{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T11:12:10Z","timestamp":1783768330377,"version":"3.55.0"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T00:00:00Z","timestamp":1778025600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T00:00:00Z","timestamp":1778025600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52472337"],"award-info":[{"award-number":["52472337"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s00530-026-02314-w","type":"journal-article","created":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:42:42Z","timestamp":1778046162000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-document localization method based on bottom-up architecture"],"prefix":"10.1007","volume":"32","author":[{"given":"Kun","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiuman","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wancheng","family":"Jing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"WenSheng","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,6]]},"reference":[{"key":"2314_CR1","doi-asserted-by":"crossref","unstructured":"Paliwal, D.S.S., Rahul, V.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":"2314_CR2","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, pages 9365\u20139374, (2019)","DOI":"10.1109\/CVPR.2019.00959"},{"key":"2314_CR3","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), Volume 1, pp. 105\u2013110, IEEE, (2017)","DOI":"10.1109\/ICDAR.2017.26"},{"key":"2314_CR4","doi-asserted-by":"crossref","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, International Journal on Document Analysis and Recognition (IJDAR), 22:351\u2013360, Springer, (2019)","DOI":"10.1007\/s10032-019-00341-0"},{"key":"2314_CR5","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":"2314_CR6","doi-asserted-by":"crossref","unstructured":"Wu, H., Qian, H., Wu, H., Moorsel, A.V.: LDRNet: enabling real-time document localization on mobile devices. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pp. 618\u2013629, Springer, (2022)","DOI":"10.1007\/978-3-031-23618-1_42"},{"key":"2314_CR7","doi-asserted-by":"crossref","unstructured":"Wu, Y., Xu, Z., Duan, Y., Wu, Y., Zheng, Q., Li, H., Hu, X.,Jin, L.: 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":"2314_CR8","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":"2314_CR9","unstructured":"Jiang, T., Lu, P., Zhang, L., Ma, N., Han, R., Lyu, C., Li, Y., Chen, K.: Rtmpose: real-time multi-person pose estimation based on mmpose, arXiv preprint arXiv:2303.07399, (2023)"},{"key":"2314_CR10","doi-asserted-by":"crossref","unstructured":"Toshev, A., Szegedy, C.: Deeppose: hman pose estimation via deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1653\u20131660, (2014)","DOI":"10.1109\/CVPR.2014.214"},{"key":"2314_CR11","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S., Sheikh, Y.: Realtime multi-person 2d pose estimation using part affinity fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7291\u20137299, (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"2314_CR12","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":"2314_CR13","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":"2314_CR14","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":"2314_CR15","unstructured":"Poma, S., Riba, E., Sappa, A.: Dense extreme inception network: Towards a robust cnn model for edge detection. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp. 1923\u20131932, (2020)"},{"key":"2314_CR16","unstructured":"Zhuo, S., Liu, W., Zitong, Yu., Dewen, H., Liao, Q., Tian, Q., Pietik\u00e4inen, M., Liu, L.: Pixel difference networks for efficient edge detection. In: oceedings of the IEEE\/CVF international conference on computer vision, pp. 5117\u20135127, (2021)"},{"key":"2314_CR17","doi-asserted-by":"crossref","unstructured":"Pu, M., Huang, Y., Liu, Y.,Guan, Q., Ling, H.: Edter: edge detection with transformer. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 1402\u20131412, (2022)","DOI":"10.1109\/CVPR52688.2022.00146"},{"key":"2314_CR18","doi-asserted-by":"crossref","unstructured":"Zhou, C., Huang, Y., Pu, M., Guan, Q., Deng, R., Ling, H.: Muge: multiple granularity edge detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 952\u201325962, (2024)","DOI":"10.1109\/CVPR52733.2024.02452"},{"issue":"7","key":"2314_CR19","first-page":"6675","volume":"38","author":"Y Ye","year":"2024","unstructured":"Ye, Y., Kai, X., Huang, Y., Yi, R., Cai, Z.: Diffusionedge: diffusion probabilistic model for crisp edge detection. Proc. AAAI Conf. Artif Intell. 38(7), 6675\u20136683 (2024)","journal-title":"Proc. AAAI Conf. Artif Intell."},{"key":"2314_CR20","doi-asserted-by":"crossref","unstructured":"Zhou, C., Huang, Y., Pu, M., Guan, Q., Huang, L., Ling, H.: The treasure beneath multiple annotations: An uncertainty-aware edge detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15507\u201315517, (2024)","DOI":"10.1109\/CVPR52729.2023.01488"},{"key":"2314_CR21","doi-asserted-by":"crossref","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: European conference on computer vision, pp. 483\u2013499, Springer, (2016)","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"2314_CR22","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":"2314_CR23","doi-asserted-by":"crossref","unstructured":"Huang, J., Zhu, Z., Guo, F., Huang, G.: The devil is in the details: delving into unbiased data processing for human pose estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 5700\u20135709, (2020)","DOI":"10.1109\/CVPR42600.2020.00574"},{"key":"2314_CR24","doi-asserted-by":"crossref","unstructured":"Sun, X., Xiao, B., Wei, F., Liang, S., Wei, Y.: Integral human pose regression. In: Proceedings of the European conference on computer vision (ECCV), pp. 529\u2013545, (2018)","DOI":"10.1007\/978-3-030-01231-1_33"},{"key":"2314_CR25","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":"2314_CR26","doi-asserted-by":"crossref","unstructured":"Maji, D., Nagori, S., Mathew, M., Poddar, D.: Yolo-pose: enhancing yolo for multi person pose estimation using object keypoint similarity loss. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 2637\u20132646, (2022)","DOI":"10.1109\/CVPRW56347.2022.00297"},{"key":"2314_CR27","unstructured":"Jiang,T., Lu, P., Zhang, L., Ma, N., Han, R., Lyu, C., Li, Y., Chen, K.: RTMPose: real-time multi-person pose estimation based on MMPose, arXiv preprint arXiv:2303.07399, (2023)"},{"key":"2314_CR28","doi-asserted-by":"crossref","unstructured":"Ronneberger, O.,Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: International Conference on Medical image computing and computer-assisted intervention, pp. 234\u2013241, Springer, (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"2314_CR29","doi-asserted-by":"crossref","unstructured":"Shan, Z., Wang, Y., Wei, S., Li, X., Pang, H., Zhou, X.: Docscanner: document location and enhancement based on image segmentation. In: 2022 18th International Conference on Computational Intelligence and Security (CIS), pp. 98\u2013101, IEEE, (2022)","DOI":"10.1109\/CIS58238.2022.00028"},{"key":"2314_CR30","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\u20133892, SPIE, (2018)","DOI":"10.1117\/12.2311478"},{"key":"2314_CR31","doi-asserted-by":"crossref","unstructured":"Nguyen, H.D., Vu, D.N., Nguyen, V.A., Nguyen, T.D., Nguyen, P.L.: A robust document localization solution with segmentation and clustering. In: International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, pp. 167\u2013179, Springer, (2023)","DOI":"10.1007\/978-3-031-36819-6_15"},{"key":"2314_CR32","doi-asserted-by":"publisher","unstructured":"Sun, Z., Peng, J., Li, M, Wang, H.: Hierarchical Sequential Context Modelling for High-Fidelity Image Inpainting. IEEE Transactions on Circuits and Systems for Video Technology (2025). https:\/\/doi.org\/10.1109\/TCSVT.2025.3647673","DOI":"10.1109\/TCSVT.2025.3647673"},{"key":"2314_CR33","doi-asserted-by":"crossref","unstructured":"Wang, H., Chen, Y., Yao, M., Liu, W., Peng, J, Xu. F.: Tensor completion framework by graph refinement for incomplete multi-view clustering. IEEE Transactions on Multimedia (2025)","DOI":"10.1109\/TMM.2025.3613125"},{"key":"2314_CR34","first-page":"1","volume":"62","author":"Y Zhang","year":"2024","unstructured":"Zhang, Y., Ye, M., Zhu, G., 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."},{"key":"2314_CR35","unstructured":"Liu, S., Huang, D., Wang, Y.: Learning spatial fusion for single-shot object detection, arXiv preprint arXiv:1911.09516, (2019)"},{"key":"2314_CR36","unstructured":"Newell, A., Huang, Z., Deng, J.: Associative embedding: End-to-end learning for joint detection and grouping. In: Proceedings of the 31st International Conference onNeural Information Processing Systems (NIPS'17),pp. 2274-2284(2017)"},{"key":"2314_CR37","doi-asserted-by":"crossref","unstructured":"Burie, J., Chazalon, J., Coustaty, M., Eskenazi, S., Luqman, M.M.,Mehri, M., Jean-Marc Ogier, N.N., Prum, S., Rusi\u00f1ol, M.: 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":"2314_CR38","doi-asserted-by":"crossref","unstructured":"Dizaj, S.B., Soheili, M.,Mansouri, A.: A new image dataset for document corner localization. In: 2020 International Conference on Machine Vision and Image Processing (MVIP), pp. 1\u20134, IEEE, (2020)","DOI":"10.1109\/MVIP49855.2020.9116896"},{"issue":"15","key":"2314_CR39","doi-asserted-by":"publisher","first-page":"3890","DOI":"10.1049\/iet-ipr.2020.0532","volume":"14","author":"RBD Neves","year":"2020","unstructured":"Neves, R.B.D., Lima, E., Bezerra, B.L., Zanchettin, C., Toselli, A.H.: HU-PageScan: a fully convolutional neural network for document page crop. IET Image Proc. 14(15), 3890\u20133898 (2020)","journal-title":"IET Image Proc."},{"key":"2314_CR40","doi-asserted-by":"crossref","unstructured":"Luo, Z., Wang, Z., Huang, Y., Wang, L., Tan, T., Zhou, F.: 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":"2314_CR41","unstructured":"Lyu, C., Zhang, W., Huang, H., Zhou, Y., Wang, Y., Liu, Y., Zhang, S., Chen, K.: Rtmdet: an empirical study of designing real-time object detectors, arXiv preprint arXiv:2212.07784, (2022)"},{"key":"2314_CR42","doi-asserted-by":"publisher","first-page":"32611","DOI":"10.52202\/079017-1024","volume":"37","author":"H Zhu","year":"2024","unstructured":"Zhu, H., Haoning, W., Li, Y., Zhang, Z., Chen, B., Zhu, L., Fang, Y., Zhai, G., Lin, W., Wang, S.: Adaptive image quality assessment via teaching large multimodal model to compare. Adv. Neural. Inf. Process. Syst. 37, 32611\u201332629 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2314_CR43","doi-asserted-by":"publisher","unstructured":"Wang, Z., Cheng, X., Yao, X., Zhou, Z., Zhang, H., Chang, H.: Vehicle tracking trajectory optimization algorithm based on bidirectional long short-term memory with Savitzky\u2013Golay in a vehicle-road cooperative environment. Journal of Intelligent Transportation Systems(2025). https:\/\/doi.org\/10.1080\/15472450.2025.2479227","DOI":"10.1080\/15472450.2025.2479227"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02314-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-026-02314-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02314-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T10:19:46Z","timestamp":1783765186000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-026-02314-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,6]]},"references-count":43,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["2314"],"URL":"https:\/\/doi.org\/10.1007\/s00530-026-02314-w","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,6]]},"assertion":[{"value":"26 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"261"}}