informatics. IEEE, 2014.."},{"key":"e_1_3_2_1_15_1","volume-title":"IEEE","author":"Zhong X","year":"2020","unstructured":"Zhong X , Tang J , Yepes A J . PubLayNet : Largest Dataset Ever for Document Layout Analysis[C]\/\/ 2019 International Conference on Document Analysis and Recognition (ICDAR) . IEEE , 2020 .. Zhong X , Tang J , Yepes A J . PubLayNet: Largest Dataset Ever for Document Layout Analysis[C]\/\/ 2019 International Conference on Document Analysis and Recognition (ICDAR). IEEE, 2020.."},{"key":"e_1_3_2_1_16_1","volume-title":"Table Detection Using Deep Learning[C]\/\/ ICDAR","author":"Gilani A","year":"2017","unstructured":"Gilani A , Qasim S R , Malik I , Table Detection Using Deep Learning[C]\/\/ ICDAR . IEEE Computer Society , 2017 . Gilani A , Qasim S R , Malik I , Table Detection Using Deep Learning[C]\/\/ ICDAR. IEEE Computer Society, 2017."},{"doi-asserted-by":"crossref","unstructured":"He K Gkioxari G P Doll\u00e1r Mask R-CNN[C]\/\/ IEEE. IEEE 2017.  He K Gkioxari G P Doll\u00e1r Mask R-CNN[C]\/\/ IEEE. IEEE 2017.","key":"e_1_3_2_1_17_1","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_1_18_1","volume-title":"MMDetection: Open MMLab Detection Toolbox and Benchmark[J]","author":"Chen K","year":"2019","unstructured":"Chen K , Wang J , Pang J , MMDetection: Open MMLab Detection Toolbox and Benchmark[J] . 2019 . Chen K , Wang J , Pang J , MMDetection: Open MMLab Detection Toolbox and Benchmark[J]. 2019."},{"key":"e_1_3_2_1_19_1","volume-title":"Cascade R-CNN: high quality object detection and instance segmentation. CoRR,abs\/1906.09756","author":"Zhaowei Cai","year":"2019","unstructured":"Zhaowei Cai and Nuno Vasconcelos. Cascade R-CNN: high quality object detection and instance segmentation. CoRR,abs\/1906.09756 , 2019 . Zhaowei Cai and Nuno Vasconcelos. Cascade R-CNN: high quality object detection and instance segmentation. CoRR,abs\/1906.09756, 2019."},{"key":"e_1_3_2_1_20_1","volume-title":"Real-Time Object Detection[C]\/\/ Computer Vision & Pattern Recognition","author":"Redmon J","year":"2016","unstructured":"Redmon J , Divvala S , Girshick R , You Only Look Once: Unified , Real-Time Object Detection[C]\/\/ Computer Vision & Pattern Recognition . IEEE , 2016 . Redmon J , Divvala S , Girshick R , You Only Look Once: Unified, Real-Time Object Detection[C]\/\/ Computer Vision & Pattern Recognition. IEEE, 2016."}],"event":{"acronym":"AIPR 2021","name":"AIPR 2021: 2021 4th International Conference on Artificial Intelligence and Pattern Recognition","location":"Xiamen China"},"container-title":["2021 4th International Conference on Artificial Intelligence and Pattern Recognition"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3488933.3489039","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3488933.3489039","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:49:00Z","timestamp":1750193340000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3488933.3489039"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,24]]},"references-count":20,"alternative-id":["10.1145\/3488933.3489039","10.1145\/3488933"],"URL":"https:\/\/doi.org\/10.1145\/3488933.3489039","relation":{},"subject":[],"published":{"date-parts":[[2021,9,24]]},"assertion":[{"value":"2022-02-25","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}