{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T23:30:55Z","timestamp":1782775855565,"version":"3.54.5"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2024,5,21]],"date-time":"2024-05-21T00:00:00Z","timestamp":1716249600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,5,21]],"date-time":"2024-05-21T00:00:00Z","timestamp":1716249600000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1007\/s11263-024-02088-6","type":"journal-article","created":{"date-parts":[[2024,5,21]],"date-time":"2024-05-21T03:32:06Z","timestamp":1716262326000},"page":"4616-4632","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["ManiCLIP: Multi-attribute Face Manipulation from Text"],"prefix":"10.1007","volume":"132","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3086-3128","authenticated-orcid":false,"given":"Hao","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guosheng","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ana Garc\u00eda","family":"del Molino","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anran","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiashi","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiqi","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,5,21]]},"reference":[{"key":"2088_CR1","doi-asserted-by":"crossref","unstructured":"Chen, J., Shen, Y., & Gao, J., et\u00a0al. (2018). Language-based image editing with recurrent attentive models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 8721\u20138729.","DOI":"10.1109\/CVPR.2018.00909"},{"key":"2088_CR2","doi-asserted-by":"crossref","unstructured":"Cheng, J., Wu, F., Tian, Y., et\u00a0al. (2020). Rifegan: Rich feature generation for text-to-image synthesis from prior knowledge. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10911\u201310920.","DOI":"10.1109\/CVPR42600.2020.01092"},{"key":"2088_CR3","doi-asserted-by":"crossref","unstructured":"Collins, E., Bala, R., Price, B., et\u00a0al. (2020). Editing in style: Uncovering the local semantics of gans. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 5771\u20135780.","DOI":"10.1109\/CVPR42600.2020.00581"},{"key":"2088_CR4","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., et\u00a0al. (2019). Arcface: Additive angular margin loss for deep face recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4690\u20134699.","DOI":"10.1109\/CVPR.2019.00482"},{"key":"2088_CR5","first-page":"19822","volume":"34","author":"M Ding","year":"2021","unstructured":"Ding, M., Yang, Z., Hong, W., et al. (2021). Cogview: Mastering text-to-image generation via transformers. Advances in Neural Information Processing Systems, 34, 19822\u201319835.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2088_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., & Ren, S., et\u00a0al. (2016). Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"2088_CR7","unstructured":"Hertz, A., Mokady, R., & Tenenbaum, J., et\u00a0al. (2022). Prompt-to-prompt image editing with cross attention control. arXiv preprintarXiv:2208.01626"},{"key":"2088_CR8","unstructured":"Heusel, M., Ramsauer, H., & Unterthiner, T., et\u00a0al. (2017). Gans trained by a two time-scale update rule converge to a local nash equilibrium. arXiv preprintarXiv:1706.08500."},{"key":"2088_CR9","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., & Abbeel, P. (2020). Denoising diffusion probabilistic models. Advances in neural information processing systems, 33, 6840\u20136851.","journal-title":"Advances in neural information processing systems"},{"key":"2088_CR10","unstructured":"Huberman-Spiegelglas, I., Kulikov, V., & Michaeli, T. (2023). An edit friendly ddpm noise space: Inversion and manipulations. arXiv preprintarXiv:2304.06140."},{"key":"2088_CR11","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Huang, Z., & Pan, X., et\u00a0al. (2021). Talk-to-edit: Fine-grained facial editing via dialog. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 13799\u201313808.","DOI":"10.1109\/ICCV48922.2021.01354"},{"key":"2088_CR12","doi-asserted-by":"crossref","unstructured":"Jo, Y., & Park, J. (2019). Sc-fegan: Face editing generative adversarial network with user\u2019s sketch and color. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 1745\u20131753.","DOI":"10.1109\/ICCV.2019.00183"},{"key":"2088_CR13","doi-asserted-by":"crossref","unstructured":"Johnson, J., Alahi, A., & Fei-Fei, L. (2016). Perceptual losses for real-time style transfer and super-resolution. In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part II 14, Springer, pp 694\u2013711.","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"2088_CR14","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., & Aila, T. (2019). A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4401\u20134410.","DOI":"10.1109\/CVPR.2019.00453"},{"key":"2088_CR15","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., & Aittala, M., et\u00a0al. (2020). Analyzing and improving the image quality of StyleGAN. In: Proc. CVPR.","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"2088_CR16","unstructured":"Kingma, D.P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprintarXiv:1412.6980."},{"key":"2088_CR17","doi-asserted-by":"crossref","unstructured":"Lee, C.H., Liu, Z., & Wu, L., et\u00a0al. (2020). Maskgan: Towards diverse and interactive facial image manipulation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"2088_CR18","unstructured":"Li, B., Qi, X., & Lukasiewicz, T., et\u00a0al. (2019). Controllable text-to-image generation. Advances in Neural Information Processing Systems,32."},{"key":"2088_CR19","doi-asserted-by":"crossref","unstructured":"Li, B., Qi, X., & Lukasiewicz, T., et\u00a0al. (2020). Manigan: Text-guided image manipulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 7880\u20137889.","DOI":"10.1109\/CVPR42600.2020.00790"},{"key":"2088_CR20","first-page":"16331","volume":"34","author":"H Ling","year":"2021","unstructured":"Ling, H., Kreis, K., Li, D., et al. (2021). Editgan: High-precision semantic image editing. Advances in Neural Information Processing Systems, 34, 16331\u201316345.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2088_CR21","unstructured":"Liu, H., Li, C., Wu, Q., et\u00a0al. (2024). Visual instruction tuning. Advances in neural information processing systems,36."},{"key":"2088_CR22","doi-asserted-by":"crossref","unstructured":"Nitzan, Y., Bermano, A., Li, Y., et\u00a0al. (2020). Face identity disentanglement via latent space mapping. arXiv preprintarXiv:2005.07728.","DOI":"10.1145\/3414685.3417826"},{"key":"2088_CR23","doi-asserted-by":"crossref","unstructured":"Patashnik, O., Wu, Z., & Shechtman, E., et\u00a0al. (2021). Styleclip: Text-driven manipulation of stylegan imagery. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 2085\u20132094.","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"2088_CR24","unstructured":"Radford, A., Kim, J.W., & Hallacy, C., et\u00a0al. (2021). Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, PMLR, pp 8748\u20138763."},{"key":"2088_CR25","unstructured":"Ramesh, A., Dhariwal, P., & Nichol, A., et\u00a0al. (2022). Hierarchical text-conditional image generation with clip latents. arXiv preprintarXiv:2204.06125."},{"key":"2088_CR26","unstructured":"Ramesh, A., Pavlov, M., & Goh, G., et\u00a0al. (2021). Zero-shot text-to-image generation. In: International Conference on Machine Learning, PMLR, pp 8821\u20138831."},{"key":"2088_CR27","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., & Lorenz, D., et\u00a0al. (2021). High-resolution image synthesis with latent diffusion models. arXiv:2112.10752.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2088_CR28","doi-asserted-by":"crossref","unstructured":"Saha, R., Duke, B., & Shkurti, F., et\u00a0al. (2021). Loho: Latent optimization of hairstyles via orthogonalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 1984\u20131993.","DOI":"10.1109\/CVPR46437.2021.00202"},{"key":"2088_CR29","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., & Zhu, M., et\u00a0al. (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4510\u20134520.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"2088_CR30","first-page":"25278","volume":"35","author":"C Schuhmann","year":"2022","unstructured":"Schuhmann, C., Beaumont, R., Vencu, R., et al. (2022). Laion-5b: An open large-scale dataset for training next generation image-text models. Advances in Neural Information Processing Systems, 35, 25278\u201325294.","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"3","key":"2088_CR31","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1002\/j.1538-7305.1948.tb01338.x","volume":"27","author":"CE Shannon","year":"1948","unstructured":"Shannon, C. E. (1948). A mathematical theory of communication. The Bell system technical journal, 27(3), 379\u2013423.","journal-title":"The Bell system technical journal"},{"key":"2088_CR32","doi-asserted-by":"crossref","unstructured":"Shen, Y., Gu, J., & Tang. X., et\u00a0al. (2020a). Interpreting the latent space of gans for semantic face editing. In: CVPR.","DOI":"10.1109\/CVPR42600.2020.00926"},{"issue":"4","key":"2088_CR33","doi-asserted-by":"publisher","first-page":"2004","DOI":"10.1109\/TPAMI.2020.3034267","volume":"44","author":"Y Shen","year":"2020","unstructured":"Shen, Y., Yang, C., Tang, X., et al. (2020). Interfacegan: Interpreting the disentangled face representation learned by gans. IEEE transactions on pattern analysis and machine intelligence, 44(4), 2004\u20132018.","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"2088_CR34","doi-asserted-by":"crossref","unstructured":"Tan, Z., Chai, M., Chen, D., et\u00a0al. (2020). Michigan: multi-input-conditioned hair image generation for portrait editing. arXiv preprintarXiv:2010.16417.","DOI":"10.1145\/3386569.3392488"},{"key":"2088_CR35","unstructured":"Tov, O., Alaluf, Y., & Nitzan, Y., et\u00a0al. (2021). Designing an encoder for stylegan image manipulation. arXiv preprintarXiv:2102.02766."},{"key":"2088_CR36","doi-asserted-by":"crossref","unstructured":"Wang, H., Lin, G., Hoi, S.C., et\u00a0al. (2021). Cycle-consistent inverse gan for text-to-image synthesis. In: Proceedings of the 29th ACM International Conference on Multimedia, pp 630\u2013638.","DOI":"10.1145\/3474085.3475226"},{"key":"2088_CR37","doi-asserted-by":"crossref","unstructured":"Wang, T., Zhang, Y., & Fan, Y., et\u00a0al. (2022). High-fidelity gan inversion for image attribute editing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 11379\u201311388.","DOI":"10.1109\/CVPR52688.2022.01109"},{"key":"2088_CR38","doi-asserted-by":"crossref","unstructured":"Wei, T., Chen, D., & Zhou, W., et\u00a0al. (2022). Hairclip: Design your hair by text and reference image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 18072\u201318081.","DOI":"10.1109\/CVPR52688.2022.01754"},{"key":"2088_CR39","doi-asserted-by":"crossref","unstructured":"Wu, Z., Lischinski, D., & Shechtman, E. (2021). Stylespace analysis: Disentangled controls for stylegan image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 12863\u201312872.","DOI":"10.1109\/CVPR46437.2021.01267"},{"key":"2088_CR40","doi-asserted-by":"crossref","unstructured":"Wu, Q., Liu, Y., & Zhao, H., et\u00a0al. (2023). Uncovering the disentanglement capability in text-to-image diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 1900\u20131910.","DOI":"10.1109\/CVPR52729.2023.00189"},{"key":"2088_CR41","doi-asserted-by":"crossref","unstructured":"Xia, W., Yang, Y., & Xue, J.H., et\u00a0al. (2021). Tedigan: Text-guided diverse face image generation and manipulation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","DOI":"10.1109\/CVPR46437.2021.00229"},{"key":"2088_CR42","doi-asserted-by":"crossref","unstructured":"Xu, Y., Yin, Y., & Jiang, L., et\u00a0al. (2022). Transeditor: Transformer-based dual-space gan for highly controllable facial editing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 7683\u20137692.","DOI":"10.1109\/CVPR52688.2022.00753"},{"key":"2088_CR43","doi-asserted-by":"crossref","unstructured":"Xu, T., Zhang, P., & Huang, Q., et\u00a0al. (2018). Attngan: Fine-grained text to image generation with attentional generative adversarial networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1316\u20131324.","DOI":"10.1109\/CVPR.2018.00143"},{"key":"2088_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, H., Koh, J.Y., & Baldridge, J., et\u00a0al. (2021). Cross-modal contrastive learning for text-to-image generation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 833\u2013842.","DOI":"10.1109\/CVPR46437.2021.00089"},{"key":"2088_CR45","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., & Qi, X., et\u00a0al. (2017). Pyramid scene parsing network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2881\u20132890.","DOI":"10.1109\/CVPR.2017.660"},{"key":"2088_CR46","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Zhang, R., & Chen, C., et\u00a0al. (2022). Towards language-free training for text-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 17907\u201317917.","DOI":"10.1109\/CVPR52688.2022.01738"},{"key":"2088_CR47","doi-asserted-by":"crossref","unstructured":"Zhu, M., Pan, P., & Chen, W., et\u00a0al. (2019). Dm-gan: Dynamic memory generative adversarial networks for text-to-image synthesis. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5802\u20135810.","DOI":"10.1109\/CVPR.2019.00595"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02088-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02088-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02088-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,4]],"date-time":"2024-10-04T06:23:56Z","timestamp":1728023036000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02088-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,21]]},"references-count":47,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2024,10]]}},"alternative-id":["2088"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02088-6","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,21]]},"assertion":[{"value":"14 July 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 April 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 May 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}