{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T17:38:00Z","timestamp":1758044280398,"version":"3.44.0"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032046130","type":"print"},{"value":"9783032046147","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,13]],"date-time":"2025-09-13T00:00:00Z","timestamp":1757721600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,13]],"date-time":"2025-09-13T00:00:00Z","timestamp":1757721600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-04614-7_2","type":"book-chapter","created":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T12:22:38Z","timestamp":1757679758000},"page":"23-39","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["IndicDLP: A Foundational Dataset for\u00a0Multi-lingual and\u00a0Multi-domain Document Layout Parsing"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5407-0455","authenticated-orcid":false,"given":"Oikantik","family":"Nath","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5483-2232","authenticated-orcid":false,"given":"Sahithi","family":"Kukkala","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3687-9922","authenticated-orcid":false,"given":"Mitesh","family":"Khapra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4134-1154","authenticated-orcid":false,"given":"Ravi Kiran","family":"Sarvadevabhatla","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,13]]},"reference":[{"key":"2_CR1","unstructured":"Shodhganga. https:\/\/shodhganga.inflibnet.ac.in\/"},{"key":"2_CR2","unstructured":"Shoonya. https:\/\/github.com\/AI4Bharat\/Shoonya"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Antonacopoulos, A., Bridson, D., Papadopoulos, C., Pletschacher, S.: Prima: a realistic dataset for performance evaluation of document layout analysis. In: Proceedings of the 10th International Conference on Document Analysis and Recognition (ICDAR2009), Barcelona, Spain, pp. 296\u2013300 (2009)","DOI":"10.1109\/ICDAR.2009.271"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Appalaraju, S., Jasani, B., Kota, B.U., Xie, Y., Manmatha, R.: Docformer: end-to-end transformer for document understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00103"},{"key":"2_CR5","doi-asserted-by":"publisher","unstructured":"Auer, C., Dolfi, M., Carvalho, A., Berrospi\u00a0Ramis, C., Staar, P.W.J.: Delivering document conversion as a cloud service with high throughput and responsiveness. In: Proceedings of the 2022 IEEE 15th International Conference on Cloud Computing (CLOUD), pp. 363\u2013373. IEEE (2022). https:\/\/doi.org\/10.1109\/CLOUD55607.2022.00060","DOI":"10.1109\/CLOUD55607.2022.00060"},{"key":"2_CR6","doi-asserted-by":"publisher","unstructured":"Banerjee, A., Biswas, S., Llad\u00f3s, J., Pal, U.: Swindocsegmenter: an end-to-end unified domain adaptive transformer for document instance segmentation. In: Document Analysis and Recognition - ICDAR 2023 - 17th International Conference, San Jos\u00e9, CA, USA, August 21\u201326, 2023, Proceedings, Part I. Lecture Notes in Computer Science, vol. 14187, pp. 307\u2013325 (2023). https:\/\/doi.org\/10.1007\/978-3-031-41676-7_18","DOI":"10.1007\/978-3-031-41676-7_18"},{"key":"2_CR7","unstructured":"Biswas, S., Banerjee, A., Llad\u00f3s, J., Pal, U.: Docsegtr: an instance-level end-to-end document image segmentation transformer (2022)"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection (2017)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Rodla: benchmarking the robustness of document layout analysis models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.01473"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Cheng, H., et al.: M6doc: a large-scale multi-format, multi-type, multi-layout, multi-language, multi-annotation category dataset for modern document layout analysis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15138\u201315147 (2023)","DOI":"10.1109\/CVPR52729.2023.01453"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Da, C., Luo, C., Zheng, Q., Yao, C.: Vision grid transformer for document layout analysis. In: IEEE International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.01783"},{"issue":"9","key":"2_CR12","doi-asserted-by":"publisher","DOI":"10.1002\/eng2.12832","volume":"6","author":"A Fateh","year":"2024","unstructured":"Fateh, A., Fateh, M., Abolghasemi, V.: Enhancing optical character recognition: Efficient techniques for document layout analysis and text line detection. Eng. Rep. 6(9), e12832 (2024). https:\/\/doi.org\/10.1002\/eng2.12832","journal-title":"Eng. Rep."},{"key":"2_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2021.116601","volume":"102","author":"HT Ha","year":"2022","unstructured":"Ha, H.T., Hor\u00e1k, A.: Information extraction from scanned invoice images using text analysis and layout features. Signal Process. Image Commun. 102, 116601 (2022). https:\/\/doi.org\/10.1016\/j.image.2021.116601","journal-title":"Signal Process. Image Commun."},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Harley, A., Ufkes, A., Derpanis, K.: Evaluation of deep convolutional nets for document image classification and retrieval. In: International Conference on Document Analysis and Recognition (ICDAR) (2015)","DOI":"10.1109\/ICDAR.2015.7333910"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"2_CR16","doi-asserted-by":"publisher","first-page":"150451","DOI":"10.1109\/ACCESS.2024.3479990","volume":"12","author":"ES Jaha","year":"2024","unstructured":"Jaha, E.S.: Comparative semantic document layout analysis for enhanced document image retrieval. IEEE Access 12, 150451\u2013150467 (2024). https:\/\/doi.org\/10.1109\/ACCESS.2024.3479990","journal-title":"IEEE Access"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Li, J., Xu, Y., Lv, T., Cui, L., Zhang, C., Wei, F.: DIT: self-supervised pre-training for document image transformer. In: Proceedings of the ACM Multimedia Conference (2022)","DOI":"10.1145\/3503161.3547911"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: Docbank: a benchmark dataset for document layout analysis. In: Proceedings of the International Conference on Computational Linguistics (COLING) (2020)","DOI":"10.18653\/v1\/2020.coling-main.82"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Li, P., et al.: SelfDOC: self-supervised document representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00560"},{"key":"2_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"2_CR21","unstructured":"Liu, W., et al.: SSD: single shot multibox detector (2015)"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Pfitzmann, B., Auer, C., Dolfi, M., Nassar, A., Staar, P.: Doclaynet: a large human-annotated dataset for document-layout segmentation. In: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 3743\u20133751 (2022)","DOI":"10.1145\/3534678.3539043"},{"key":"2_CR23","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks (2015)"},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Shihab, M., et al.: Badlad: a large multi-domain Bengali document layout analysis dataset. In: IEEE International Conference on Document Analysis and Recognition (ICDAR) (2023)","DOI":"10.1007\/978-3-031-41676-7_19"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Tang, Z., et al.: Unifying vision, text, and layout for universal document processing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.01845"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Terven, J., Cordova-Esparza, D.: A comprehensive review of yolo architectures in computer vision: From yolov1 to yolov8 and yolo-nas. ArXiv (2023)","DOI":"10.3390\/make5040083"},{"key":"2_CR27","unstructured":"Wang, A., et al.: Yolov10: real-time end-to-end object detection. In: Proceedings of the Neural Information Processing Systems Conference (NeurIPS) (2024)"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Xiao, B., et al.: Florence-2: advancing a unified representation for a variety of vision tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"2_CR29","unstructured":"Zhang, H., et al.: Dino: DETR with improved denoising anchor boxes for end-to-end object detection. ArXiv (2022)"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, N., et al.: M2doc: a multi-modal fusion approach for document layout analysis. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 7233\u20137241 (2024)","DOI":"10.1609\/aaai.v38i7.28552"},{"key":"2_CR31","unstructured":"Zhao, Z., Kang, H., Wang, B., He, C.: Doclayout-yolo: enhancing document layout analysis through diverse synthetic data and global-to-local adaptive perception. arXiv (2024)"},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Zhong, X., Tang, J., Jimeno-Yepes, A.: Publaynet: largest dataset ever for document layout analysis. In: IEEE International Conference on Document Analysis and Recognition (ICDAR) (2019)","DOI":"10.1109\/ICDAR.2019.00166"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04614-7_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T12:22:49Z","timestamp":1757679769000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04614-7_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,13]]},"ISBN":["9783032046130","9783032046147"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04614-7_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,13]]},"assertion":[{"value":"13 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wuhan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iapr.org\/icdar2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}