{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T10:49:44Z","timestamp":1743072584038,"version":"3.40.3"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031476365"},{"type":"electronic","value":"9783031476372"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-47637-2_26","type":"book-chapter","created":{"date-parts":[[2023,11,4]],"date-time":"2023-11-04T20:01:39Z","timestamp":1699128099000},"page":"340-354","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Fine-Grained Face Sketch-Photo Synthesis with\u00a0Text-Guided Diffusion Models"],"prefix":"10.1007","author":[{"given":"Jin","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huaibo","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junxian","family":"Duan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ran","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,5]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Cheng, S.I., Chen, Y.J., Chiu, W.C., Tseng, H.Y., Lee, H.Y.: Adaptively-realistic image generation from stroke and sketch with diffusion model. In: WACV (2023)","DOI":"10.1109\/WACV56688.2023.00404"},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"Choi, J., Kim, S., Jeong, Y., Gwon, Y., Yoon, S.: Ilvr: conditioning method for denoising diffusion probabilistic models. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01410"},{"key":"26_CR3","unstructured":"Chung, H., Sim, B., Ryu, D., Ye, J.C.: Improving diffusion models for inverse problems using manifold constraints. In: NeurIPS (2022)"},{"key":"26_CR4","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: NeurIPS, vol. 34 (2021)"},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Duan, S., Chen, Z., Wu, Q.M.J., Cai, L., Lu, D.: Multi-scale gradients self-attention residual learning for face photo-sketch transformation. In: IEEE TIFS (2021)","DOI":"10.1109\/TIFS.2020.3031386"},{"key":"26_CR6","unstructured":"Goodfellow, I.J., et al.: Generative adversarial networks. arXiv preprint arXiv:1406.2661 (2014)"},{"key":"26_CR7","doi-asserted-by":"crossref","unstructured":"Gu, S., et al.: Vector quantized diffusion model for text-to-image synthesis. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"26_CR8","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1007\/978-3-642-05224-8_11","volume-title":"Advances in Machine Learning","author":"R He","year":"2009","unstructured":"He, R., Hu, B.-G., Yuan, X.-T.: Robust discriminant analysis based on nonparametric maximum entropy. In: Zhou, Z.-H., Washio, T. (eds.) ACML 2009. LNCS (LNAI), vol. 5828, pp. 120\u2013134. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-05224-8_11"},{"issue":"12","key":"26_CR9","doi-asserted-by":"publisher","first-page":"5543","DOI":"10.1109\/TIP.2015.2466106","volume":"24","author":"R He","year":"2015","unstructured":"He, R., Zhang, M., Wang, L., Ji, Y., Yin, Q.: Cross-modal subspace learning via pairwise constraints. IEEE Trans. Image Process. 24(12), 5543\u20135556 (2015)","journal-title":"IEEE Trans. Image Process."},{"key":"26_CR10","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local NASH equilibrium. In: NeurIPS (2017)"},{"key":"26_CR11","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)"},{"key":"26_CR12","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. In: NeurIPSW (2021)"},{"key":"26_CR13","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"Li, H., Yang, Y., Chang, M., Chen, S., Feng, H., Xu, Z., Li, Q., Chen, Y.: SRDiff: single image super-resolution with diffusion probabilistic models. In: Neurocomputing (2022)","DOI":"10.1016\/j.neucom.2022.01.029"},{"key":"26_CR15","doi-asserted-by":"crossref","unstructured":"Lin, Y., Ling, S., Fu, K., Cheng, P.: An identity-preserved model for face sketch-photo synthesis. In: IEEE LSP (2020)","DOI":"10.1109\/LSP.2020.3005039"},{"key":"26_CR16","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2019)"},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"Luo, M., Wu, H., Huang, H., He, W., He, R.: Memory-modulated transformer network for heterogeneous face recognition. In: IEEE TIFS (2022)","DOI":"10.1109\/TIFS.2022.3177960"},{"key":"26_CR18","unstructured":"Meng, C., et al.: SDEdit: guided image synthesis and editing with stochastic differential equations. In: ICLR (2021)"},{"key":"26_CR19","unstructured":"Nichol, A., et al.: Glide: towards photorealistic image generation and editing with text-guided diffusion models. In: ICML (2022)"},{"key":"26_CR20","doi-asserted-by":"crossref","unstructured":"Peng, C., Gao, X., Wang, N., Li, J.: Superpixel-based face sketch\u2013photo synthesis. In: IEEE TCSVT (2017)","DOI":"10.1109\/TCSVT.2015.2502861"},{"key":"26_CR21","doi-asserted-by":"crossref","unstructured":"Peng, C., Wang, N., Li, J., Gao, X.: Universal face photo-sketch style transfer via multiview domain translation. In: IEEE TIP (2020)","DOI":"10.1109\/TIP.2020.3016502"},{"key":"26_CR22","doi-asserted-by":"crossref","unstructured":"Preechakul, K., Chatthee, N., Wizadwongsa, S., Suwajanakorn, S.: Diffusion autoencoders: toward a meaningful and decodable representation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01036"},{"key":"26_CR23","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"26_CR25","doi-asserted-by":"crossref","unstructured":"Saharia, C., Ho, J., Chan, W., Salimans, T., Fleet, D.J., Norouzi, M.: Image super-resolution via iterative refinement. In: IEEE TPAMI (2022)","DOI":"10.1109\/TPAMI.2022.3204461"},{"key":"26_CR26","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: ICML (2015)"},{"key":"26_CR27","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: ICLR (2021)"},{"key":"26_CR28","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. In: ICLR (2021)"},{"key":"26_CR29","doi-asserted-by":"crossref","unstructured":"Tang, X., Wang, X.: Face sketch recognition. In: IEEE TCSVT (2004)","DOI":"10.1109\/TCSVT.2003.818353"},{"key":"26_CR30","doi-asserted-by":"crossref","unstructured":"Voynov, A., Aberman, K., Cohen-Or, D.: Sketch-guided text-to-image diffusion models. arXiv preprint arXiv:2211.13752 (2022)","DOI":"10.1145\/3588432.3591560"},{"key":"26_CR31","doi-asserted-by":"crossref","unstructured":"Wang, L., Sindagi, V., Patel, V.: High-quality facial photo-sketch synthesis using multi-adversarial networks. In: FG (2018)","DOI":"10.1109\/FG.2018.00022"},{"key":"26_CR32","unstructured":"Wang, X., Tang, X.: Face photo-sketch synthesis and recognition. In: IEEE TPAMI (2008)"},{"key":"26_CR33","doi-asserted-by":"crossref","unstructured":"Xiao, B., Gao, X., Tao, D., Yuan, Y., Li, J.: Photo-sketch synthesis and recognition based on subspace learning. In: Neurocomputing (2010)","DOI":"10.1016\/j.neucom.2009.10.014"},{"key":"26_CR34","doi-asserted-by":"crossref","unstructured":"Yu, J., et al.: Toward realistic face photo\u2013sketch synthesis via composition-aided GANs. In: IEEE TCYB (2021)","DOI":"10.1109\/TCYB.2020.2972944"},{"key":"26_CR35","doi-asserted-by":"crossref","unstructured":"Yu, W., Zhu, M., Wang, N., Wang, X., Gao, X.: An efficient transformer based on global and local self-attention for face photo-sketch synthesis. In: IEEE TIP (2023)","DOI":"10.1109\/TIP.2022.3229614"},{"key":"26_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, L., Zhang, L., Mou, X., Zhang, D.: FSIM: a feature similarity index for image quality assessment. In: IEEE TIP (2011)","DOI":"10.1109\/TIP.2011.2109730"},{"key":"26_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"26_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, S., Ji, R., Hu, J., Lu, X., Li, X.: Face sketch synthesis by multidomain adversarial learning. In: IEEE TNNLS (2018)","DOI":"10.1109\/TNNLS.2018.2869574"},{"key":"26_CR39","doi-asserted-by":"crossref","unstructured":"Zhao, M., Bao, F., Li, C., Zhu, J.: EGSDE: unpaired image-to-image translation via energy-guided stochastic differential equations. In: NeurIPS (2022)","DOI":"10.1109\/CVPR46437.2021.01615"},{"key":"26_CR40","unstructured":"Zhou, H., Kuang, Z., Wong, K.Y.K.: Markov weight fields for face sketch synthesis. In: CVPR (2012)"},{"key":"26_CR41","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: ICCV (2017)","DOI":"10.1109\/ICCV.2017.244"},{"key":"26_CR42","doi-asserted-by":"crossref","unstructured":"Zhu, M., Li, J., Wang, N., Gao, X.: Knowledge distillation for face photo\u2013sketch synthesis. In: IEEE TNNLS (2022)","DOI":"10.1109\/TNNLS.2020.3030536"},{"key":"26_CR43","doi-asserted-by":"crossref","unstructured":"Zhu, M., Wang, N., Gao, X., Li, J., Li, Z.: Face photo-sketch synthesis via knowledge transfer. In: IJCAI (2019)","DOI":"10.24963\/ijcai.2019\/147"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-47637-2_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,4]],"date-time":"2023-11-04T20:08:54Z","timestamp":1699128534000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-47637-2_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031476365","9783031476372"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-47637-2_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"5 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kitakyushu","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"acpr2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ericlab.org\/acpr2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"164","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"93","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"57% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}