{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T15:40:16Z","timestamp":1783698016909,"version":"3.55.0"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031736353","type":"print"},{"value":"9783031736360","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,5]],"date-time":"2024-11-05T00:00:00Z","timestamp":1730764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,5]],"date-time":"2024-11-05T00:00:00Z","timestamp":1730764800000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-73636-0_20","type":"book-chapter","created":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T15:06:32Z","timestamp":1730732792000},"page":"340-356","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["StableDrag: Stable Dragging for\u00a0Point-Based Image Editing"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4788-9751","authenticated-orcid":false,"given":"Yutao","family":"Cui","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5009-459X","authenticated-orcid":false,"given":"Xiaotong","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guozhen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9342-1837","authenticated-orcid":false,"given":"Shengming","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2805-3692","authenticated-orcid":false,"given":"Kai","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3674-7718","authenticated-orcid":false,"given":"Limin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,5]]},"reference":[{"key":"20_CR1","doi-asserted-by":"crossref","unstructured":"Abdal, R., Qin, Y., Wonka, P.: Image2stylegan: how to embed images into the stylegan latent space? In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4432\u20134441 (2019)","DOI":"10.1109\/ICCV.2019.00453"},{"issue":"3","key":"20_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3447648","volume":"40","author":"R Abdal","year":"2021","unstructured":"Abdal, R., Zhu, P., Mitra, N.J., Wonka, P.: Styleflow: attribute-conditioned exploration of stylegan-generated images using conditional continuous normalizing flows. ACM Trans. Graph. (ToG) 40(3), 1\u201321 (2021)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"20_CR3","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1007\/978-3-031-19784-0_41","volume-title":"ECCV 2022","author":"O Bar-Tal","year":"2022","unstructured":"Bar-Tal, O., Ofri-Amar, D., Fridman, R., Kasten, Y., Dekel, T.: Text2live: text-driven layered image and video editing. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13675, pp. 707\u2013723. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19784-0_41"},{"key":"20_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1007\/978-3-319-48881-3_56","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"L Bertinetto","year":"2016","unstructured":"Bertinetto, L., Valmadre, J., Henriques, J.F., Vedaldi, A., Torr, P.H.S.: Fully-convolutional siamese networks for object tracking. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 850\u2013865. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-48881-3_56"},{"key":"20_CR5","doi-asserted-by":"crossref","unstructured":"Bolme, D.S., Beveridge, J.R., Draper, B.A., Lui, Y.M.: Visual object tracking using adaptive correlation filters. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2010)","DOI":"10.1109\/CVPR.2010.5539960"},{"key":"20_CR6","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, pp. 18392\u201318402 (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"20_CR7","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. arXiv preprint arXiv:2304.08465 (2023)","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"20_CR8","doi-asserted-by":"crossref","unstructured":"Chen, X., Yan, B., Zhu, J., Wang, D., Yang, X., Lu, H.: Transformer tracking. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00803"},{"issue":"7","key":"20_CR9","doi-asserted-by":"publisher","first-page":"1967","DOI":"10.1109\/TNNLS.2018.2875194","volume":"30","author":"A Creswell","year":"2018","unstructured":"Creswell, A., Bharath, A.A.: Inverting the generator of a generative adversarial network. IEEE Trans. Neural Netw. Learn. Syst. 30(7), 1967\u20131974 (2018)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"Cui, Y., Jiang, C., Wang, L., Wu, G.: Mixformer: end-to-end tracking with iterative mixed attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"20_CR11","unstructured":"Cui, Y., Song, T., Wu, G., Wang, L.: Mixformerv2: efficient fully transformer tracking. In: Advances in Neural Information Processing Systems (2023)"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Bhat, G., Khan, F.S., Felsberg, M.: ATOM: accurate tracking by overlap maximization. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00479"},{"key":"20_CR13","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: NeurIPS (2021)"},{"key":"20_CR14","doi-asserted-by":"crossref","unstructured":"Endo, Y.: User-controllable latent transformer for stylegan image layout editing. arXiv preprint arXiv:2208.12408 (2022)","DOI":"10.1111\/cgf.14686"},{"key":"20_CR15","unstructured":"Epstein, D., Jabri, A., Poole, B., Efros, A.A., Holynski, A.: Diffusion self-guidance for controllable image generation. arXiv preprint arXiv:2306.00986 (2023)"},{"key":"20_CR16","unstructured":"Esser, P., Rombach, R., Blattmann, A., Ommer, B.: ImageBART: bidirectional context with multinomial diffusion for autoregressive image synthesis. In: NeurIPS (2021)"},{"key":"20_CR17","unstructured":"Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion. In: ICLR (2023)"},{"key":"20_CR18","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N., Weinberger, K. (eds.) Advances in Neural Information Processing Systems, vol.\u00a027. Curran Associates, Inc. (2014). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2014\/file\/5ca3e9b122f61f8f06494c97b1afccf3-Paper.pdf"},{"key":"20_CR19","unstructured":"Goodfellow, I.J., et al.: Generative adversarial nets. In: NeurIPS (2014)"},{"key":"20_CR20","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"},{"issue":"3","key":"20_CR21","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1109\/TPAMI.2014.2345390","volume":"37","author":"JF Henriques","year":"2015","unstructured":"Henriques, J.F., Caseiro, R., Martins, P., Batista, J.: High-speed tracking with kernelized correlation filters. IEEE Trans. Pattern Anal. Mach. Intell. 37(3), 583\u2013596 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"20_CR22","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-Or, D.: Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626 (2022)"},{"key":"20_CR23","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)"},{"key":"20_CR24","unstructured":"Karras, T., et al.: Alias-free generative adversarial networks. In: NeurIPS (2021)"},{"key":"20_CR25","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"20_CR26","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: 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 (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"20_CR27","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of StyleGAN. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"20_CR28","doi-asserted-by":"crossref","unstructured":"Kawar, B., et al.: Imagic: text-based real image editing with diffusion models. arXiv preprint arXiv:2210.09276 (2022)","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"20_CR29","doi-asserted-by":"crossref","unstructured":"Kawar, B., 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":"20_CR30","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"20_CR31","doi-asserted-by":"crossref","unstructured":"Kumari, N., Zhang, B., Zhang, R., Shechtman, E., Zhu, J.Y.: Multi-concept customization of text-to-image diffusion. arXiv preprint arXiv:2212.04488 (2022)","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"20_CR32","doi-asserted-by":"crossref","unstructured":"Leimk\u00fchler, T., Drettakis, G.: Freestylegan: free-view editable portrait rendering with the camera manifold. arXiv preprint arXiv:2109.09378 (2021)","DOI":"10.1145\/3478513.3480538"},{"key":"20_CR33","doi-asserted-by":"crossref","unstructured":"Li, B., Wu, W., Wang, Q., Zhang, F., Xing, J., Yan, J.: Siamrpn++: evolution of siamese visual tracking with very deep networks. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2019)","DOI":"10.1109\/CVPR.2019.00441"},{"key":"20_CR34","doi-asserted-by":"crossref","unstructured":"Li, B., Yan, J., Wu, W., Zhu, Z., Hu, X.: High performance visual tracking with siamese region proposal network. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2018)","DOI":"10.1109\/CVPR.2018.00935"},{"key":"20_CR35","unstructured":"Liew, J.H., Yan, H., Zhou, D., Feng, J.: Magicmix: semantic mixing with diffusion models. arXiv preprint arXiv:2210.16056 (2022)"},{"key":"20_CR36","unstructured":"Ling, P., Chen, L., Zhang, P., Chen, H., Jin, Y.: Freedrag: point tracking is not you need for interactive point-based image editing. arXiv preprint arXiv:2307.04684 (2023)"},{"key":"20_CR37","unstructured":"Lipton, Z.C., Tripathi, S.: Precise recovery of latent vectors from generative adversarial networks. arXiv preprint arXiv:1702.04782 (2017)"},{"key":"20_CR38","doi-asserted-by":"crossref","unstructured":"Mao, J., Wang, X., Aizawa, K.: Guided image synthesis via initial image editing in diffusion model. arXiv preprint arXiv:2305.03382 (2023)","DOI":"10.1145\/3581783.3612191"},{"key":"20_CR39","unstructured":"Meng, C., et al.: Sdedit: guided image synthesis and editing with stochastic differential equations. arXiv preprint arXiv:2108.01073 (2021)"},{"key":"20_CR40","unstructured":"Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)"},{"key":"20_CR41","unstructured":"Mou, C., Wang, X., Song, J., Shan, Y., Zhang, J.: Dragondiffusion: enabling drag-style manipulation on diffusion models. arXiv preprint arXiv:2307.02421 (2023)"},{"key":"20_CR42","unstructured":"Nichol, A., et al.: GLIDE: towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)"},{"key":"20_CR43","doi-asserted-by":"crossref","unstructured":"Pan, X., Tewari, A., Leimk\u00fchler, T., Liu, L., Meka, A., Theobalt, C.: Drag your GAN: interactive point-based manipulation on the generative image manifold. arXiv preprint arXiv:2305.10973 (2023)","DOI":"10.1145\/3588432.3591500"},{"key":"20_CR44","doi-asserted-by":"crossref","unstructured":"Parmar, G., Singh, K.K., Zhang, R., Li, Y., Lu, J., Zhu, J.Y.: Zero-shot image-to-image translation. arXiv preprint arXiv:2302.03027 (2023)","DOI":"10.1145\/3588432.3591513"},{"key":"20_CR45","doi-asserted-by":"crossref","unstructured":"Patashnik, O., Wu, Z., Shechtman, E., Cohen-Or, D., Lischinski, D.: Styleclip: text-driven manipulation of stylegan imagery. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2085\u20132094 (2021)","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"20_CR46","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with CLIP latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"20_CR47","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: 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":"20_CR48","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":"20_CR49","unstructured":"Saharia, C., et\u00a0al.: Photorealistic text-to-image diffusion models with deep language understanding. arXiv preprint arXiv:2205.11487 (2022)"},{"key":"20_CR50","doi-asserted-by":"crossref","unstructured":"Shi, Y., Xue, C., Pan, J., Zhang, W., Tan, V.Y., Bai, S.: Dragdiffusion: harnessing diffusion models for interactive point-based image editing. arXiv preprint arXiv:2306.14435 (2023)","DOI":"10.1109\/CVPR52733.2024.00844"},{"key":"20_CR51","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1921\u20131930 (2023)","DOI":"10.1109\/CVPR52729.2023.00191"},{"issue":"4","key":"20_CR52","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530087","volume":"41","author":"SY Wang","year":"2022","unstructured":"Wang, S.Y., Bau, D., Zhu, J.Y.: Rewriting geometric rules of a GAN. ACM Trans. Graph. (TOG) 41(4), 1\u201316 (2022)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"20_CR53","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1007\/978-3-319-46454-1_36","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J-Y Zhu","year":"2016","unstructured":"Zhu, J.-Y., Kr\u00e4henb\u00fchl, P., Shechtman, E., Efros, A.A.: Generative visual manipulation on the natural image manifold. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016 Part V. LNCS, vol. 9909, pp. 597\u2013613. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_36"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73636-0_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T10:52:51Z","timestamp":1765018371000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73636-0_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,5]]},"ISBN":["9783031736353","9783031736360"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73636-0_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,5]]},"assertion":[{"value":"5 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}