{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T02:59:03Z","timestamp":1767322743865,"version":"3.48.0"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032113160","type":"print"},{"value":"9783032113177","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-3-032-11317-7_49","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T02:54:07Z","timestamp":1767322447000},"page":"609-619","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SISMA: Semantic Face Image Synthesis with\u00a0Mamba"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7567-753X","authenticated-orcid":false,"given":"Filippo","family":"Botti","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8110-9714","authenticated-orcid":false,"given":"Alex","family":"Ergasti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6595-4874","authenticated-orcid":false,"given":"Tomaso","family":"Fontanini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9465-6753","authenticated-orcid":false,"given":"Claudio","family":"Ferrari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1463-5384","authenticated-orcid":false,"given":"Massimo","family":"Bertozzi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1211-529X","authenticated-orcid":false,"given":"Andrea","family":"Prati","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"49_CR1","doi-asserted-by":"publisher","unstructured":"Botti, F., et al.: Mamba-ST: state space model for efficient style transfer. In: 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 7797\u20137806 (2025). https:\/\/doi.org\/10.1109\/WACV61041.2025.00757","DOI":"10.1109\/WACV61041.2025.00757"},{"key":"49_CR2","unstructured":"Dao, T., Gu, A.: Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality. arXiv preprint arXiv:2405.21060 (2024)"},{"key":"49_CR3","doi-asserted-by":"publisher","unstructured":"Ergasti, A., Botti, F., Fontanini, T., Ferrari, C., Bertozzi, M., Prati, A.: U-shape mamba: state space model for faster diffusion. In: 2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 3242\u20133249 (2025). https:\/\/doi.org\/10.1109\/CVPRW67362.2025.00307","DOI":"10.1109\/CVPRW67362.2025.00307"},{"key":"49_CR4","doi-asserted-by":"crossref","unstructured":"Ergasti, A., Ferrari, C., Fontanini, T., Bertozzi, M., Prati, A.: Controllable face synthesis with semantic latent diffusion models. In: Palaiahnakote, S., Schuckers, S., Ogier, J.M., Bhattacharya, P., Pal, U., Bhattacharya, S. (eds.) Pattern Recognition. ICPR 2024 International Workshops and Challenges, pp. 337\u2013352. Springer Nature Switzerland, Cham (2025)","DOI":"10.1007\/978-3-031-87660-8_25"},{"key":"49_CR5","doi-asserted-by":"crossref","unstructured":"Fontanini, T., Ferrari, C., Bertozzi, M., Prati, A.: Automatic generation of semantic parts for face image synthesis. In: International Conference on Image Analysis and Processing, pp. 209\u2013221. Springer (2023)","DOI":"10.1007\/978-3-031-43148-7_18"},{"key":"49_CR6","doi-asserted-by":"crossref","unstructured":"Fontanini, T., Ferrari, C., Lisanti, G., Bertozzi, M., Prati, A.: Semantic image synthesis via class-adaptive cross-attention. IEEE Access (2025)","DOI":"10.1109\/ACCESS.2025.3529216"},{"key":"49_CR7","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.patrec.2023.10.010","volume":"176","author":"T Fontanini","year":"2023","unstructured":"Fontanini, T., et al.: FrankenMask: manipulating semantic masks with transformers for face parts editing. Pattern Recogn. Lett. 176, 14\u201320 (2023)","journal-title":"Pattern Recogn. Lett."},{"key":"49_CR8","unstructured":"Gao, Y., Huang, J., Sun, X., Jie, Z., Zhong, Y., Ma, L.: Matten: Video generation with mamba-attention (2024). https:\/\/arxiv.org\/abs\/2405.03025"},{"key":"49_CR9","unstructured":"Gu, A., Dao, T.: Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)"},{"key":"49_CR10","unstructured":"Gu, A., Goel, K., R\u00e9, C.: Efficiently modeling long sequences with structured state spaces. arXiv preprint arXiv:2111.00396 (2021)"},{"key":"49_CR11","first-page":"572","volume":"34","author":"A Gu","year":"2021","unstructured":"Gu, A., et al.: Combining recurrent, convolutional, and continuous-time models with linear state space layers. Adv. Neural. Inf. Process. Syst. 34, 572\u2013585 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"49_CR12","doi-asserted-by":"crossref","unstructured":"Hu, V.T., et al.: ZigMa: a DiT-style zigzag mamba diffusion model. In: European Conference on Computer Vision, pp. 148\u2013166. Springer (2024)","DOI":"10.1007\/978-3-031-72664-4_9"},{"key":"49_CR13","unstructured":"Huang, L., Chen, D., Liu, Y., Shen, Y., Zhao, D., Zhou, J.: Composer: Creative and controllable image synthesis with composable conditions (2023)"},{"key":"49_CR14","doi-asserted-by":"crossref","unstructured":"Huang, Z., Chan, K.C.K., Jiang, Y., Liu, Z.: Collaborative diffusion for multi-modal face generation and editing (2023)","DOI":"10.1109\/CVPR52729.2023.00589"},{"key":"49_CR15","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"49_CR16","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"49_CR17","doi-asserted-by":"crossref","unstructured":"Lee, C.H., Liu, Z., Wu, L., Luo, P.: MaskGAN: Towards diverse and interactive facial image manipulation (2020)","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"49_CR18","unstructured":"Lipman, Y., Chen, R.T.Q., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=PqvMRDCJT9t"},{"key":"49_CR19","unstructured":"Liu, X., Yin, G., Shao, J., Wang, X., et\u00a0al.: Learning to predict layout-to-image conditional convolutions for semantic image synthesis. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"49_CR20","unstructured":"Liu, X., Gong, C., Liu, Q.: Flow straight and fast: Learning to generate and transfer data with rectified flow. arXiv preprint arXiv:2209.03003 (2022)"},{"key":"49_CR21","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"49_CR22","doi-asserted-by":"crossref","unstructured":"Mou, C., et al.: T2I-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models. arXiv preprint arXiv:2302.08453 (2023)","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"49_CR23","doi-asserted-by":"crossref","unstructured":"Park, T., Liu, M.Y., Wang, T.C., Zhu, J.Y.: Semantic image synthesis with spatially-adaptive normalization (2019)","DOI":"10.1109\/CVPR.2019.00244"},{"key":"49_CR24","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"49_CR25","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"49_CR26","doi-asserted-by":"crossref","unstructured":"Shi, Y., Yang, X., Wan, Y., Shen, X.: SemanticStyleGAN: Learning compositional generative priors for controllable image synthesis and editing (2022)","DOI":"10.1109\/CVPR52688.2022.01097"},{"key":"49_CR27","doi-asserted-by":"crossref","unstructured":"Tan, Z., et al.: Diverse semantic image synthesis via probability distribution modeling (2021)","DOI":"10.1109\/CVPR46437.2021.00787"},{"key":"49_CR28","doi-asserted-by":"crossref","unstructured":"Tan, Z., et al.: Efficient semantic image synthesis via class-adaptive normalization (2021)","DOI":"10.1109\/TPAMI.2021.3076487"},{"key":"49_CR29","doi-asserted-by":"crossref","unstructured":"Tang, H., Bai, S., Sebe, N.: Dual attention GANs for semantic image synthesis. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 1994\u20132002 (2020)","DOI":"10.1145\/3394171.3416270"},{"key":"49_CR30","doi-asserted-by":"crossref","unstructured":"Tarollo, G., Fontanini, T., Ferrari, C., Borghi, G., Prati, A.: Adversarial identity injection for semantic face image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1471\u20131480 (2024)","DOI":"10.1109\/CVPRW63382.2024.00154"},{"key":"49_CR31","doi-asserted-by":"crossref","unstructured":"Wang, T.C., Liu, M.Y., Zhu, J.Y., Tao, A., Kautz, J., Catanzaro, B.: High-resolution image synthesis and semantic manipulation with conditional GANs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8798\u20138807 (2018)","DOI":"10.1109\/CVPR.2018.00917"},{"key":"49_CR32","unstructured":"Wang, W., Bao, J., Zhou, W., Chen, D., Chen, D., Yuan, L., Li, H.: Semantic image synthesis via diffusion models (2022)"},{"key":"49_CR33","doi-asserted-by":"crossref","unstructured":"Wang, Y., Qi, L., Chen, Y.C., Zhang, X., Jia, J.: Image synthesis via semantic composition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13749\u201313758 (2021)","DOI":"10.1109\/ICCV48922.2021.01349"},{"key":"49_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"49_CR35","doi-asserted-by":"crossref","unstructured":"Zhu, J., Shen, Y., Zhao, D., Zhou, B.: In-domain GAN inversion for real image editing. In: European Conference on Computer Vision, pp. 592\u2013608. Springer (2020)","DOI":"10.1007\/978-3-030-58520-4_35"},{"key":"49_CR36","doi-asserted-by":"publisher","unstructured":"Zhu, P., Abdal, R., Qin, Y., Wonka, P.: SEAN: image synthesis with semantic region-adaptive normalization. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (2020).https:\/\/doi.org\/10.1109\/cvpr42600.2020.00515","DOI":"10.1109\/cvpr42600.2020.00515"},{"key":"49_CR37","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Xu, Z., You, A., Bai, X.: Semantically multi-modal image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5467\u20135476 (2020)","DOI":"10.1109\/CVPR42600.2020.00551"}],"container-title":["Lecture Notes in Computer Science","Image Analysis and Processing - ICIAP 2025 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-11317-7_49","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T02:54:10Z","timestamp":1767322450000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-11317-7_49"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032113160","9783032113177"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-11317-7_49","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIAP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image Analysis and Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Rome","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"15 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iciap2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iciap.org\/home","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}