{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T03:47:15Z","timestamp":1770695235086,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":29,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819569564","type":"print"},{"value":"9789819569571","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\/978-981-95-6957-1_21","type":"book-chapter","created":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T10:43:57Z","timestamp":1770633837000},"page":"290-303","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TTEdit: Cross-Modal Fusion with\u00a0Diffusion Models for\u00a0Detail-Aware Fashion Editing"],"prefix":"10.1007","author":[{"given":"Feng","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Junliang","family":"Tan","sequence":"additional","affiliation":[]},{"given":"Zhenming","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Biao","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Junyan","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Yao","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Ming","family":"Jiang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,2,10]]},"reference":[{"key":"21_CR1","unstructured":"Shuai, X., Ding, H., Ma, X., et al.: A survey of multimodal-guided image editing with text-to-image diffusion models. arXiv preprint arXiv:2406.14555 (2024)"},{"issue":"12","key":"21_CR2","doi-asserted-by":"publisher","first-page":"15098","DOI":"10.1109\/TPAMI.2023.3305243","volume":"45","author":"F Zhan","year":"2023","unstructured":"Zhan, F., Yu, Y., Wu, R., et al.: Multimodal image synthesis and editing: the generative AI era. IEEE Trans. Pattern Anal. Mach. Intell. 45(12), 15098\u201315119 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR3","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"21_CR4","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems, vol. 33, pp. 6840\u20136851 (2020)"},{"key":"21_CR5","unstructured":"Radford, A., Kim, J.W., Hallacy, C., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"issue":"5","key":"21_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3610287","volume":"42","author":"AC Baykal","year":"2023","unstructured":"Baykal, A.C., Anees, A.B., Ceylan, D., et al.: CLIP-guided StyleGAN inversion for text-driven real image editing. ACM Trans. Graph. 42(5), 1\u201318 (2023)","journal-title":"ACM Trans. Graph."},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Kawar, B., Zada, S., Lang, O., et al.: Imagic: text-based real image editing with diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6007\u20136017 (2023)","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Lin, Y., Chen, Y.W., Tsai, Y.H., et al.: Text-driven image editing via learnable regions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7059\u20137068 (2024)","DOI":"10.1109\/CVPR52733.2024.00674"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Lin, A., Zhao, N., Ning, S., et al.: FashionTex: controllable virtual try-on with text and texture. In: ACM SIGGRAPH 2023 Conference Proceedings, pp. 1\u20139 (2023)","DOI":"10.1145\/3588432.3591568"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., et al.: 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":"21_CR11","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., et al.: Hierarchical text-conditional image generation with CLIP latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"21_CR12","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.C.H.: BLIP: bootstrapping Language-Image Pre-training for unified vision-language understanding and generation. In: Proceedings of the 39th International Conference on Machine Learning (ICML 2022), PMLR, vol. 162, pp. 12888\u201312900 (2022)"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: InstructPix2Pix: learning to follow image editing instructions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18392\u201318402 (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Wang, T., Ye, M.: TexFit: text-driven fashion image editing with diffusion models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 9, pp. 10198\u201310206 (2024)","DOI":"10.1609\/aaai.v38i9.28885"},{"key":"21_CR15","unstructured":"Nichol, A., Dhariwal, P., Ramesh, A., et al.: Glide: towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)"},{"key":"21_CR16","unstructured":"Gal, R., Alaluf, Y., Atzmon, Y., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618 (2022)"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Mou, C., Wang, X., Xie, L., et al.: T2I-adapter: learning adapters to dig out more controllable ability for text-to-image diffusion models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 5, pp. 4296\u20134304 (2024)","DOI":"10.1609\/aaai.v38i5.28226"},{"issue":"4","key":"21_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3450626.3459884","volume":"40","author":"KM Lewis","year":"2021","unstructured":"Lewis, K.M., Varadharajan, S., Kemelmacher-Shlizerman, I.: TryOnGAN: body-aware try-on via layered interpolation. ACM Trans. Graph. (TOG) 40(4), 1\u201310 (2021)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"21_CR19","unstructured":"Xie, Z., Huang, Z., Zhao, F., et al.: PASTA-GAN++: a versatile framework for high-resolution unpaired virtual try-on. arXiv preprint arXiv:2207.13475 (2022)"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Zhang, J., Li, K., Lai, Y.K., et al.: PISE: person image synthesis and editing with decoupled GAN. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7982\u20137990 (2021)","DOI":"10.1109\/CVPR46437.2021.00789"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Raffiee, A.H., Sollami, M.: GarmentGAN: photo-realistic adversarial fashion transfer. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 3923\u20133930. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9412908"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 4015\u20134026 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"21_CR23","unstructured":"Xiao, J., Wang, Z.: DeepLabv3+: encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1\u20135 (2019)"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2881\u20132890 (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"21_CR25","doi-asserted-by":"crossref","unstructured":"Gatys, L.A., Ecker, A.S., Bethge, M.: Image style transfer using convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2414\u20132423 (2016)","DOI":"10.1109\/CVPR.2016.265"},{"issue":"4","key":"21_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530104","volume":"41","author":"Y Jiang","year":"2022","unstructured":"Jiang, Y., Yang, S., Qiu, H., Wu, W., Loy, C.C., Liu, Z.: Text2Human: text-driven controllable human image generation. ACM Trans. Graph. (Proceedings of SIGGRAPH) 41(4), 1\u201311 (2022)","journal-title":"ACM Trans. Graph. (Proceedings of SIGGRAPH)"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Yang, B., Gu, S., Zhang, B., et al.: Paint by example: exemplar-based image editing with diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18381\u201318391 (2023)","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"21_CR28","doi-asserted-by":"crossref","unstructured":"Chen, X., Huang, L., Liu, Y., et al.: AnyDoor: zero-shot object-level image customization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6593\u20136602 (2024)","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"21_CR29","unstructured":"Song, W., Jiang, H., Yang, Z., et al.: Insert anything: image insertion via in-context editing in DiT. arXiv preprint arXiv:2504.15009 (2025)"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-6957-1_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T10:44:03Z","timestamp":1770633843000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-6957-1_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819569564","9789819569571"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-6957-1_21","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":"10 February 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Prague","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 January 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 January 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2026.cz\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}