{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,16]],"date-time":"2026-11-16T18:06:31Z","timestamp":1794852391659,"version":"4.9.1"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370433","type":"print"},{"value":"9783032370440","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-3-032-37044-0_7","type":"book-chapter","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:19:49Z","timestamp":1788891589000},"page":"117-132","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["RT-DocLayout: Real-Time End-to-End Document Layout Analysis with\u00a0Reading Order in\u00a0the\u00a0Wild"],"prefix":"10.1007","author":[{"given":"Cheng","family":"Cui","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tingquan","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xueqing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changda","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yubo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zelun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaxuan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manhui","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suyin","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiqing","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,9]]},"reference":[{"key":"7_CR1","unstructured":"Blecher, L., Cucurull, G., Scialom, T., Stojnic, R.: Nougat: Neural optical understanding for academic documents (2023). https:\/\/arxiv.org\/abs\/2308.13418"},{"key":"7_CR2","unstructured":"Cui, C., et al.: Paddleocr-vl-1.5: Towards a multi-task 0.9b VLM for robust in-the-wild document parsing (2026). https:\/\/arxiv.org\/abs\/2601.21957"},{"key":"7_CR3","unstructured":"Cui, C., et al.: Paddleocr-vl: Boosting multilingual document parsing via a 0.9b ultra-compact vision-language model (2025). https:\/\/arxiv.org\/abs\/2510.14528"},{"key":"7_CR4","unstructured":"Feng, H., et al.: Dolphin-v2: Universal document parsing via scalable anchor prompting (2026). https:\/\/arxiv.org\/abs\/2602.05384"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Feng, H., et al.: Dolphin: Document image parsing via heterogeneous anchor prompting (2025). https:\/\/arxiv.org\/abs\/2505.14059","DOI":"10.18653\/v1\/2025.findings-acl.1130"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Gu, Z., et al.: Xylayoutlm: Towards layout-aware multimodal networks for visually-rich document understanding (2022). https:\/\/arxiv.org\/abs\/2203.06947","DOI":"10.1109\/CVPR52688.2022.00454"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Ha, J., Haralick, R.M., Phillips, I.T.: Recursive xy cut using bounding boxes of connected components. In: Proceedings of 3rd International Conference on Document Analysis and Recognition. vol.\u00a02, pp. 952\u2013955. IEEE (1995)","DOI":"10.1109\/ICDAR.1995.602059"},{"key":"7_CR8","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn (2018). https:\/\/arxiv.org\/abs\/1703.06870"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Huang, Y., Lv, T., Cui, L., Lu, Y., Wei, F.: Layoutlmv3: Pre-training for document ai with unified text and image masking (2022). https:\/\/arxiv.org\/abs\/2204.08387","DOI":"10.1145\/3503161.3548112"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Kim, G., et al.: OCR-free document understanding transformer (2022). https:\/\/arxiv.org\/abs\/2111.15664","DOI":"10.1007\/978-3-031-19815-1_29"},{"key":"7_CR11","unstructured":"Lee, C.Y., et al.: Rope: Reading order equivariant positional encoding for graph-based document information extraction (2021). https:\/\/arxiv.org\/abs\/2106.10786"},{"key":"7_CR12","unstructured":"Li, F., et al.: Mask dino: Towards a unified transformer-based framework for object detection and segmentation (2022). https:\/\/arxiv.org\/abs\/2206.02777"},{"key":"7_CR13","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 (2022). https:\/\/arxiv.org\/abs\/2203.02378","DOI":"10.1145\/3503161.3547911"},{"key":"7_CR14","unstructured":"Li, Y., Yang, G., Liu, H., Wang, B., Zhang, C.: dots.ocr: Multilingual document layout parsing in a single vision-language model (2025). https:\/\/arxiv.org\/abs\/2512.02498"},{"key":"7_CR15","unstructured":"Li, Z., et al.: Monkeyocr: Document parsing with a structure-recognition-relation triplet paradigm (2026). https:\/\/arxiv.org\/abs\/2506.05218"},{"key":"7_CR16","unstructured":"Niu, J., et al.: Mineru2.5: A decoupled vision-language model for efficient high-resolution document parsing (2025). https:\/\/arxiv.org\/abs\/2509.22186"},{"key":"7_CR17","unstructured":"opendatalab: Mineru2.0-2505-0.9b. https:\/\/huggingface.co\/opendatalab\/MinerU2.0-2505-0.9B (2025)"},{"key":"7_CR18","unstructured":"Ouyang, L., et al.: Omnidocbench: Benchmarking diverse pdf document parsing with comprehensive annotations (2025). https:\/\/arxiv.org\/abs\/2412.07626"},{"key":"7_CR19","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: Towards real-time object detection with region proposal networks (2016). https:\/\/arxiv.org\/abs\/1506.01497"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Shen, Z., Zhang, R., Dell, M., Lee, B.C.G., Carlson, J., Li, W.: Layoutparser: A unified toolkit for deep learning based document image analysis (2021). https:\/\/arxiv.org\/abs\/2103.15348","DOI":"10.1007\/978-3-030-86549-8_9"},{"key":"7_CR21","unstructured":"Tang, Z., et al.: Unifying vision, text, and layout for universal document processing (2023). https:\/\/arxiv.org\/abs\/2212.02623"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Wang, J., Hu, K., Huo, Q.: Dlaformer: An end-to-end transformer for document layout analysis (2024). https:\/\/arxiv.org\/abs\/2405.11757","DOI":"10.1007\/978-3-031-70546-5_3"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Wang, Z., Xu, Y., Cui, L., Shang, J., Wei, F.: Layoutreader: Pre-training of text and layout for reading order detection (2021). https:\/\/arxiv.org\/abs\/2108.11591","DOI":"10.18653\/v1\/2021.emnlp-main.389"},{"key":"7_CR24","unstructured":"Xu, Y., et al.: Layoutlmv2: Multi-modal pre-training for visually-rich document understanding (2022). https:\/\/arxiv.org\/abs\/2012.14740"},{"key":"7_CR25","doi-asserted-by":"publisher","unstructured":"Xu, Y., Li, M., Cui, L., Huang, S., Wei, F., Zhou, M.: Layoutlm: pre-training of text and layout for document image understanding. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery amp; Data Mining, pp. 1192\u20131200. KDD \u201920, ACM (Aug 2020). https:\/\/doi.org\/10.1145\/3394486.3403172","DOI":"10.1145\/3394486.3403172"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Zhao, Y., et al.: DETRs beat YOLOs on real-time object detection (2024). https:\/\/arxiv.org\/abs\/2304.08069","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"7_CR27","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 (2024). https:\/\/arxiv.org\/abs\/2410.12628"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Zhong, X., Tang, J., Yepes, A.J.: Publaynet: largest dataset ever for document layout analysis (2019). https:\/\/arxiv.org\/abs\/1908.07836","DOI":"10.1109\/ICDAR.2019.00166"},{"key":"7_CR29","unstructured":"Zhou, C., et al.: Real5-omnidocbench: A full-scale physical reconstruction benchmark for robust document parsing in the wild (2026). https:\/\/arxiv.org\/abs\/2603.04205"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37044-0_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:19:54Z","timestamp":1788891594000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37044-0_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370433","9783032370440"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37044-0_7","relation":{"is-part-of":[{"id-type":"doi","id":"https:\/\/doi.org\/10.1007\/978-3-032-37044-0","asserted-by":"object"}]},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"9 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}