{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:40:17Z","timestamp":1765309217225,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23B2022, U22B2047 and 62371301"],"award-info":[{"award-number":["U23B2022, U22B2047 and 62371301"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754857","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:56:44Z","timestamp":1761375404000},"page":"82-91","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["DITL\n                    <sup>2<\/sup>\n                    : Dual-Stage Invariance Transfer Learning for Generalizable Document Image Tampering Localization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1568-4697","authenticated-orcid":false,"given":"Songze","family":"Li","sequence":"first","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen, China, Shenzhen Key Laboratory of Media Security, Shenzhen, China, and Shenzhen University, Shenzhen, Chile"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2422-3332","authenticated-orcid":false,"given":"Yunfei","family":"Guo","sequence":"additional","affiliation":[{"name":"Tencent YouTu Lab, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9140-194X","authenticated-orcid":false,"given":"Shen","family":"Chen","sequence":"additional","affiliation":[{"name":"Tencent YouTu Lab, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2613-5451","authenticated-orcid":false,"given":"Bin","family":"Li","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen, China, Shenzhen Key Laboratory of Media Security, Shenzhen, China, and Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5291-4635","authenticated-orcid":false,"given":"Kaiqing","family":"Lin","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen, China, Shenzhen Key Laboratory of Media Security, Shenzhen, China, and Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4857-6810","authenticated-orcid":false,"given":"Changsheng","family":"Chen","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen, China, Shenzhen Key Laboratory of Media Security, Shenzhen, China, and Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0532-9481","authenticated-orcid":false,"given":"Haodong","family":"Li","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen, China, Shenzhen Key Laboratory of Media Security, Shenzhen, China, and Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2359-1523","authenticated-orcid":false,"given":"Taiping","family":"Yao","sequence":"additional","affiliation":[{"name":"Tencent YouTu Lab, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3175-3553","authenticated-orcid":false,"given":"Shouhong","family":"Ding","sequence":"additional","affiliation":[{"name":"Tencent YouTu Lab, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"First International Workshop on Computational Document Forensics.","author":"Artaud Chlo\u00e9","year":"2017","unstructured":"Chlo\u00e9 Artaud, Antoine Doucet, Jean-Marc Ogier, and Vincent Poulain d'Andecy. 2017. Receipt dataset for fraud detection. In First International Workshop on Computational Document Forensics."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.3390\/sym17030395"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2983"},{"key":"e_1_3_2_1_4_1","volume-title":"International conference on machine learning. PmLR, 1597-1607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PmLR, 1597-1607."},{"key":"e_1_3_2_1_5_1","volume-title":"Enhancing Tampered Text Detection Through Frequency Feature Fusion and Decomposition. In European Conference on Computer Vision. Springer, 200-217","author":"Chen Zhongxi","year":"2024","unstructured":"Zhongxi Chen, Shen Chen, Taiping Yao, Ke Sun, Shouhong Ding, Xianming Lin, Liujuan Cao, and Rongrong Ji. 2024. Enhancing Tampered Text Detection Through Frequency Feature Fusion and Decomposition. In European Conference on Computer Vision. Springer, 200-217."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Bowen Cheng Ishan Misra Alexander G. Schwing Alexander Kirillov and Rohit Girdhar. 2022. Masked-attention Mask Transformer for Universal Image Segmentation. CVPR.","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2024.3367947"},{"key":"e_1_3_2_1_9_1","volume-title":"Texture synthesis using convolutional neural networks. Advances in neural information processing systems","author":"Gatys Leon","year":"2015","unstructured":"Leon Gatys, Alexander S Ecker, and Matthias Bethge. 2015. Texture synthesis using convolutional neural networks. Advances in neural information processing systems, Vol. 28 (2015)."},{"key":"e_1_3_2_1_10_1","volume-title":"Scaling laws for transfer. arXiv preprint arXiv:2102.01293","author":"Hernandez Danny","year":"2021","unstructured":"Danny Hernandez, Jared Kaplan, Tom Henighan, and Sam McCandlish. 2021. Scaling laws for transfer. arXiv preprint arXiv:2102.01293 (2021)."},{"key":"e_1_3_2_1_11_1","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al., 2022. Lora: Low-rank adaptation of large language models. ICLR, Vol. 1, 2 (2022), 3.","journal-title":"ICLR"},{"key":"e_1_3_2_1_12_1","volume-title":"Scaling laws for neural language models. arXiv preprint arXiv:2001.08361","author":"Kaplan Jared","year":"2020","unstructured":"Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. 2020. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 (2020)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00069"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2016.2636089"},{"key":"e_1_3_2_1_16_1","volume-title":"SAFIRE: Segment Any Forged Image Region. arXiv preprint arXiv:2412.08197","author":"Kwon Myung-Joon","year":"2024","unstructured":"Myung-Joon Kwon, Wonjun Lee, Seung-Hun Nam, Minji Son, and Changick Kim. 2024. SAFIRE: Segment Any Forged Image Region. arXiv preprint arXiv:2412.08197 (2024)."},{"key":"e_1_3_2_1_17_1","volume-title":"Document image forgery detection and localization in desensitization scenarios. Signal Processing","author":"Li Weixiang","year":"2025","unstructured":"Weixiang Li, Bin Li, Kengtao Zheng, Songze Li, and Haodong Li. 2025. Document image forgery detection and localization in desensitization scenarios. Signal Processing (2025), 110123."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_28"},{"key":"e_1_3_2_1_19_1","volume-title":"CTP-Net: Character texture perception network for document image forgery localization. arXiv preprint arXiv:2308.02158","author":"Liao Xin","year":"2023","unstructured":"Xin Liao, Siliang Chen, Jiaxin Chen, Tianyi Wang, and Xiehua Li. 2023. CTP-Net: Character texture perception network for document image forgery localization. arXiv preprint arXiv:2308.02158 (2023)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"e_1_3_2_1_21_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110828"},{"key":"e_1_3_2_1_23_1","volume-title":"ICDAR 2023 competition on detecting tampered text in images. In International Conference on Document Analysis and Recognition. Springer, 587-600","author":"Luo Dongliang","year":"2023","unstructured":"Dongliang Luo, Yu Zhou, Rui Yang, Yuliang Liu, Xianjin Liu, Jishen Zeng, Enming Zhang, Biao Yang, Ziming Huang, Lianwen Jin, et al., 2023. ICDAR 2023 competition on detecting tampered text in images. In International Conference on Document Analysis and Recognition. Springer, 587-600."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TENCON.2019.8929465"},{"key":"e_1_3_2_1_25_1","volume-title":"Image Generation and Learning Strategy for Deep Document Forgery Detection. arXiv preprint arXiv:2311.03650","author":"Okamoto Yamato","year":"2023","unstructured":"Yamato Okamoto, Osada Genki, Iu Yahiro, Rintaro Hasegawa, Peifei Zhu, and Hirokatsu Kataoka. 2023. Image Generation and Learning Strategy for Deep Document Forgery Detection. arXiv preprint arXiv:2311.03650 (2023)."},{"key":"e_1_3_2_1_26_1","unstructured":"Maxime Oquab Timoth\u00e9e Darcet Th\u00e9o Moutakanni Huy Vo Marc Szafraniec Vasil Khalidov Pierre Fernandez Daniel Haziza Francisco Massa Alaaeldin El-Nouby et al. 2023. Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00262"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00575"},{"key":"e_1_3_2_1_29_1","volume-title":"TextSleuth: Towards Explainable Tampered Text Detection. arXiv preprint arXiv:2412.14816","author":"Qu Chenfan","year":"2024","unstructured":"Chenfan Qu, Jian Liu, Haoxing Chen, Baihan Yu, Jingjing Liu, Weiqiang Wang, and Lianwen Jin. 2024a. TextSleuth: Towards Explainable Tampered Text Detection. arXiv preprint arXiv:2412.14816 (2024)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i1.32051"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01025"},{"key":"e_1_3_2_1_32_1","volume-title":"International conference on machine learning. PmLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748-8763."},{"key":"e_1_3_2_1_33_1","volume-title":"International Conference on Neural Information Processing. Springer, 140-151","author":"Shao Huiru","year":"2023","unstructured":"Huiru Shao, Kaizhu Huang, Wei Wang, Xiaowei Huang, and Qiufeng Wang. 2023. Progressive supervision for tampering localization in document images. In International Conference on Neural Information Processing. Springer, 140-151."},{"key":"e_1_3_2_1_34_1","volume-title":"European Conference on Computer Vision. Springer, 290-306","author":"Shao Huiru","year":"2024","unstructured":"Huiru Shao, Zhuang Qian, Kaizhu Huang, Wei Wang, Xiaowei Huang, and Qiufeng Wang. 2024. Delving into Adversarial Robustness on Document Tampering Localization. In European Conference on Computer Vision. Springer, 290-306."},{"key":"e_1_3_2_1_35_1","volume-title":"Deep image composition meets image forgery. arXiv preprint arXiv:2404.02897","author":"Tahir Eren","year":"2024","unstructured":"Eren Tahir and Mert Bal. 2024. Deep image composition meets image forgery. arXiv preprint arXiv:2404.02897 (2024)."},{"key":"e_1_3_2_1_36_1","unstructured":"Tianchi. 2020. Security AI Challenger Program. https:\/\/tianchi.aliyun.com\/competition\/entrance\/531812\/introduction."},{"key":"e_1_3_2_1_37_1","unstructured":"Tianchi. 2022. Real-World Image Forgery Localization Challenge. https:\/\/tianchi.aliyun.com\/competition\/entrance\/531945\/introduction."},{"key":"e_1_3_2_1_38_1","first-page":"49","volume-title":"Proceedings ELMAR-2013","author":"Tralic Dijana","year":"2013","unstructured":"Dijana Tralic, Ivan Zupancic, Sonja Grgic, and Mislav Grgic. 2013. CoMoFoD-New database for copy-move forgery detection. In Proceedings ELMAR-2013. IEEE, 49-54."},{"key":"e_1_3_2_1_39_1","article-title":"Visualizing data using t-SNE","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research, Vol. 9, 11 (2008).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_13"},{"key":"e_1_3_2_1_41_1","first-page":"29","article-title":"Tampered text detection via rgb and frequency relationship modeling","volume":"8","author":"Wang Yuxin","year":"2022","unstructured":"Yuxin Wang, Boqiang Zhang, Hongtao Xie, and Yongdong Zhang. 2022b. Tampered text detection via rgb and frequency relationship modeling. Chinese Journal of Network and Information Security, Vol. 8, 3 (2022), 29-40.","journal-title":"Chinese Journal of Network and Information Security"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02704"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20193"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1002\/int.22792"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095070"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01213"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00219"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2021.3070444"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754857","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:35:21Z","timestamp":1765308921000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754857"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":48,"alternative-id":["10.1145\/3746027.3754857","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754857","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}