{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T02:59:03Z","timestamp":1768273143683,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":29,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819556755","type":"print"},{"value":"9789819556762","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\/978-981-95-5676-2_7","type":"book-chapter","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T20:32:19Z","timestamp":1768249939000},"page":"94-108","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Bottom-Up Multi-document Localization Method in\u00a0Unconstrained Environments"],"prefix":"10.1007","author":[{"given":"Qiuman","family":"Tan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wancheng","family":"Jing","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"WenSheng","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,13]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Baek, Y., Lee, B., Han, D., Yun, S., Lee, H.: Character region awareness for text detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9365\u20139374 (2019)","DOI":"10.1109\/CVPR.2019.00959"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Burie, J.-C.: Icdar2015 competition on smartphone document capture and ocr (smartdoc). In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 1161\u20131165. IEEE (2015)","DOI":"10.1109\/ICDAR.2015.7333943"},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Cheng, B., Xiao, B., Wang, J., Shi, H., Huang, T.S., Zhang, L.: Higherhrnet: scale-aware representation learning for bottom-up human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and pattern recognition, pp. 5386\u20135395 (2020)","DOI":"10.1109\/CVPR42600.2020.00543"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"das Neves, R.B., Lima, E., Bezerra, B.L.D., Zanchettin, C., Toselli, A.H.: Hu-pagescan: a fully convolutional neural network for document page crop. IET Image Processing 14(15), 3890\u20133898 (2020)","DOI":"10.1049\/iet-ipr.2020.0532"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Geng, Z., Sun, K., Xiao, B., Zhang, Z., Wang, J.: Bottom-up human pose estimation via disentangled keypoint regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14676\u201314686 (2021)","DOI":"10.1109\/CVPR46437.2021.01444"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Javed, K., Shafait, F.: Real-time document localization in natural images by recursive application of a cnn. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 1, pp. 105\u2013110. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.26"},{"key":"7_CR8","unstructured":"Jiang, T., et al.: Rtmpose: Real-time multi-person pose estimation based on mmpose. arXiv preprint arXiv:2303.07399 (2023)"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Kreiss, S., Bertoni, L., Alahi, A.: Pifpaf: composite fields for human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11977\u201311986 (2019)","DOI":"10.1109\/CVPR.2019.01225"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Li, F., et al.: Mask dino: towards a unified transformer-based framework for object detection and segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3041\u20133050 (2023)","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Li, J., Wang, C., Zhu, H., Mao, Y., Fang, H.-S., Lu, C.: Crowdpose: efficient crowded scenes pose estimation and a new benchmark. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10863\u201310872 (2019)","DOI":"10.1109\/CVPR.2019.01112"},{"key":"7_CR12","unstructured":"Liu, S., Huang, D., Wang, Y.: Learning spatial fusion for single-shot object detection. arXiv preprint arXiv:1911.09516 (2019)"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Liu, Y., Cheng, M.-M., Hu, X., Wang, K., Bai, X.: Richer convolutional features for edge detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3000\u20133009 (2017)","DOI":"10.1109\/CVPR.2017.622"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Luo, Z., Wang, Z., Huang, Y., Wang, L., Tan, T., Zhou, E.: Rethinking the heatmap regression for bottom-up human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13264\u201313273 (2021)","DOI":"10.1109\/CVPR46437.2021.01306"},{"key":"7_CR15","unstructured":"Lyu, C., et al.: Rtmdet: an empirical study of designing real-time object detectors. arXiv preprint arXiv:2212.07784 (2022)"},{"key":"7_CR16","unstructured":"Newell, A., Huang, Z., Deng, J.: Associative embedding: end-to-end learning for joint detection and grouping. Adv. Neural Inform. Process. Syst. 30 (2017)"},{"key":"7_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/978-3-319-46484-8_29","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Newell","year":"2016","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 483\u2013499. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_29"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Paliwal, S.S., Vishwanath, D., Rahul, R., Sharma, M., Vig, L.: Tablenet: deep learning model for end-to-end table detection and tabular data extraction from scanned document images. In: 2019 international conference on document analysis and recognition (ICDAR), pp. 128\u2013133. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00029"},{"key":"7_CR19","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/j.neucom.2021.09.033","volume":"466","author":"R Pan","year":"2021","unstructured":"Pan, R., Zhu, A.: Multi-document detection via corner localization and association. Neurocomputing 466, 37\u201348 (2021)","journal-title":"Neurocomputing"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Skoryukina, N., Shemiakina, J., Arlazarov, V.L., Faradjev, I.: Document localization algorithms based on feature points and straight lines. In: Tenth International Conference on Machine Vision (ICMV 2017), vol. 10696, pp. 385\u2013392. SPIE (2018)","DOI":"10.1117\/12.2311478"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5693\u20135703 (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Toshev, A., Szegedy, C.: Deeppose: human pose estimation via deep neural networks. : Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1653\u20131660 (2014)","DOI":"10.1109\/CVPR.2014.214"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Van\u00a0Nguyen, S., Nguyen, D.A., Pham, L.S.Q.: Digitalization of administrative documents a digital transformation step in practice. In: 2021 8th NAFOSTED Conference on Information and Computer Science (NICS), pp. 519\u2013524. IEEE (2021)","DOI":"10.1109\/NICS54270.2021.9701547"},{"key":"7_CR24","doi-asserted-by":"publisher","unstructured":"Wu, H., Qian, H., Wu, H., van Moorsel, A. LDRNet: enabling real-time document localization on mobile devices. In: Koprinska, I., et al. (eds.) ECML PKDD 2022. CCIS, vol. 1752. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-23618-1_42","DOI":"10.1007\/978-3-031-23618-1_42"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Wu, J., Li, X., Li, X., Ding, H., Tong, Y., Tao, D.: Towards robust referring image segmentation. IEEE Trans. Image Process. (2024)","DOI":"10.1109\/TIP.2024.3371348"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Wu, Y., et al.:Rdlnet: a novel and accurate real-world document localization method. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 9847\u20139855 (2024)","DOI":"10.1145\/3664647.3681655"},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Xie, S., Tu, Z.:Holistically-nested edge detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1395\u20131403 (2015)","DOI":"10.1109\/ICCV.2015.164"},{"key":"7_CR28","first-page":"1","volume":"62","author":"M Yin Zhang","year":"2024","unstructured":"Yin Zhang, M., Ye, G.Z., Liu, Y., Guo, P., Yan, J.: Ffca-yolo for small object detection in remote sensing images. IEEE Trans. Geosci. Remote Sens. 62, 1\u201315 (2024)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"3","key":"7_CR29","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1007\/s10032-019-00341-0","volume":"22","author":"A Zhu","year":"2019","unstructured":"Zhu, A., Zhang, C., Li, Z., Xiong, S.: Coarse-to-fine document localization in natural scene image with regional attention and recursive corner refinement. Inter. J. Document Analy. Recogn. (IJDAR) 22(3), 351\u2013360 (2019). https:\/\/doi.org\/10.1007\/s10032-019-00341-0","journal-title":"Inter. J. Document Analy. Recogn. (IJDAR)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5676-2_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T20:32:23Z","timestamp":1768249943000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5676-2_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819556755","9789819556762"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5676-2_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"13 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","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":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}