{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T22:52:00Z","timestamp":1770331920066,"version":"3.49.0"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729973","type":"print"},{"value":"9783031729980","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"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\/978-3-031-72998-0_6","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T18:01:58Z","timestamp":1727632918000},"page":"91-108","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Object-Centric Diffusion for\u00a0Efficient Video Editing"],"prefix":"10.1007","author":[{"given":"Kumara","family":"Kahatapitiya","sequence":"first","affiliation":[]},{"given":"Adil","family":"Karjauv","sequence":"additional","affiliation":[]},{"given":"Davide","family":"Abati","sequence":"additional","affiliation":[]},{"given":"Fatih","family":"Porikli","sequence":"additional","affiliation":[]},{"given":"Yuki M.","family":"Asano","sequence":"additional","affiliation":[]},{"given":"Amirhossein","family":"Habibian","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"6_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592450","volume":"42","author":"O Avrahami","year":"2023","unstructured":"Avrahami, O., Fried, O., Lischinski, D.: Blended latent diffusion. ACM Trans. Graph. (TOG) 42, 1\u201311 (2023)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Blattmann, A., et al.: Align your latents: high-resolution video synthesis with latent diffusion models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"6_CR3","unstructured":"Bolya, D., Fu, C.Y., Dai, X., Zhang, P., Feichtenhofer, C., Hoffman, J.: Token merging: your ViT but faster. International Conference on Learning Representations (2023)"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Bolya, D., Hoffman, J.: Token merging for fast stable diffusion. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPRW59228.2023.00484"},{"key":"6_CR5","unstructured":"Chen, W., et al.: Control-a-video: controllable text-to-video generation with diffusion models. arXiv preprint arXiv:2305.13840 (2023)"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Esser, P., Chiu, J., Atighehchian, P., Granskog, J., Germanidis, A.: Structure and content-guided video synthesis with diffusion models. In: IEEE International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"6_CR7","unstructured":"Geyer, M., Bar-Tal, O., Bagon, S., Dekel, T.: TokenFlow: consistent diffusion features for consistent video editing. In: International Conference on Learning Representations (2024)"},{"key":"6_CR8","first-page":"139","volume":"63","author":"I Goodfellow","year":"2014","unstructured":"Goodfellow, I., et al.: Generative adversarial networks. Neural Inf. Process. Syst. 63, 139\u2013144 (2014)","journal-title":"Neural Inf. Process. Syst."},{"key":"6_CR9","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-Or, D.: Prompt-to-prompt image editing with cross attention control. In: International Conference on Learning Representations (2023)"},{"key":"6_CR10","unstructured":"Ho, J., et\u00a0al.: Imagen video: High definition video generation with diffusion models. arXiv preprint arXiv:2210.02303 (2022)"},{"key":"6_CR11","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Neural Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Neural Inf. Process. Syst."},{"key":"6_CR12","first-page":"1","volume":"23","author":"J Ho","year":"2022","unstructured":"Ho, J., Saharia, C., Chan, W., Fleet, D.J., Norouzi, M., Salimans, T.: Cascaded diffusion models for high fidelity image generation. J. Mach. Learn. Res. 23, 1\u201333 (2022)","journal-title":"J. Mach. Learn. Res."},{"key":"6_CR13","first-page":"8633","volume":"35","author":"J Ho","year":"2022","unstructured":"Ho, J., Salimans, T., Gritsenko, A., Chan, W., Norouzi, M., Fleet, D.J.: Video diffusion models. Neural Inf. Process. Syst. 35, 8633\u20138646 (2022)","journal-title":"Neural Inf. Process. Syst."},{"key":"6_CR14","unstructured":"Hong, W., Ding, M., Zheng, W., Liu, X., Tang, J.: CogVideo: large-scale pretraining for text-to-video generation via transformers. In: International Conference on Learning Representations (2023)"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Khachatryan, L., et al.: Text2Video-zero: text-to-image diffusion models are zero-shot video generators. In: IEEE International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"6_CR16","unstructured":"Kim, B.K., Song, H.K., Castells, T., Choi, S.: On architectural compression of text-to-image diffusion models. arXiv preprint arXiv:2305.15798 (2023)"},{"key":"6_CR17","unstructured":"Kim, D., et al.: Consistency trajectory models: Learning probability flow ode trajectory of diffusion. In: International Conference on Learning Representations (2024)"},{"key":"6_CR18","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: International Conference on Learning Representations (2014)"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. In: IEEE International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"6_CR20","first-page":"28858","volume":"35","author":"M Li","year":"2022","unstructured":"Li, M., Lin, J., Meng, C., Ermon, S., Han, S., Zhu, J.Y.: Efficient spatially sparse inference for conditional GANs and diffusion models. Neural Inf. Process. Syst. 35, 28858\u201328873 (2022)","journal-title":"Neural Inf. Process. Syst."},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Li, X., Ma, C., Yang, X., Yang, M.H.: VidToMe: video token merging for zero-shot video editing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2024)","DOI":"10.1109\/CVPR52733.2024.00715"},{"key":"6_CR22","unstructured":"Li, Y., et al.: SnapFusion: text-to-image diffusion model on mobile devices within two seconds. Neural Inf. Process. Syst. (2023)"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Liu, S., Zhang, Y., Li, W., Lin, Z., Jia, J.: Video-P2P: video editing with cross-attention control. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2024)","DOI":"10.1109\/CVPR52733.2024.00821"},{"key":"6_CR24","first-page":"5775","volume":"35","author":"C Lu","year":"2022","unstructured":"Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., Zhu, J.: DPM-solver: a fast ode solver for diffusion probabilistic model sampling in around 10 steps. Neural Inf. Process. Syst. 35, 5775\u20135787 (2022)","journal-title":"Neural Inf. Process. Syst."},{"key":"6_CR25","unstructured":"Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., Zhu, J.: DPM-solver++: fast solver for guided sampling of diffusion probabilistic models. arXiv preprint arXiv:2211.01095 (2022)"},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Meng, C., et al.: On distillation of guided diffusion models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"6_CR27","unstructured":"Microsoft deepspeed. https:\/\/github.com\/microsoft\/DeepSpeed"},{"key":"6_CR28","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. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"6_CR29","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: IEEE International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"6_CR30","unstructured":"Pont-Tuset, J., Perazzi, F., Caelles, S., Arbel\u00e1ez, P., Sorkine-Hornung, A., Van Gool, L.: The 2017 DAVIS challenge on video object segmentation. arXiv:1704.00675 (2017)"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Qi, C., et al.: FateZero: fusing attentions for zero-shot text-based video editing. In: IEEE International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"6_CR32","doi-asserted-by":"publisher","first-page":"107404","DOI":"10.1016\/j.patcog.2020.107404","volume":"106","author":"X Qin","year":"2020","unstructured":"Qin, X., Zhang, Z., Huang, C., Dehghan, M., Zaiane, O.R., Jagersand, M.: U2-net: going deeper with nested U-structure for salient object detection. Pattern Recogn. 106, 107404 (2020)","journal-title":"Pattern Recogn."},{"key":"6_CR33","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1109\/TPAMI.2020.3019967","volume":"44","author":"R Ranftl","year":"2020","unstructured":"Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., Koltun, V.: Towards robust monocular depth estimation: mixing datasets for zero-shot cross-dataset transfer. IEEE Trans. Pattern Anal. Mach. Intell. 44, 1623\u20131637 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_CR34","unstructured":"Ren, T., et\u00a0al.: Grounded SAM: assembling open-world models for diverse visual tasks. arXiv preprint arXiv:2401.14159 (2024)"},{"key":"6_CR35","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 conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"6_CR36","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 \u2013 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":"6_CR37","unstructured":"Salimans, T., Ho, J.: Progressive distillation for fast sampling of diffusion models. In: International Conference on Learning Representations (2022)"},{"key":"6_CR38","first-page":"25278","volume":"35","author":"C Schuhmann","year":"2022","unstructured":"Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models. Neural Inf. Process. Syst. 35, 25278\u201325294 (2022)","journal-title":"Neural Inf. Process. Syst."},{"key":"6_CR39","unstructured":"Singer, U., et\u00a0al.: Make-a-video: text-to-video generation without text-video data. In: International Conference on Learning Representations (2023)"},{"key":"6_CR40","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: International Conference on Learning Representations (2021)"},{"key":"6_CR41","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 conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"6_CR42","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: IEEE International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"6_CR43","unstructured":"Yun, Y.K., Lin, W.: Self-reformer: self-refined network with transformer for salient object detection. IEEE Trans. Multimed. (2023)"},{"key":"6_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: IEEE International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"6_CR45","unstructured":"Zhang, Y., Wei, Y., Jiang, D., Zhang, X., Zuo, W., Tian, Q.: ControlVideo: training-free controllable text-to-video generation. In: International Conference on Learning Representations (2024)"},{"key":"6_CR46","unstructured":"Zhou, D., Wang, W., Yan, H., Lv, W., Zhu, Y., Feng, J.: MagicVideo: efficient video generation with latent diffusion models. arXiv preprint arXiv:2211.11018 (2022)"}],"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\/978-3-031-72998-0_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T18:03:16Z","timestamp":1727632996000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72998-0_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031729973","9783031729980"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72998-0_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"30 September 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"}}]}}