{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:54:23Z","timestamp":1776887663003,"version":"3.51.2"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729911","type":"print"},{"value":"9783031729928","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:00:00Z","timestamp":1730246400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:00:00Z","timestamp":1730246400000},"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\/978-3-031-72992-8_11","type":"book-chapter","created":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T08:29:02Z","timestamp":1730190542000},"page":"183-199","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["DragVideo: Interactive Drag-Style Video Editing"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2899-3055","authenticated-orcid":false,"given":"Yufan","family":"Deng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1497-6914","authenticated-orcid":false,"given":"Ruida","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5137-1211","authenticated-orcid":false,"given":"Yuhao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3148-0380","authenticated-orcid":false,"given":"Yu-Wing","family":"Tai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7155-2919","authenticated-orcid":false,"given":"Chi-Keung","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,30]]},"reference":[{"key":"11_CR1","unstructured":"Bai, J., et al.: UniEdit: a unified tuning-free framework for video motion and appearance editing. arXiv preprint arXiv:2402.13185 (2024)"},{"key":"11_CR2","unstructured":"Brooks, T., et al.: Video generation models as world simulators (2024). https:\/\/openai.com\/research\/video-generation-models-as-world-simulators"},{"key":"11_CR3","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":"11_CR4","doi-asserted-by":"crossref","unstructured":"Ceylan, D., Huang, C.H.P., Mitra, N.J.: Pix2Video: video editing using image diffusion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 23206\u201323217 (2023)","DOI":"10.1109\/ICCV51070.2023.02121"},{"key":"11_CR5","unstructured":"Chen, W., et al.: Control-a-video: controllable text-to-video generation with diffusion models. arXiv preprint arXiv:2305.13840 (2023)"},{"key":"11_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1007\/978-3-031-19815-1_37","volume-title":"Computer Vision \u2013 ECCV 2022","author":"HK Cheng","year":"2022","unstructured":"Cheng, H.K., Schwing, A.G.: XMem: long-term video object segmentation with an Atkinson-Shiffrin memory model. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13688, pp. 640\u2013658. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_37"},{"key":"11_CR7","first-page":"13610","volume":"35","author":"C Doersch","year":"2022","unstructured":"Doersch, C., et al.: TAP-Vid: a benchmark for tracking any point in a video. Adv. Neural. Inf. Process. Syst. 35, 13610\u201313626 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR8","unstructured":"Guo, Y., et al.: AnimateDiff: animate your personalized text-to-image diffusion models without specific tuning. arXiv preprint arXiv:2307.04725 (2023)"},{"key":"11_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/978-3-031-20047-2_4","volume-title":"Computer Vision \u2013 ECCV 2022","author":"AW Harley","year":"2022","unstructured":"Harley, A.W., Fang, Z., Fragkiadaki, K.: Particle video revisited: tracking through occlusions using point trajectories. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13682, pp. 59\u201375. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_4"},{"key":"11_CR10","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR11","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"11_CR12","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Hu, J., Hui, K.H., Liu, Z., Zhang, H., Fu, C.W.: CNS-Edit: 3D shape editing via coupled neural shape optimization. arXiv preprint arXiv:2402.02313 (2024)","DOI":"10.1145\/3641519.3657412"},{"key":"11_CR14","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8110\u20138119 (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"11_CR15","doi-asserted-by":"crossref","unstructured":"Khachatryan, L., et al.: Text2Video-zero: text-to-image diffusion models are zero-shot video generators. arXiv preprint arXiv:2303.13439 (2023)","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"11_CR16","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"key":"11_CR17","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Mokady, R., Hertz, A., Aberman, K., Pritch, Y., Cohen-Or, D.: Null-text inversion for editing real images using guided diffusion models. arXiv preprint arXiv:2211.09794 (2022)","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"11_CR19","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":"11_CR20","doi-asserted-by":"crossref","unstructured":"Ouyang, H., et al.: CoDef: content deformation fields for temporally consistent video processing. arXiv preprint arXiv:2308.07926 (2023)","DOI":"10.1109\/CVPR52733.2024.00773"},{"key":"11_CR21","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. In: ACM SIGGRAPH 2023 Conference Proceedings, pp. 1\u201311 (2023)","DOI":"10.1145\/3588432.3591500"},{"key":"11_CR22","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"11_CR23","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":"11_CR24","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":"11_CR25","unstructured":"Shin, C., Kim, H., Lee, C.H., Lee, S.g., Yoon, S.: Edit-a-video: single video editing with object-aware consistency. arXiv preprint arXiv:2303.07945 (2023)"},{"key":"11_CR26","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"11_CR27","unstructured":"Tang, L., Jia, M., Wang, Q., Phoo, C.P., Hariharan, B.: Emergent correspondence from image diffusion. arXiv preprint arXiv:2306.03881 (2023)"},{"key":"11_CR28","unstructured":"Tanveer, M., Wang, Y., Wang, R., Zhao, N., Mahdavi-Amiri, A., Zhang, H.: AnaMoDiff: 2D analogical motion diffusion via disentangled denoising. arXiv preprint arXiv:2402.03549 (2024)"},{"key":"11_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1007\/978-3-030-58536-5_24","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Teed","year":"2020","unstructured":"Teed, Z., Deng, J.: RAFT: recurrent all-pairs field transforms for optical flow. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part II. LNCS, vol. 12347, pp. 402\u2013419. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_24"},{"key":"11_CR30","unstructured":"Unterthiner, T., Van\u00a0Steenkiste, S., Kurach, K., Marinier, R., Michalski, M., Gelly, S.: Towards accurate generative models of video: a new metric & challenges. arXiv preprint arXiv:1812.01717 (2018)"},{"key":"11_CR31","doi-asserted-by":"crossref","unstructured":"Wang, Q., et al.: Tracking everything everywhere all at once. arXiv preprint arXiv:2306.05422 (2023)","DOI":"10.1109\/ICCV51070.2023.01813"},{"key":"11_CR32","unstructured":"Wang, X., et al.: VideoComposer: compositional video synthesis with motion controllability. arXiv preprint arXiv:2306.02018 (2023)"},{"key":"11_CR33","doi-asserted-by":"crossref","unstructured":"Wu, J.Z., et al.: Tune-a-video: one-shot tuning of image diffusion models for text-to-video generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7623\u20137633 (2023)","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"11_CR34","unstructured":"Yang, J., Gao, M., Li, Z., Gao, S., Wang, F., Zheng, F.: Track anything: segment anything meets videos. arXiv preprint arXiv:2304.11968 (2023)"},{"key":"11_CR35","doi-asserted-by":"crossref","unstructured":"Yang, S., Zhou, Y., Liu, Z., Loy, C.C.: Rerender a video: zero-shot text-guided video-to-video translation. arXiv preprint arXiv:2306.07954 (2023)","DOI":"10.1145\/3610548.3618160"},{"key":"11_CR36","unstructured":"Zhang, Y., Wei, Y., Jiang, D., Zhang, X., Zuo, W., Tian, Q.: ControlVideo: training-free controllable text-to-video generation. arXiv preprint arXiv:2305.13077 (2023)"}],"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\/978-3-031-72992-8_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T12:04:40Z","timestamp":1732968280000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72992-8_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,30]]},"ISBN":["9783031729911","9783031729928"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72992-8_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,30]]},"assertion":[{"value":"30 October 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"}}]}}