{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T04:38:13Z","timestamp":1758083893861,"version":"3.44.0"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032046260"},{"type":"electronic","value":"9783032046277"}],"license":[{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"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\/978-3-032-04627-7_18","type":"book-chapter","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T02:07:48Z","timestamp":1757988468000},"page":"311-328","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DocAI-TL: Structured Document Tampering Localization with\u00a0DocAI Model"],"prefix":"10.1007","author":[{"given":"Youjie","family":"Li","sequence":"first","affiliation":[]},{"given":"Shiqiang","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Guijia","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Qifeng","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Changsheng","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,16]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Ahmed, A.G.H., Shafait, F.: Forgery detection based on intrinsic document contents. In: IPAR DAS, pp. 252\u2013256. IEEE (2014)","DOI":"10.1109\/DAS.2014.26"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Appalaraju, S., Tang, P., Dong, Q., Sankaran, N., Zhou, Y., Manmatha, R.: DocFormerv2: local features for document understanding. In: AAAI, vol.\u00a038, pp. 709\u2013718 (2024)","DOI":"10.1609\/aaai.v38i2.27828"},{"key":"18_CR3","unstructured":"Artaud, C.: D\u00e9tection des fraudes: de l\u2019image \u00e1 la s\u00e9mantique du contenu: application \u00e1 la v\u00e9rification des informations extraites d\u2019un corpus de tickets de caisse. Ph.D. thesis, Universit\u00e9 de La Rochelle (2019)"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"van Beusekom, J., Shafait, F.: Distortion measurement for automatic document verification. In: ICDAR, pp. 289\u2013293. IEEE (2011)","DOI":"10.1109\/ICDAR.2011.66"},{"key":"18_CR5","doi-asserted-by":"publisher","unstructured":"Chen, Z., et al.: Enhancing tampered text detection through frequency feature fusion and decomposition. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) ECCV 2024. LNCS, vol. 15091, pp. 200\u2013217. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-73414-4_12","DOI":"10.1007\/978-3-031-73414-4_12"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Cruz, F., Sidere, N., Coustaty, M., d\u2019Andecy, V.P., Ogier, J.M.: Local binary patterns for document forgery detection. In: ICDAR, vol.\u00a01, pp. 1223\u20131228. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.202"},{"issue":"3","key":"18_CR7","doi-asserted-by":"publisher","first-page":"3539","DOI":"10.1109\/TPAMI.2022.3180556","volume":"45","author":"C Dong","year":"2022","unstructured":"Dong, C., Chen, X., Hu, R., Cao, J., Li, X.: MVSS-Net: multi-view multi-scale supervised networks for image manipulation detection. IEEE TPAMI 45(3), 3539\u20133553 (2022)","journal-title":"IEEE TPAMI"},{"issue":"1","key":"18_CR8","first-page":"3495","volume":"70","author":"L Dong","year":"2024","unstructured":"Dong, L., Liang, W., Wang, R.: Robust text image tampering localization via forgery traces enhancement and multiscale attention. IEEE TCE 70(1), 3495\u20133507 (2024)","journal-title":"IEEE TCE"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Eskenazi, S., Gomez-Kr\u00e4mer, P., Ogier, J.M.: The delaunay document layout descriptor. In: DocEng, pp. 167\u2013175 (2015)","DOI":"10.1145\/2682571.2797059"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Huang, Y., Lv, T., Cui, L., Lu, Y., Wei, F.: LayoutLMv3: pre-training for document ai with unified text and image masking. In: ACM MM, pp. 4083\u20134091 (2022)","DOI":"10.1145\/3503161.3548112"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Huang, Z., Chen, K., He, J., Bai, X., Karatzas, D., Lu, S., Jawahar, C.: ICDAR2019 competition on scanned receipt OCR and information extraction. In: ICDAR, pp. 1516\u20131520. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00244"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Jaume, G., Ekenel, H.K., Thiran, J.P.: FUNSD: a dataset for form understanding in noisy scanned documents. In: ICDARW, vol.\u00a02, pp.\u00a01\u20136. IEEE (2019)","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"18_CR13","unstructured":"Kenton, J.D.M.W.C., Toutanova, L.K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT, vol.\u00a01, p.\u00a02. Minneapolis, Minnesota (2019)"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. In: ICCV, pp. 4015\u20134026 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"18_CR15","unstructured":"Li, C., et\u00a0al.: PP-OCRv3: more attempts for the improvement of ultra lightweight OCR system. arXiv preprint arXiv:2206.03001 (2022)"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Liang, W., Dong, L., Wang, R., Yan, D., Li, Y.: Robust document image forgery localization against image blending. In: IEEE TrustCom, pp. 810\u2013817. IEEE (2022)","DOI":"10.1109\/TrustCom56396.2022.00113"},{"key":"18_CR17","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: NeurIPS, vol. 36, pp. 34892\u201334916 (2023)"},{"key":"18_CR18","unstructured":"Liu, Y., et al.: TextMonkey: an OCR-free large multimodal model for understanding document. arXiv preprint arXiv:2403.04473 (2024)"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Z., et\u00a0al.: Swin transformer v2: scaling up capacity and resolution. In: CVPR, pp. 12009\u201312019 (2022)","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Luo, C., Cheng, C., Zheng, Q., Yao, C.: GeoLayoutLM: geometric pre-training for visual information extraction. In: CVPR, pp. 7092\u20137101 (2023)","DOI":"10.1109\/CVPR52729.2023.00685"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Luo, D., et al.: Toward real text manipulation detection: new dataset and new solution. Pattern Recogn. 157, 110828 (2025)","DOI":"10.1016\/j.patcog.2024.110828"},{"key":"18_CR22","unstructured":"Mindee: docTR: Document text recognition (2021). https:\/\/github.com\/mindee\/doctr"},{"key":"18_CR23","unstructured":"Park, S., Shin, S., Lee, B., Lee, J., Surh, J., Seo, M., Lee, H.: CORD: a consolidated receipt dataset for post-OCR parsing. In: Workshop on Document Intelligence at NeurIPS 2019 (2019)"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Qu, C., et al.: Towards robust tampered text detection in document image: new dataset and new solution. In: CVPR, pp. 5937\u20135946 (2023)","DOI":"10.1109\/CVPR52729.2023.00575"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Qu, C., Zhong, Y., Guo, F., Jin, L.: Omni-IML: towards unified image manipulation localization. arXiv preprint arXiv:2411.14823 (2024)","DOI":"10.32388\/MNREU8"},{"issue":"2","key":"18_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3686158","volume":"21","author":"Y Song","year":"2025","unstructured":"Song, Y., Jiang, W., Chai, X., Gan, Z., Zhou, M., Chen, L.: Cross-attention based two-branch networks for document image forgery localization in the metaverse. ACM TOMM 21(2), 1\u201324 (2025)","journal-title":"ACM TOMM"},{"key":"18_CR27","first-page":"1232","volume":"29","author":"Y Sun","year":"2022","unstructured":"Sun, Y., Ni, R., Zhao, Y.: ET: edge-enhanced transformer for image splicing detection. IEEE SPL 29, 1232\u20131236 (2022)","journal-title":"IEEE SPL"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Tang, Z., et al.: Unifying vision, text, and layout for universal document processing. In: CVPR, pp. 19254\u201319264 (2023)","DOI":"10.1109\/CVPR52729.2023.01845"},{"key":"18_CR29","doi-asserted-by":"publisher","unstructured":"Torn\u00e9s, B.M., Boros, E., Doucet, A., Gomez-Kr\u00e4mer, P., Ogier, J.M.: Detecting forged receipts with domain-specific ontology-based entities & relations. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds) ICDAR 2023. LNCS, vol. 14189, pp. 184\u2013199. Springer (2023). https:\/\/doi.org\/10.1007\/978-3-031-41682-8_12","DOI":"10.1007\/978-3-031-41682-8_12"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Wang, J., Jin, L., Ding, K.: LiLT: a simple yet effective language-independent layout transformer for structured document understanding. arXiv preprint arXiv:2202.13669 (2022)","DOI":"10.18653\/v1\/2022.acl-long.534"},{"key":"18_CR31","doi-asserted-by":"publisher","unstructured":"Wang, Y., Xie, H., Xing, M., Wang, J., Zhu, S., Zhang, Y.: Detecting tampered scene text in the wild. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13688, pp. 215\u2013232. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_13","DOI":"10.1007\/978-3-031-19815-1_13"},{"issue":"3","key":"18_CR32","first-page":"29","volume":"8","author":"Y Wang","year":"2022","unstructured":"Wang, Y., Zhang, B., Xie, H., Zhang, Y.: Tampered text detection via RGB and frequency relationship modeling. Chin. J. Netw. Inf. Secur. 8(3), 29\u201340 (2022)","journal-title":"Chin. J. Netw. Inf. Secur."},{"key":"18_CR33","unstructured":"Wu, J., et al.: Medical SAM adapter: adapting segment anything model for medical image segmentation. arXiv preprint arXiv:2304.12620 (2023)"},{"key":"18_CR34","doi-asserted-by":"crossref","unstructured":"Wu, L., et al.: Editing text in the wild. In: ACM MM, pp. 1500\u20131508 (2019)","DOI":"10.1145\/3343031.3350929"},{"key":"18_CR35","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: SegFormer: simple and efficient design for semantic segmentation with transformers. In: NeurIPS, vol. 34, pp. 12077\u201312090 (2021)"},{"issue":"8","key":"18_CR36","first-page":"5272","volume":"37","author":"W Xu","year":"2022","unstructured":"Xu, W., et al.: Document images forgery localization using a two-stream network. IJIS 37(8), 5272\u20135289 (2022)","journal-title":"IJIS"},{"key":"18_CR37","doi-asserted-by":"crossref","unstructured":"Xu, Y., et\u00a0al.: LayoutLMv2: multi-modal pre-training for visually-rich document understanding. arXiv preprint arXiv:2012.14740 (2020)","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"18_CR38","doi-asserted-by":"crossref","unstructured":"Xu, Y., Li, M., Cui, L., Huang, S., Wei, F., Zhou, M.: LayoutLM: pre-training of text and layout for document image understanding. In: SIGKDD, pp. 1192\u20131200 (2020)","DOI":"10.1145\/3394486.3403172"},{"key":"18_CR39","first-page":"7964","volume":"30","author":"L Zhao","year":"2021","unstructured":"Zhao, L., Chen, C., Huang, J.: Deep learning-based forgery attack on document images. IEEE TIP 30, 7964\u20137979 (2021)","journal-title":"IEEE TIP"},{"key":"18_CR40","first-page":"2986","volume":"16","author":"P Zhuang","year":"2021","unstructured":"Zhuang, P., Li, H., Tan, S., Li, B., Huang, J.: Image tampering localization using a dense fully convolutional network. IEEE TIFS 16, 2986\u20132999 (2021)","journal-title":"IEEE TIFS"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04627-7_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T02:08:02Z","timestamp":1757988482000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04627-7_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,16]]},"ISBN":["9783032046260","9783032046277"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04627-7_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,9,16]]},"assertion":[{"value":"16 September 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"}}]}}