{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T05:57:57Z","timestamp":1743055077097,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031781186"},{"type":"electronic","value":"9783031781193"}],"license":[{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-78119-3_1","type":"book-chapter","created":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T02:00:35Z","timestamp":1733277635000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ODTr: Transformer Integrating OCR Auxiliary Map and\u00a0Image Depth Information for\u00a0Document Image Unwarping"],"prefix":"10.1007","author":[{"given":"Xiangyu","family":"Xie","sequence":"first","affiliation":[]},{"given":"Yuxuan","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Liangcai","family":"Gao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,5]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Bandyopadhyay, H., Dasgupta, T., Das, N., Nasipuri, M.: A gated and bifurcated stacked u-net module for document image dewarping. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 10548\u201310554. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9413001"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Das, S., Ma, K., Shu, Z., Samaras, D., Shilkrot, R.: Dewarpnet: single-image document unwarping with stacked 3D and 2D regression networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 131\u2013140 (2019)","DOI":"10.1109\/ICCV.2019.00022"},{"key":"1_CR4","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"1_CR5","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Feng, H., Wang, Y., Zhou, W., Deng, J., Li, H.: Doctr: document image transformer for geometric unwarping and illumination correction. arXiv preprint arXiv:2110.12942 (2021)","DOI":"10.1145\/3474085.3475388"},{"key":"1_CR7","unstructured":"Fu, B., Wu, M., Li, R., Li, W., Xu, Z., Yang, C.: A model-based book dewarping method using text line detection. In: Proceedings of the 2nd International Workshop on Camera Based Document Analysis and Recognition, Curitiba, Brazil, pp. 63\u201370 (2007)"},{"key":"1_CR8","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"1_CR9","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"issue":"11","key":"1_CR10","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"1_CR11","unstructured":"Levenshtein, V.I., et\u00a0al.: Binary codes capable of correcting deletions, insertions, and reversals. In: Soviet physics Doklady. vol.\u00a010, pp. 707\u2013710. Soviet Union (1966)"},{"issue":"6","key":"1_CR12","first-page":"1","volume":"38","author":"X Li","year":"2019","unstructured":"Li, X., Zhang, B., Liao, J., Sander, P.V.: Document rectification and illumination correction using a patch-based CNN. ACM Trans. Graphics (TOG) 38(6), 1\u201311 (2019)","journal-title":"ACM Trans. Graphics (TOG)"},{"key":"1_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107576","volume":"108","author":"X Liu","year":"2020","unstructured":"Liu, X., Meng, G., Fan, B., Xiang, S., Pan, C.: Geometric rectification of document images using adversarial gated unwarping network. Pattern Recogn. 108, 107576 (2020)","journal-title":"Pattern Recogn."},{"key":"1_CR14","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Ma, K., Shu, Z., Bai, X., Wang, J., Samaras, D.: DocuNet: document image unwarping via a stacked U-Net. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700\u20134709 (2018)","DOI":"10.1109\/CVPR.2018.00494"},{"key":"1_CR16","doi-asserted-by":"crossref","unstructured":"Meng, G., Wang, Y., Qu, S., Xiang, S., Pan, C.: Active flattening of curved document images via two structured beams. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3890\u20133897 (2014)","DOI":"10.1109\/CVPR.2014.497"},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Pham, N.Q., Nguyen, T.S., Niehues, J., M\u00fcller, M., St\u00fcker, S., Waibel, A.: Very deep self-attention networks for end-to-end speech recognition. arXiv preprint arXiv:1904.13377 (2019)","DOI":"10.21437\/Interspeech.2019-2702"},{"key":"1_CR18","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I., et\u00a0al.: Improving language understanding by generative pre-training (2018)"},{"issue":"140","key":"1_CR19","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., Liu, P.J.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Ramanna, V.K.B., Bukhari, S.S., Dengel, A.: Document image dewarping using deep learning. In: ICPRAM, pp. 524\u2013531 (2019)","DOI":"10.5220\/0007368405240531"},{"key":"1_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Smith, L.N., Topin, N.: Super-convergence: Very fast training of neural networks using large learning rates. In: Artificial Intelligence and Machine Learning for Multi-domain Operations Applications, vol. 11006, pp. 369\u2013386. SPIE (2019)","DOI":"10.1117\/12.2520589"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Sun, F., et al.: Bert4rec: sequential recommendation with bidirectional encoder representations from transformer. In: Proceedings of the 28th ACM International Conference on Information and Knowledge Management, pp. 1441\u20131450 (2019)","DOI":"10.1145\/3357384.3357895"},{"key":"1_CR24","doi-asserted-by":"publisher","unstructured":"Tsoi, Y.C., Brown, M.S.: Multi-view document rectification using boundary. In: 2007 IEEE Conference on Computer Vision and Pattern Recognition, pp.\u00a01\u20138 (2007). https:\/\/doi.org\/10.1109\/CVPR.2007.383251","DOI":"10.1109\/CVPR.2007.383251"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Ulges, A., Lampert, C.H., Breuel, T.: Document capture using stereo vision. In: Proceedings of the 2004 ACM symposium on Document engineering, pp. 198\u2013200 (2004)","DOI":"10.1145\/1030397.1030434"},{"key":"1_CR26","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"1_CR27","unstructured":"Wang, Z., Simoncelli, E.P., Bovik, A.C.: Multiscale structural similarity for image quality assessment. In: The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003. vol.\u00a02, pp. 1398\u20131402. IEEE (2003)"},{"key":"1_CR28","doi-asserted-by":"publisher","unstructured":"Yamashita, A., Kawarago, A., Kaneko, T., Miura, K.: Shape reconstruction and image restoration for non-flat surfaces of documents with a stereo vision system. In: Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. vol.\u00a01, pp. 482\u2013485 (2004). doi: https:\/\/doi.org\/10.1109\/ICPR.2004.1334171","DOI":"10.1109\/ICPR.2004.1334171"},{"issue":"2","key":"1_CR29","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1109\/TPAMI.2017.2675980","volume":"40","author":"S You","year":"2017","unstructured":"You, S., Matsushita, Y., Sinha, S., Bou, Y., Ikeuchi, K.: Multiview rectification of folded documents. IEEE Trans. Pattern Anal. Mach. Intell. 40(2), 505\u2013511 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78119-3_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T02:02:26Z","timestamp":1733277746000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78119-3_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,5]]},"ISBN":["9783031781186","9783031781193"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78119-3_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,5]]},"assertion":[{"value":"5 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}