{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T07:50:23Z","timestamp":1781941823279,"version":"3.54.5"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T00:00:00Z","timestamp":1777248000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T00:00:00Z","timestamp":1777248000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"\u5e7f\u897f\u91cd\u70b9\u7814\u53d1\u8ba1\u5212","award":["No.2023AB01337"],"award-info":[{"award-number":["No.2023AB01337"]}]},{"DOI":"10.13039\/501100018570","name":"Special Project of Central Government for Local Science and Technology Development of Hubei Province","doi-asserted-by":"publisher","award":["No.2024ZY0144"],"award-info":[{"award-number":["No.2024ZY0144"]}],"id":[{"id":"10.13039\/501100018570","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["No.2023YFC3904605"],"award-info":[{"award-number":["No.2023YFC3904605"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["IJDAR"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s10032-026-00592-8","type":"journal-article","created":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T02:08:20Z","timestamp":1777255700000},"page":"225-239","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["EMBFN: an efficient multi-scale bidirectional parallel fusion network for answer sheet text analysis"],"prefix":"10.1007","volume":"29","author":[{"given":"Pengbin","family":"Fu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gaizhi","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongqiang","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huirong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,27]]},"reference":[{"key":"592_CR1","doi-asserted-by":"publisher","first-page":"142642","DOI":"10.1109\/ACCESS.2020.3012542","volume":"8","author":"J Memon","year":"2020","unstructured":"Memon, J., Sami, M., Khan, R.A., Uddin, M.: Handwritten optical character recognition (ocr): A comprehensive systematic literature review (slr). IEEE Access 8, 142642\u2013142668 (2020). https:\/\/doi.org\/10.1109\/ACCESS.2020.3012542","journal-title":"IEEE Access"},{"key":"592_CR2","doi-asserted-by":"publisher","first-page":"91588","DOI":"10.1109\/ACCESS.2022.3202639","volume":"10","author":"FM Schmitt-Koopmann","year":"2022","unstructured":"Schmitt-Koopmann, F.M., Huang, E.M., Hutter, H.-P., Stadelmann, T., Darvishy, A.: Formulanet: A benchmark dataset for mathematical formula detection. IEEE Access 10, 91588\u201391596 (2022). https:\/\/doi.org\/10.1109\/ACCESS.2022.3202639","journal-title":"IEEE Access"},{"key":"592_CR3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3202639","author":"W Zhao","year":"2021","unstructured":"Zhao, W., Gao, L., Yan, Z., Peng, S., Lin, D., Zhang, Z.: Handwritten mathematical expression recognition with bidirectionally trained transformer. IEEE International Conference on Document Analysis and Recognition (2021). https:\/\/doi.org\/10.1109\/ACCESS.2022.3202639","journal-title":"IEEE International Conference on Document Analysis and Recognition"},{"key":"592_CR4","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1007\/978-3-031-19815-1_23","volume":"2022","author":"W Zhao","year":"2022","unstructured":"Zhao, W., Gao, L.: Comer: Modeling coverage for transformer-based handwritten mathematical expression recognition. Computer Vision - ECCV 2022, 392\u2013408 (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_23","journal-title":"Computer Vision - ECCV"},{"key":"592_CR5","doi-asserted-by":"publisher","unstructured":"Yiheng, X., Li, M., Cui, L., Huang, S., Wei, F., Zhou, M.: Layoutlm: Pre-training of text and layout for document image understanding. Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, https:\/\/doi.org\/10.1145\/33944863403172(2020)","DOI":"10.1145\/33944863403172"},{"issue":"9","key":"592_CR6","doi-asserted-by":"publisher","first-page":"6111","DOI":"10.1007\/s00371-023-03156-7","volume":"40","author":"F PengBin","year":"2023","unstructured":"PengBin, F., Zhang, X., Yang, H.R.: Answer sheet layout analysis based on yolov5s-dc and mser. Vis. Comput. 40(9), 6111\u20136122 (2023). https:\/\/doi.org\/10.1007\/s00371-023-03156-7","journal-title":"Vis. Comput."},{"key":"592_CR7","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Proceedings of the 31st International Conference on Neural Information Processing Systems, page 6000\u20136010, (2017)"},{"key":"592_CR8","doi-asserted-by":"publisher","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. Computer Vision \u2013 ECCV,: 16th European Conference, Glasgow, UK, August 23\u201328, 2020. Proceedings, Part I, page 213\u2013229, 2020 (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"592_CR9","doi-asserted-by":"crossref","unstructured":"Zhang, S., Wang, X., Wang, J., Pang, J., Lyu, C., Zhang, W., Luo, P., Chen, K.: Dense distinct query for end-to-end object detection. 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 7329\u20137338, (2023)","DOI":"10.1109\/CVPR52729.2023.00708"},{"issue":"06","key":"592_CR10","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis & Machine Intelligence 39(06), 1137\u20131149 (2017)","journal-title":"IEEE Transactions on Pattern Analysis & Machine Intelligence"},{"key":"592_CR11","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You Only Look Once: Unified, Real-Time Object Detection . 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 779\u2013788, (June 2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"592_CR12","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume":"2016","author":"W Liu","year":"2016","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Cheng-Yang, F., Berg, A.C.: Ssd: Single shot multibox detector. Computer Vision - ECCV 2016, 21\u201337 (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2","journal-title":"Computer Vision - ECCV"},{"key":"592_CR13","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 936\u2013944, (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"592_CR14","unstructured":"Liu, S., Huang, D., Wang, Y.: Learning spatial fusion for single-shot object detection. ArXiv, abs\/1911.09516, (2019). arxiv:1911.09516"},{"key":"592_CR15","doi-asserted-by":"publisher","unstructured":"Xu, Y., Xu, Y., Lv, T., Cui, L., Wei, F., Wang, G., Lu, Y., Florencio, D., Zhang, C., Che, W., Zhang, M., Zhou, L.: LayoutLMv2: Multi-modal pre-training for visually-rich document understanding. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 2579\u20132591, August 2021. https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.201.","DOI":"10.18653\/v1\/2021.acl-long.201."},{"key":"592_CR16","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548112","author":"Y Huang","year":"2022","unstructured":"Huang, Y., Lv, T., Cui, L., Yutong, L., Wei, F.: Layoutlmv3: Pre-training for document ai with unified text and image masking. Proceedings of the 30th ACM International Conference on Multimedia (2022). https:\/\/doi.org\/10.1145\/3503161.3548112","journal-title":"Proceedings of the 30th ACM International Conference on Multimedia"},{"key":"592_CR17","unstructured":"Biswas, S., Banerjee, A., Llad\u2019os, J., Pal, U.: Docsegtr: An instance-level end-to-end document image segmentation transformer. ArXiv, abs\/2201.11438, (2022). arxiv:abs\/2201.11438"},{"key":"592_CR18","doi-asserted-by":"publisher","unstructured":"Phong, B.H., Hoang, T.M., Le, T.-L.: A hybrid method for mathematical expression detection in scientific document images. IEEE Access, 8:83663\u201383684, (2020). https:\/\/doi.org\/10.1109\/ACCESS.2020.2992067","DOI":"10.1109\/ACCESS.2020.2992067"},{"key":"592_CR19","unstructured":"Zhong, Y., Qi, X., Li, S., Gu, D., Chen, Y., Ning, P., Xiao, R.: 1st place solution for icdar 2021 competition on mathematical formula detection. ArXiv, abs\/2107.05534, (2021). https:\/\/arxiv.org\/abs\/2107.05534"},{"key":"592_CR20","unstructured":"Li, X., Wang, W., Wu, L., Chen, S., Hu, X., Li, J., Tang, J., Yang, J.: Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection. Proceedings of the 34th International Conference on Neural Information Processing Systems, (2020). https:\/\/dl.acm.org\/doi\/10.5555\/3495724.3497487"},{"key":"592_CR21","doi-asserted-by":"publisher","unstructured":"Anitei, D., S\u00e1nchez, J.A., Fuentes, J.M., Paredes, R., Bened\u00ed, J.M.: Icdar 2021 competition on mathematical formula detection. Document Analysis and Recognition \u2013 ICDAR 2021, pages 783\u2013795, (2021). https:\/\/doi.org\/10.1007\/978-3-030-86337-1_52","DOI":"10.1007\/978-3-030-86337-1_52"},{"key":"592_CR22","doi-asserted-by":"crossref","unstructured":"Du, Y., Chen, Z., Jia, C., Yin, X., Li, C., Du, Y., Jiang, Y.-G.: Context perception parallel decoder for scene text recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, pages 1\u201316, (2025)","DOI":"10.1109\/TPAMI.2025.3545453"},{"key":"592_CR23","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/j.patrec.2023.05.033","volume":"172","author":"D Anitei","year":"2023","unstructured":"Anitei, D., S\u00e1nchez, J.A., Bened\u00ed, J.M., Noya, E.: The ibem dataset: A large printed scientific image dataset for indexing and searching mathematical expressions. Pattern Recogn. Lett. 172, 29\u201336 (2023). https:\/\/doi.org\/10.1016\/j.patrec.2023.05.033","journal-title":"Pattern Recogn. Lett."},{"key":"592_CR24","unstructured":"Bochkovskiy, A., Wang, C.-Y., Liao, H.-Y.M.: Yolov4: Optimal speed and accuracy of object detection. ArXiv, abs\/2004.10934, (2020). arxiv:2004.10934"},{"key":"592_CR25","doi-asserted-by":"publisher","unstructured":"Latha, R.S., Sreekanth, G.R., Suganthe, R.C., Rajadevi, R., Jagadeeswaran, V.V., Logesh, R., Maheshvar, A.: Text detection and language identification in natural scene images using yolov5. 2023 International Conference on Computer Communication and Informatics (ICCCI), pages 1\u20137, (2023). https:\/\/doi.org\/10.1109\/ICCCI56745.2023.10128400.","DOI":"10.1109\/ICCCI56745.2023.10128400."},{"key":"592_CR26","unstructured":"Zheng Ge, Songtao Liu, Feng Wang, Zeming Li, and Jian Sun. YOLOX: Exceeding YOLO Series in 2021. arXiv e-prints, page arXiv:2107.08430, July 2021"},{"key":"592_CR27","unstructured":"Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., Ren, D.: Distance-iou loss: Faster and better learning for bounding box regression. ArXiv, abs\/1911.08287, (2019) arxiv:abs\/1911.08287"},{"key":"592_CR28","unstructured":"Loshchilov, I., Hutter, F.: Sgdr: Stochastic gradient descent with warm restarts. arXiv Learning, (2016). arxiv:1608.03983"},{"key":"592_CR29","unstructured":"Peng, Y., Li, H., Wu, P., Zhang, Y., Sun, X., Wu, F.: D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement. arXiv e-prints, page arXiv:2410.13842, (October 2024)"},{"key":"592_CR30","unstructured":"Huang, S., Hou, Y., Liu, L., Yu, X., Shen, X.: Real-Time Object Detection Meets DINOv3. arXiv e-prints, page arXiv:2509.20787, (September 2025)"},{"key":"592_CR31","unstructured":"Robinson, I., Robicheaux, P., Popov, M., Ramanan, D., Peri, N.: RF-DETR: Neural Architecture Search for Real-Time Detection Transformers. arXiv e-prints, page arXiv:2511.09554, (November 2025)"},{"issue":"5","key":"592_CR32","doi-asserted-by":"publisher","first-page":"1483","DOI":"10.1109\/TPAMI.2019.2956516","volume":"43","author":"Z Cai","year":"2021","unstructured":"Cai, Z., Vasconcelos, N.: Cascade r-cnn: High quality object detection and instance segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 43(5), 1483\u20131498 (2021). https:\/\/doi.org\/10.1109\/TPAMI.2019.2956516","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"592_CR33","doi-asserted-by":"crossref","unstructured":"Lu, X., Li, B., Yue, Y., Li, Q., Yan, J.: Grid r-cnn. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 7355\u20137364, (2019)","DOI":"10.1109\/CVPR.2019.00754"},{"key":"592_CR34","doi-asserted-by":"crossref","unstructured":"Pang, J., Chen, K., Shi, J., Feng, H., Ouyang, W., Lin, D.: Libra R-CNN: Towards Balanced Learning for Object Detection . 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 821\u2013830, (June 2019)","DOI":"10.1109\/CVPR.2019.00091"},{"issue":"6","key":"592_CR35","doi-asserted-by":"publisher","first-page":"3096","DOI":"10.1109\/TPAMI.2021.3050494","volume":"44","author":"X Zhang","year":"2022","unstructured":"Zhang, X., Wan, F., Liu, C., Ji, X., Ye, Q.: Learning to match anchors for visual object detection. IEEE Trans. Pattern Anal. Mach. Intell. 44(6), 3096\u20133109 (2022). https:\/\/doi.org\/10.1109\/TPAMI.2021.3050494","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"592_CR36","doi-asserted-by":"crossref","unstructured":"Wu, Y., Chen, Y., Yuan, L., Liu, Z., Wang, L., Li, H., Fu, Y.: Rethinking classification and localization for object detection. 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 10183\u201310192, (2020)","DOI":"10.1109\/CVPR42600.2020.01020"},{"key":"592_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, S., Chi, C., Yao, Y., Lei, Z., Li, S.Z.: Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 9756\u20139765, (2020)","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"592_CR38","doi-asserted-by":"publisher","unstructured":"Wang, J., Zhang, W., Cao, Y., Chen, K., Pang, J., Gong, T., Shi, J., Loy, C.C., Lin, D.: Side-aware boundary localization for more precise object detection. Computer Vision \u2013 ECCV 2020, pages 403\u2013419, (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_24","DOI":"10.1007\/978-3-030-58548-8_24"},{"key":"592_CR39","doi-asserted-by":"publisher","unstructured":"Zhang, H., Chang, H., Ma, B., Wang, N., Chen, X.: Dynamic r-cnn: Towards high quality object detection via dynamic training. Computer Vision \u2013 ECCV: 16th European Conference, Glasgow, UK, August 23\u201328, 2020. Proceedings, Part XV, page 260\u2013275, 2020 (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_16","DOI":"10.1007\/978-3-030-58555-6_16"},{"key":"592_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, H., Wang, Y., Dayoub, F., Sunderhauf, N.: VarifocalNet: An IoU-aware Dense Object Detector . 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 8510\u20138519, June (2021)","DOI":"10.1109\/CVPR46437.2021.00841"},{"key":"592_CR41","doi-asserted-by":"crossref","unstructured":"Sun, P., Zhang, R., Jiang, Y., Kong, T., Xu, C., Zhan, W., Tomizuka, M., Li, L., Yuan, Z., Wang, C., Luo, P.: Sparse r-cnn: End-to-end object detection with learnable proposals. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 14449\u201314458, (2021)","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"592_CR42","doi-asserted-by":"crossref","unstructured":"Feng, C., Zhong, Y., Gao, Y., Scott, M.R., Huang, W.: TOOD: Task-aligned One-stage Object Detection . 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pages 3490\u20133499, (October 2021)","DOI":"10.1109\/ICCV48922.2021.00349"},{"key":"592_CR43","doi-asserted-by":"publisher","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, abs\/2212.07784, (2022). https:\/\/doi.org\/10.48550\/arXiv.2212.07784","DOI":"10.48550\/arXiv.2212.07784"},{"key":"592_CR44","unstructured":"Jocher, G., Chaurasia, A., Qiu, J.: Ultralytics yolov8. Version 8.0.0. AGPL-3.0. GitHub repository, (2023). ORCID: 0000-0001-5950-6979, 0000-0002-7603-6750, 0000-0003-3783-7069"},{"key":"592_CR45","unstructured":"Jocher, G., Qiu, J.: Ultralytics yolo11. Version 11.0.0. AGPL-3.0. GitHub repository, (2024). ORCID: 0000-0001-5950-6979 (Glenn Jocher), 0000-0002-7603-6750 (Jing Qiu)"},{"key":"592_CR46","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Lv, W., Xu, S., Wei, J., Wang, G., Dang, Q., Liu, Y., Chen, J.: Detrs beat yolos on real-time object detection. 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 16965\u201316974, (2024)","DOI":"10.1109\/CVPR52733.2024.01605"}],"container-title":["International Journal on Document Analysis and Recognition (IJDAR)"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-026-00592-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10032-026-00592-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-026-00592-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T07:07:02Z","timestamp":1781939222000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10032-026-00592-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,27]]},"references-count":46,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["592"],"URL":"https:\/\/doi.org\/10.1007\/s10032-026-00592-8","relation":{},"ISSN":["1433-2833","1433-2825"],"issn-type":[{"value":"1433-2833","type":"print"},{"value":"1433-2825","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,27]]},"assertion":[{"value":"10 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 February 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 April 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 April 2026","order":4,"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 that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}]}}