{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:43:04Z","timestamp":1775230984012,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":37,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819787944","type":"print"},{"value":"9789819787951","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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\/978-981-97-8795-1_19","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T23:03:49Z","timestamp":1730588629000},"page":"278-291","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Robust Document Presentation Attack Detection via\u00a0Diffusion Models and\u00a0Knowledge Distillation"],"prefix":"10.1007","author":[{"given":"Bokang","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4857-6810","authenticated-orcid":false,"given":"Changsheng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"19_CR1","unstructured":"Bao, H., Dong, L., Piao, S., Wei, F.: Beit: Bert pre-training of image transformers. In: International Conference on Learning Representations (2021)"},{"key":"19_CR2","doi-asserted-by":"publisher","first-page":"1814","DOI":"10.1109\/TIFS.2023.3255585","volume":"18","author":"D Benalcazar","year":"2023","unstructured":"Benalcazar, D., Tapia, J.E., Gonzalez, S., Busch, C.: Synthetic id card image generation for improving presentation attack detection. IEEE Trans. Inf. Forensics Secur. 18, 1814\u20131824 (2023)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"19_CR3","unstructured":"Chen, C., Chen, W., Chen, X., Li, H.: A document presentation attack detection scheme with optical flow under a flashlight. Pattern Recognition, Submitted (2023)"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Chen, C., Deng, y., Lin, L., Yu, Z., Lai, Z.: Multi-modal document presentation attack detection with forensic trace disentanglement. In: IEEE International Conference on Multimedia and Expo (2024)","DOI":"10.1109\/ICME57554.2024.10687888"},{"key":"19_CR5","doi-asserted-by":"publisher","first-page":"1283","DOI":"10.1109\/TIFS.2023.3333548","volume":"19","author":"C Chen","year":"2024","unstructured":"Chen, C., Li, B., Cai, R., Zeng, J., Huang, J.: Distortion model-based spectral augmentation for generalized recaptured document detection. IEEE Trans. Inf. Forensics Secur. 19, 1283\u20131298 (2024)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"19_CR6","doi-asserted-by":"publisher","first-page":"2890","DOI":"10.1109\/TIFS.2022.3197054","volume":"17","author":"C Chen","year":"2022","unstructured":"Chen, C., Zhang, S., Lan, F., Huang, J.: Domain-agnostic document authentication against practical recapturing attacks. IEEE Trans. Inf. Forensics Secur. 17, 2890\u20132905 (2022)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"19_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2022.108666","volume":"200","author":"C Chen","year":"2022","unstructured":"Chen, C., Zhao, L., Yan, J., Li, H.: A distortion model-based pre-screening method for document image tampering localization under recapturing attack. Signal Process. 200, 108666 (2022)","journal-title":"Signal Process."},{"key":"19_CR8","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat gans on image synthesis. Adv. Neural. Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR9","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth 16 $$\\times $$ 16 words: Transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"19_CR10","doi-asserted-by":"publisher","first-page":"6898","DOI":"10.1109\/TIP.2020.2995049","volume":"29","author":"S Ge","year":"2020","unstructured":"Ge, S., Zhao, S., Li, C., Zhang, Y., Li, J.: Efficient low-resolution face recognition via bridge distillation. IEEE Trans. Image Process. 29, 6898\u20136908 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"19_CR11","unstructured":"Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved training of wasserstein gans. Adv. Neural Inform. Process. Syst. 30 (2017)"},{"issue":"1","key":"19_CR12","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1007\/s44267-023-00003-0","volume":"1","author":"G Guo","year":"2023","unstructured":"Guo, G., Han, L., Wang, L., Zhang, D., Han, J.: Semantic-aware knowledge distillation with parameter-free feature uniformization. Visual Intell. 1(1), 6 (2023)","journal-title":"Visual Intell."},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"19_CR14","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: NIPS Deep Learning and Representation Learning Workshop (2015)"},{"key":"19_CR15","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR16","doi-asserted-by":"publisher","first-page":"2800","DOI":"10.1109\/TIFS.2022.3192999","volume":"17","author":"Z Hu","year":"2022","unstructured":"Hu, Z., Chen, C., Mow, W.H., Huang, J.: Document recapture detection based on a unified distortion model of halftone cells. IEEE Trans. Inf. Forensics Secur. 17, 2800\u20132815 (2022)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"issue":"1","key":"19_CR17","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1007\/s44267-024-00040-3","volume":"2","author":"Z Jia","year":"2024","unstructured":"Jia, Z., Sun, S., Liu, G., Liu, B.: Mssd: multi-scale self-distillation for object detection. Visual Intell. 2(1), 8 (2024)","journal-title":"Visual Intell."},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"Li, J., Kong, C., Wang, S., Li, H.: Two-branch multi-scale deep neural network for generalized document recapture attack detection. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, pp.\u00a01\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10095419"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: 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":"19_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11976\u201311986 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"19_CR22","unstructured":"Metz, L., Poole, B., Pfau, D., Sohl-Dickstein, J.: Unrolled generative adversarial networks. In: International Conference on Learning Representations (2016)"},{"key":"19_CR23","unstructured":"Phuong, M., Lampert, C.: Towards understanding knowledge distillation. In: International Conference on Machine Learning, pp. 5142\u20135151. PMLR (2019)"},{"issue":"7","key":"19_CR24","doi-asserted-by":"publisher","first-page":"181","DOI":"10.3390\/jimaging8070181","volume":"8","author":"DV Polevoy","year":"2022","unstructured":"Polevoy, D.V., Sigareva, I.V., Ershova, D.M., Arlazarov, V.V., Nikolaev, D.P., Ming, Z., Luqman, M.M., Burie, J.C.: Document liveness challenge dataset (DLC-2021). J. Imaging 8(7), 181 (2022)","journal-title":"J. Imaging"},{"key":"19_CR25","doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Doll\u00e1r, P., Girshick, R., Gkioxari, G., He, K.: Data distillation: Towards omni-supervised learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4119\u20134128 (2018)","DOI":"10.1109\/CVPR.2018.00433"},{"key":"19_CR26","unstructured":"Ravuri, S., Vinyals, O.: Classification accuracy score for conditional generative models. Adv. Neural Inform. Process. Syst. 32 (2019)"},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"Saharia, C., Chan, W., Chang, H., Lee, C., Ho, J., Salimans, T., Fleet, D., Norouzi, M.: Palette: Image-to-image diffusion models. In: ACM SIGGRAPH 2022 Conference Proceedings, pp. 1\u201310 (2022)","DOI":"10.1145\/3528233.3530757"},{"issue":"4","key":"19_CR29","first-page":"4713","volume":"45","author":"C Saharia","year":"2022","unstructured":"Saharia, C., Ho, J., Chan, W., Salimans, T., Fleet, D.J., Norouzi, M.: Image super-resolution via iterative refinement. IEEE Trans. Pattern Anal. Mach. Intell. 45(4), 4713\u20134726 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"146","key":"19_CR30","first-page":"10","volume":"2006","author":"S Tomar","year":"2006","unstructured":"Tomar, S.: Converting video formats with FFmpeg. Linux J. 2006(146), 10 (2006)","journal-title":"Linux J."},{"key":"19_CR31","unstructured":"Yan, J., Chen, C.: Cross-domain recaptured document detection with texture and reflectance characteristics. In: APSIPA ASC, pp. 1708\u20131715. IEEE (2021)"},{"key":"19_CR32","first-page":"4203","volume":"35","author":"J Yang","year":"2022","unstructured":"Yang, J., Li, C., Dai, X., Gao, J.: Focal modulation networks. Adv. Neural. Inf. Process. Syst. 35, 4203\u20134217 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR33","unstructured":"Ye, H., Zhang, J., Liu, S., Han, X., Yang, W.: Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721 (2023)"},{"key":"19_CR34","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1016\/j.sigpro.2019.02.025","volume":"160","author":"J Zhang","year":"2019","unstructured":"Zhang, J., Fisher, R.B.: 3d visual passcode: speech-driven 3d facial dynamics for behaviometrics. Signal Process. 160, 164\u2013177 (2019)","journal-title":"Signal Process."},{"key":"19_CR35","doi-asserted-by":"publisher","first-page":"7964","DOI":"10.1109\/TIP.2021.3112048","volume":"30","author":"L Zhao","year":"2021","unstructured":"Zhao, L., Chen, C., Huang, J.: Deep learning-based forgery attack on document images. IEEE Trans. Image Process. 30, 7964\u20137979 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"19_CR36","unstructured":"Zhou, Y., Muresanu, A.I., Han, Z., Paster, K., Pitis, S., Chan, H., Ba, J.: Large language models are human-level prompt engineers. In: The Eleventh International Conference on Learning Representations (2023)"},{"key":"19_CR37","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223\u20132232 (2017)","DOI":"10.1109\/ICCV.2017.244"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8795-1_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T23:04:48Z","timestamp":1730588688000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8795-1_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9789819787944","9789819787951"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8795-1_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}