{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T01:07:10Z","timestamp":1774314430009,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":25,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,18]],"date-time":"2024-04-18T00:00:00Z","timestamp":1713398400000},"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":[[2024,4,18]]},"DOI":"10.1145\/3603287.3651184","type":"proceedings-article","created":{"date-parts":[[2024,4,27]],"date-time":"2024-04-27T12:06:34Z","timestamp":1714219594000},"page":"199-204","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Optimum Deep Learning Method for Document Layout Analysis in Low Resource Languages"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4981-7822","authenticated-orcid":false,"given":"Md. Mutasim Billah Abu Noman","family":"Akanda","sequence":"first","affiliation":[{"name":"Apurba Technologies, Dhaka, Bangladesh"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1923-1738","authenticated-orcid":false,"given":"Maruf","family":"Ahmed","sequence":"additional","affiliation":[{"name":"Apurba Technologies, Dhaka, Bangladesh"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3994-3105","authenticated-orcid":false,"given":"AKM Shahariar Azad","family":"Rabby","sequence":"additional","affiliation":[{"name":"Apurba Technologies, Dhaka, Bangladesh"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8670-7124","authenticated-orcid":false,"given":"Fuad","family":"Rahman","sequence":"additional","affiliation":[{"name":"Apurba Technologies, Sunnyvale, California, USA"}]}],"member":"320","published-online":{"date-parts":[[2024,4,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355610"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99978-4_31"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"e_1_3_2_1_4_1","volume-title":"The KITTI Vision Benchmark Suite. URL http:\/\/www.cvlibs.net\/datasets\/kitti 2.5","author":"Geiger Andreas","year":"2015","unstructured":"Andreas Geiger, Philip Lenz, Christoph Stiller, and Raquel Urtasun. 2015. The KITTI Vision Benchmark Suite. URL http:\/\/www.cvlibs.net\/datasets\/kitti 2.5 (2015)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_6_1","volume-title":"Mobilenets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv preprint arXiv:1704.04861","author":"Howard Andrew G.","year":"2017","unstructured":"Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. Mobilenets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv preprint arXiv:1704.04861 (2017)."},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.","author":"Huang Gao","unstructured":"Gao Huang, Zhuang Liu, Laurens Van Der Maaten, and Kilian Q. Weinberger. 2017. Densely Connected Convolutional Networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548112"},{"key":"e_1_3_2_1_9_1","unstructured":"Glenn Jocher Ayush Chaurasia and Jing Qiu. 2023. Ultralytics YOLO. https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"e_1_3_2_1_10_1","volume-title":"Hinton","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. 2012. Imagenet Classification with Deep Convolutional Neural Networks. Advances in Neural Information Processing Systems 25 (2012)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547911"},{"key":"e_1_3_2_1_13_1","volume-title":"Zurich, Switzerland","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C. Lawrence Zitnick. 2014. Microsoft COCO: Common Objects in Context. In Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V. Springer International Publishing."},{"key":"e_1_3_2_1_14_1","volume-title":"Berg","author":"Liu Wei","year":"2016","unstructured":"Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, and Alexander C. Berg. 2016. SSD: Single Shot MultiBox Detector. In Computer Vision-ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part I, Vol. 14. Springer International Publishing."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2005.4"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_2_1_17_1","volume-title":"Advances in Neural Information Processing Systems.","author":"Ren Shaoqing","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster R-CNN: Towards Real-time Object Detection with Region Proposal Networks. In Advances in Neural Information Processing Systems. Vol. 28."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/3477.537322"},{"key":"e_1_3_2_1_19_1","volume-title":"Badlad: A Large Multi-domain Bengali Document Layout Analysis Dataset. In International Conference on Document Analysis and Recognition. Springer, 326--341","author":"Hossain Shihab Md Istiak","year":"2023","unstructured":"Md Istiak Hossain Shihab, Md Rakibul Hasan, Mahfuzur Rahman Emon, Syed Mobassir Hossen, Md Nazmuddoha Ansary, Intesur Ahmed, Fazle Rabbi Rakib, Shahriar Elahi Dhruvo, Souhardya Saha Dip, Akib Hasan Pavel, et al. 2023. Badlad: A Large Multi-domain Bengali Document Layout Analysis Dataset. In International Conference on Document Analysis and Recognition. Springer, 326--341."},{"key":"e_1_3_2_1_20_1","volume-title":"A Comprehensive Review of YOLO: From YOLOv1 to YOLOv8 and Beyond. arXiv preprint arXiv:2304.00501","author":"Terven Juan","year":"2023","unstructured":"Juan Terven and Diana Cordova-Esparza. 2023. A Comprehensive Review of YOLO: From YOLOv1 to YOLOv8 and Beyond. arXiv preprint arXiv:2304.00501 (2023)."},{"key":"e_1_3_2_1_21_1","volume-title":"Attention is All You Need. Advances in Neural Information Processing Systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All You Need. Advances in Neural Information Processing Systems 30 (2017)."},{"key":"e_1_3_2_1_22_1","volume-title":"MLP and GMM Classifiers for Layout Analysis of Historical Documents. In The 12th International Conference on Document Analysis and Recognition. IEEE, 1220--1224","author":"Wei Hao","year":"2013","unstructured":"Hao Wei, Micheal Baechler, Fouad Slimane, and Rolf Ingold. 2013. Evaluation of SVM, MLP and GMM Classifiers for Layout Analysis of Historical Documents. In The 12th International Conference on Document Analysis and Recognition. IEEE, 1220--1224."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1908.07836"},{"key":"e_1_3_2_1_24_1","unstructured":"Jun-Yan Zhu Taesung Park Phillip Isola and Alexei A Efros. 2017. Unpaired Image-to-image Translation Using Cycle-consistent Adversarial Networks. (2017) 2223--2232."},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.","author":"Zoph Barret","unstructured":"Barret Zoph, Vijay Vasudevan, Jonathon Shlens, and Quoc V. Le. 2018. Learning Transferable Architectures for Scalable Image Recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition."}],"event":{"name":"ACM SE '24: 2024 ACM Southeast Conference","location":"Marietta GA USA","acronym":"ACM SE '24","sponsor":["ACM Association for Computing Machinery"]},"container-title":["Proceedings of the 2024 ACM Southeast Conference on ZZZ"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3603287.3651184","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3603287.3651184","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T17:05:58Z","timestamp":1756487158000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3603287.3651184"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,18]]},"references-count":25,"alternative-id":["10.1145\/3603287.3651184","10.1145\/3603287"],"URL":"https:\/\/doi.org\/10.1145\/3603287.3651184","relation":{},"subject":[],"published":{"date-parts":[[2024,4,18]]},"assertion":[{"value":"2024-04-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}