{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T18:26:54Z","timestamp":1763922414238,"version":"3.45.0"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032093677","type":"print"},{"value":"9783032093684","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T00:00:00Z","timestamp":1763942400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T00:00:00Z","timestamp":1763942400000},"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\/978-3-032-09368-4_14","type":"book-chapter","created":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T18:14:39Z","timestamp":1763921679000},"page":"226-244","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep Learning for\u00a0Defect Detection in\u00a0Answer Document Image"],"prefix":"10.1007","author":[{"given":"Jun","family":"Xie","sequence":"first","affiliation":[]},{"given":"Yiming","family":"Xia","sequence":"additional","affiliation":[]},{"given":"Sailong","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Ruiqing","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Yirong","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,24]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Wu, K., Fu, H., Li, W.: Handwriting text-line detection and recognition in answer sheet composition with few labeled data. In: 2020 IEEE 11th International Conference on Software Engineering and Service Science. IEEE ICSESS, pp. 129\u2013132 (2020)","DOI":"10.1109\/ICSESS49938.2020.9237637"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Shaikh, E., Mohiuddin, I., Manzoor, A., Automated grading for handwritten answer sheets using convolutional neural networks. In: 2nd International Conference On New Trends In Computing Sciences. IEEE, pp. 1\u20136 (2019)","DOI":"10.1109\/ICTCS.2019.8923092"},{"key":"14_CR3","first-page":"1140","volume":"35","author":"MH Guo","year":"2022","unstructured":"Guo, M.H., Lu, C.Z., Hou, Q., et al.: Segnext: rethinking convolutional attention design for semantic segmentation. Adv. Neural. Inf. Process. Syst. 35, 1140\u20131156 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Zhu, X., Wang, X., et al.: R2 CNN: rotational region CNN for arbitrarily-oriented scene text detection. In: 24th International Conference on Pattern Recognition, Beijing, pp. 3610\u20133615 (2018)","DOI":"10.1109\/ICPR.2018.8545598"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Xie, X., Cheng, G., Wang, J., et al.: Oriented R-CNN for object detection. In: Proceedings of the IEEE\/CVF International Conference On Computer Vision, pp. 3520\u20133529 (2021)","DOI":"10.1109\/ICCV48922.2021.00350"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Yang, S., Pei, Z., Zhou, F., et al.: Rotated faster R-CNN for oriented object detection in aerial images. In: Proceedings of the 2020 3rd International Conference on Robot Systems and Applications, pp. 35\u201339 (2020)","DOI":"10.1145\/3402597.3402605"},{"issue":"17","key":"14_CR7","doi-asserted-by":"publisher","first-page":"5850","DOI":"10.3390\/s24175850","volume":"24","author":"S Feng","year":"2024","unstructured":"Feng, S., Huang, Y., Zhang, N.: An improved YOLOv8 OBB model for ship detection through stable diffusion data augmentation. Sensors 24(17), 5850 (2024)","journal-title":"Sensors"},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Pu, Y., Wang, Y., Xia, Z., et al.: Adaptive rotated convolution for rotated object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6589\u20136600 (2023)","DOI":"10.1109\/ICCV51070.2023.00606"},{"key":"14_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2024.3510781","volume":"62","author":"Y Zhang","year":"2024","unstructured":"Zhang, Y., Ye, M., Zhu, G., et al.: 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":"14_CR10","doi-asserted-by":"crossref","unstructured":"Li, L., Bai, Y., Zhang, S., et al.: Document forgery detection based on spatial-frequency and multi-scale feature network. J. Visual Commun. Image Representation, 104393 (2025)","DOI":"10.1016\/j.jvcir.2025.104393"},{"key":"14_CR11","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst., 30 (2017)"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., et al.: End-to-end object detection with transformers. In: European Conference on Computer Vision. Cham: Springer International Publishing, pp. 213\u2013229 (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference On Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Lv, W., Xu, S., et al.: Detrs beat yolos on real-time object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16965\u201316974 (2024)","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"14_CR15","unstructured":"Chen, Q., Su, X., Zhang, X., et al.: Lw-detr: a transformer replacement to yolo for real-time detection. arXiv preprint arXiv:2406.03459 (2024)"},{"key":"14_CR16","doi-asserted-by":"publisher","first-page":"1283","DOI":"10.1109\/TIFS.2023.3333548","volume":"19","author":"C Chen","year":"2023","unstructured":"Chen, C., Li, B., Cai, R., et al.: Distortion model-based spectral augmentation for generalized recaptured document detection. IEEE Trans. Inf. Forensics Secur. 19, 1283\u20131298 (2023)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Hu, X., Wei, B., Gao, L., et al.: SegHist: a general segmentation-based framework for chinese historical document text line detection. In: International Conference on Document Analysis and Recognition. Cham: Springer Nature Switzerland, pp. 391\u2013410 (2024)","DOI":"10.1007\/978-3-031-70543-4_23"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Kundu, A., Bhattacharya, U.: YOLO Assisted A* algorithm for robust line segmentation of degraded document images. In: International Conference on Document Analysis and Recognition. Cham: Springer Nature Switzerland, pp. 407\u2013424 (2024)","DOI":"10.1007\/978-3-031-70546-5_24"},{"key":"14_CR19","unstructured":"Li, M., Sun, H., Lei, Y., et al.: High-fidelity document stain removal via a large-scale real-world dataset and a memory-augmented transformer. arxiv preprint arxiv:2410.22922 (2024)"},{"issue":"2","key":"14_CR20","doi-asserted-by":"publisher","first-page":"266","DOI":"10.3390\/math13020266","volume":"13","author":"MSE Kasem","year":"2025","unstructured":"Kasem, M.S.E., Mahmoud, M., Yagoub, B., et al.: HTTD: a hierarchical transformer for accurate table detection in document images. Mathematics 13(2), 266 (2025)","journal-title":"Mathematics"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Murrugarra Llerena, L.N., Kirsten, L.F., Zeni, et al.: Probabilistic intersection-over-union for training and evaluation of oriented object detectors. IEEE Trans. Image Process. 33, 671\u2013681 (2024)","DOI":"10.1109\/TIP.2023.3348697"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Huang, D., Zhang, X., Zhang, R., et al.: DWM: a decomposable Winograd method for convolution acceleration. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 04, pp. 4174\u20134181 (2020)","DOI":"10.1609\/aaai.v34i04.5838"},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Sunkara, R., Luo, T.: No more strided convolutions or pooling: a new CNN building block for low-resolution images and small objects. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Cham: Springer Nature Switzerland, pp. 443\u2013459 (2022)","DOI":"10.1007\/978-3-031-26409-2_27"},{"issue":"21","key":"14_CR24","doi-asserted-by":"publisher","first-page":"6781","DOI":"10.3390\/s24216781","volume":"24","author":"R Zhang","year":"2024","unstructured":"Zhang, R., Deng, B., Cheng, X., et al.: GCS-YOLOv8: a lightweight face extractor to assist deepfake detection. Sensors 24(21), 6781 (2024)","journal-title":"Sensors"},{"key":"14_CR25","unstructured":"Victor, D.: A dataset for handwritten signature objectdetection in scanned documents. victordibia.com (2022). https:\/\/victordibia.com\/signverod.pdf"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Yang, X., Yan, J., Feng, Z., et al.: R3det: refined single-stage detector with feature refinement for rotating object. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 4, pp. 3163\u20133171 (2021)","DOI":"10.1609\/aaai.v35i4.16426"},{"key":"14_CR27","first-page":"1","volume":"60","author":"J Han","year":"2021","unstructured":"Han, J., Ding, J., Li, J., et al.: Align deep features for oriented object detection. IEEE Trans. Geosci. Remote Sens. 60, 1\u201311 (2021)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"14_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1007\/978-3-030-58555-6_16","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Zhang","year":"2020","unstructured":"Zhang, H., Chang, H., Ma, B., Wang, N., Chen, X.: Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 260\u2013275. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_16"},{"key":"14_CR29","unstructured":"Zhang, H., Li, F., Liu, S., et al.: Dino: detr with improved denoising anchor boxes for end-to-end object detection. arxiv preprint arxiv:2203.03605 (2022)"},{"key":"14_CR30","unstructured":"Lyu, C., Zhang, W., Huang, H., et al.: Rtmdet: an empirical study of designing real-time object detectors. arxiv preprint arxiv:2212.07784 (2022)"},{"key":"14_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, S., Wang, X., Wang, J., et al.: Dense distinct query for end-to-end object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7329\u20137338 (2023)","DOI":"10.1109\/CVPR52729.2023.00708"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2025 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-09368-4_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T18:14:44Z","timestamp":1763921684000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-09368-4_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,24]]},"ISBN":["9783032093677","9783032093684"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-09368-4_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,24]]},"assertion":[{"value":"24 November 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"}}]}}