{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T11:15:07Z","timestamp":1742987707897,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819756148"},{"type":"electronic","value":"9789819756155"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-5615-5_5","type":"book-chapter","created":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T13:12:02Z","timestamp":1722604322000},"page":"54-65","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Controlling Attention Map Better for Text-Guided Image Editing Diffusion Models"],"prefix":"10.1007","author":[{"given":"Siqi","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lijun","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanming","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihua","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,3]]},"reference":[{"key":"5_CR1","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: Marina, M., Tong, Z. (eds.) Proceedings of the 38th International Conference on Machine Learning, vol. 139, pp. 8821\u20138831. PMLR (2021)"},{"key":"5_CR2","unstructured":"Nichol, A., Dhariwal, P., Ramesh, A., Shyam, P., Mishkin, P., McGrew, B., et al.: GLIDE: towards photorealistic image generation and editing with text-guided diffusion models"},{"key":"5_CR3","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical Text-Conditional Image Generation with CLIP Latents"},{"key":"5_CR4","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. In: Annual Conference on Neural Information Processing Systems 2022, Advances in Neural Information Processing Systems, vol. 35. NeurIPS (2022)"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: IEEE\/CVF International Conference on Computer Vision, ICCV, pp. 3813\u20133824 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"5_CR7","unstructured":"Qin, C., Zhang, S., Yu, N., Feng, Y., Yang, X., Zhou, Y., et al.: Unicontrol: a unified diffusion model for controllable visual generation in the wild. In: Annual Conference on Neural Information Processing Systems 2023, Advances in Neural Information Processing Systems, vol. 36. NeurIPS (2023)"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Mou, C., Wang, X., Xie, L., Zhang, J., Qi, Z., Shan, Y., et al.: T2I-Adapter: learning adapters to dig out more controllable ability for text-to-image diffusion models (2023)","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"5_CR9","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., et al.: In: Annual Conference on Neural Information Processing Systems, Attention is all you need. Advances in Neural Information Processing Systems, vol. 30, pp. 5998\u20136008 (2017)"},{"key":"5_CR10","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: 9th International Conference on Learning Representations. ICLR (2021)"},{"key":"5_CR11","unstructured":"Ju, X., Zeng, A., Bian, Y., Liu, S., Xu, Q.: Direct inversion: boosting diffusion-based editing with 3 lines of code (2023)"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Cao, M., Wang, X., Qi, Z., Shan, Y., Qie, X., Zheng, Y.: MasaCtrl: tuning-free mutual self-attention control for consistent image synthesis and editing. In: IEEE\/CVF International Conference on Computer Vision, ICCV. pp. 22503\u201322513 (2023)","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"5_CR13","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-Or, D.: Prompt-to-prompt image editing with cross-attention control. In: The Eleventh International Conference on Learning Representations. ICLR (2023)"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Tumanyan, N., Geyer, M., Bagon, S., Dekel, T.: Plug-and-play diffusion features for text-driven image-to-image translation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, pp. 1921\u20131930 (2023)","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"5_CR15","unstructured":"Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems, pp. 2672\u20132680 (2014)"},{"key":"5_CR16","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. In: 7th International Conference on Learning Representations. ICLR (2019)"},{"issue":"12","key":"5_CR17","doi-asserted-by":"publisher","first-page":"4217","DOI":"10.1109\/TPAMI.2020.2970919","volume":"43","author":"T Karras","year":"2021","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. IEEE Trans. Pattern Anal. Mach. Intell. 43(12), 4217\u20134228 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"5_CR18","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: Proceedings of the 38th International Conference on Machine Learning, ICML. Proceedings of Machine Learning Research, vol. 139, pp. 8162\u20138171 (2021)"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Avrahami, O., Fried, O., Lischinski, D.: Blended latent diffusion. ACM Trans. Graph. 42(4), 149:1\u2013149:11 (2023)","DOI":"10.1145\/3592450"},{"key":"5_CR20","unstructured":"Mou, C., Wang, X., Song, J., Shan, Y., Zhang, J.: Dragondiffusion: enabling drag-style manipulation on diffusion models (2023)"},{"key":"5_CR21","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS (2020)"},{"key":"5_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2014 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"5_CR23","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: 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"issue":"4","key":"5_CR24","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"5_CR25","unstructured":"Wu, C., Huang, L., Zhang, Q., Li, B., Ji, L., Yang, F., et al.: GODIVA: generating open-domain videos from natural descriptions (2021)"},{"key":"5_CR26","unstructured":"Nichol, A.Q., Dhariwal, P., Ramesh, A., Shyam, P., Mishkin, P., McGrew, B., et al.: GLIDE: towards photorealistic image generation and editing with text-guided diffusion models. In: International Conference on Machine Learning, ICML. Proceedings of Machine Learning Research, vol. 162, pp. 16784\u201316804. PMLR (2022)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-5615-5_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T11:03:14Z","timestamp":1731150194000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-5615-5_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819756148","9789819756155"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-5615-5_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"3 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tianjin","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":"5 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2024\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}