{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T07:32:00Z","timestamp":1772695920786,"version":"3.50.1"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032046260","type":"print"},{"value":"9783032046277","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"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\/978-3-032-04627-7_28","type":"book-chapter","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T02:06:09Z","timestamp":1757988369000},"page":"485-505","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["HiLEx: Image-Based Hierarchical Layout Extraction from\u00a0Question Papers"],"prefix":"10.1007","author":[{"given":"Utathya","family":"Aich","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinjini","family":"Chakraborty","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deepan","family":"Sadhukhan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Swarnendu","family":"Ghosh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tulika","family":"Saha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,16]]},"reference":[{"key":"28_CR1","doi-asserted-by":"publisher","unstructured":"Binmakhashen, G.M., Mahmoud, S.A.: Document layout analysis: a comprehensive survey. ACM Comput. Surv. 52(6), Article 109, 36 p (2020). https:\/\/doi.org\/10.1145\/3355610","DOI":"10.1145\/3355610"},{"key":"28_CR2","doi-asserted-by":"publisher","unstructured":"Xing, H., et al.: DocHieNet: a large and diverse dataset for document hierarchy parsing. In: Al-Onaizan, Y., Bansal, M., Chen, Y.-N. (eds.) Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 1129\u20131142. Association for Computational Linguistics, Miami, Florida, USA (2024). https:\/\/doi.org\/10.18653\/v1\/2024.emnlp-main.65, https:\/\/aclanthology.org\/2024.emnlp-main.65\/","DOI":"10.18653\/v1\/2024.emnlp-main.65"},{"key":"28_CR3","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 preprint https:\/\/arxiv.org\/abs\/2410.12628 (2024)"},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"Lewis, D., Agam, G., Argamon, S., Frieder, O., Grossman, D., Heard, J.: Building a Test Collection for Complex Document Information Processing. SIGIR \u201906, pp. 665\u2013666","DOI":"10.1145\/1148170.1148307"},{"key":"28_CR5","doi-asserted-by":"crossref","unstructured":"Harley, A.W., Ufkes, A., Derpanis, K.G.: 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":"28_CR6","doi-asserted-by":"crossref","unstructured":"Zhong, X., Tang, J., Yepes, A.J.: PubLayNet: largest dataset ever for document layout analysis (2019). arXiv preprint arXiv:1908.07836","DOI":"10.1109\/ICDAR.2019.00166"},{"key":"28_CR7","doi-asserted-by":"crossref","unstructured":"Li, Y., Huang, L., Cao, J., Cui, Z., Chen, Z.: DocBank: a benchmark dataset for document layout analysis. In: Proceedings of the 28th International Conference on Computational Linguistics, pp. 949\u2013960. International Committee on Computational Linguistics, Barcelona, Spain (Online) (2020). https:\/\/aclanthology.org\/2020.coling-main.82\/","DOI":"10.18653\/v1\/2020.coling-main.82"},{"key":"28_CR8","doi-asserted-by":"publisher","unstructured":"Pfitzmann, B., Auer, C., Dolfi, M., Nassar, A.S., 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. Association for Computing Machinery, New York, NY, USA (2022). https:\/\/doi.org\/10.1145\/3534678.3539043","DOI":"10.1145\/3534678.3539043"},{"key":"28_CR9","unstructured":"Da, C., Luo, C., Zheng, Q., Yao, C.: D$$^4$$LA: A Diverse Benchmark for Document Layout Analysis (2023). Retrieved from https:\/\/doi.org\/10.57702\/7lissvsc"},{"key":"28_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":"28_CR11","unstructured":"Li, M., Cui, L., Huang, S., Wei, F., Zhou, M., Li, Z.: TableBank: A Benchmark Dataset for Table Detection and Recognition (2019). arXiv preprint arXiv:1903.01949 (2019)"},{"key":"28_CR12","unstructured":"GMAT. GMAT Sample Question Paper 2023 With 100 Q And A | EduAims. https:\/\/eduaims.in\/gmat-sample-paper-pdf\/"},{"key":"28_CR13","unstructured":"Hank Walker. https:\/\/people.engr.tamu.edu\/d-walker\/index.html"},{"key":"28_CR14","unstructured":"GRE Practice Book (2004). https:\/\/www.prepscholar.com\/gre\/blog\/wp-content\/uploads\/sites\/3\/2016\/09\/GRE_practicebook_2004.pdf"},{"key":"28_CR15","unstructured":"GRE. GR9768.pdf. https:\/\/wmich.edu\/mathclub\/files\/GR9768.pdf"},{"key":"28_CR16","unstructured":"MANHATTAN PREP. 5 lb. Book. https:\/\/dl.icdst.org\/pdfs\/files1\/eceb4737c3836a94ef7ba0b88ae5510b.pdf"},{"key":"28_CR17","unstructured":"SAT Sample Questions. SAT Study Guide 2020 - Practice Test 9. https:\/\/satsuite.collegeboard.org\/media\/pdf\/sat-practice-test-9.pdf"},{"key":"28_CR18","unstructured":"SAT Sample Questions. SAT Study Guide 2020 - Practice Test 10. https:\/\/satsuite.collegeboard.org\/media\/pdf\/sat-practice-test-10.pdf"},{"key":"28_CR19","unstructured":"SAT Sample Questions. SAT Study Guide 2020 - Practice Test 3. https:\/\/satsuite.collegeboard.org\/media\/pdf\/sat-practice-test-3.pdf"},{"key":"28_CR20","unstructured":"UGC NET. University Grants Commission - NET. https:\/\/www.ugcnetonline.in\/previous_question_papers.php"},{"key":"28_CR21","unstructured":"GATE. GATE 2022 Official Site. https:\/\/gate.iitkgp.ac.in\/old_question_papers.html"},{"key":"28_CR22","unstructured":"Jocher, G., Chaurasia, A., Qiu, J., et al.: Ultralytics YOLOv8: Cutting-Edge, Real-Time Object Detection (2023). https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"28_CR23","unstructured":"Jocher, G., Chaurasia, A., Qiu, J., et al.: Ultralytics YOLOv9: Advanced Real-Time Object Detection (2024). https:\/\/github.com\/ultralytics\/yolov9"},{"key":"28_CR24","unstructured":"Jocher, G., Chaurasia, A., Qiu, J., et al.: Ultralytics YOLOv10: Next-Gen Real-Time Object Detection (2024). https:\/\/github.com\/ultralytics\/yolov10"},{"key":"28_CR25","unstructured":"Jocher, G., Chaurasia, A., Qiu, J., et al.: Ultralytics YOLOv11: State-of-the-Art Object Detection (2024). https:\/\/github.com\/ultralytics\/yolov11"},{"key":"28_CR26","unstructured":"Jocher, G., Chaurasia, A., Qiu, J., et al.: Ultralytics YOLOv12: Cutting-Edge Vision Model (2025). https:\/\/github.com\/ultralytics\/yolov12"},{"key":"28_CR27","unstructured":"Chen, S., Liu, X., Shen, J., et al.: RT-DETR: Real-Time End-to-End Object Detection with Transformers (2023). https:\/\/github.com\/IDEA-Research\/RT-DETR"},{"key":"28_CR28","unstructured":"Wu, Y., Kirillov, A., Massa, F., et al.: Detectron2: A PyTorch-based Modular Object Detection Library (2019). https:\/\/github.com\/facebookresearch\/detectron2"},{"key":"28_CR29","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., et al.: DETR: End-to-End Object Detection with Transformers (2020). https:\/\/github.com\/facebookresearch\/detr","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"28_CR30","unstructured":"Xiao, B., et al.: Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks. arXiv preprint arXiv:2311.06242 (2023). https:\/\/arxiv.org\/abs\/2311.06242"},{"key":"28_CR31","unstructured":"Steiner, A., et al.: PaliGemma 2: A Family of Versatile VLMs for Transfer. arXiv preprint arXiv:2412.03555 (2024). https:\/\/arxiv.org\/abs\/2412.03555"},{"key":"28_CR32","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Proceedings of the European Conference on Computer Vision (ECCV) (2014). https:\/\/arxiv.org\/abs\/1405.0312","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"28_CR33","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016). https:\/\/arxiv.org\/abs\/1506.02640","DOI":"10.1109\/CVPR.2016.91"}],"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\/978-3-032-04627-7_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T02:06:20Z","timestamp":1757988380000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04627-7_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,16]]},"ISBN":["9783032046260","9783032046277"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04627-7_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,16]]},"assertion":[{"value":"16 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"}}]}}