{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T10:30:12Z","timestamp":1766485812448,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031703805"},{"type":"electronic","value":"9783031703812"}],"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\/978-3-031-70381-2_21","type":"book-chapter","created":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T10:01:54Z","timestamp":1725184914000},"page":"332-347","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["DiffSynth: Latent In-Iteration Deflickering for\u00a0Realistic Video Synthesis"],"prefix":"10.1007","author":[{"given":"Zhongjie","family":"Duan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lizhou","family":"You","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cen","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziheng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weining","family":"Qian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,22]]},"reference":[{"issue":"3","key":"21_CR1","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1145\/1531326.1531330","volume":"28","author":"C Barnes","year":"2009","unstructured":"Barnes, C., Shechtman, E., Finkelstein, A., Goldman, D.B.: PatchMatch: a randomized correspondence algorithm for structural image editing. ACM Trans. Graph. 28(3), 24 (2009)","journal-title":"ACM Trans. Graph."},{"key":"21_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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22563\u201322575 (2023)","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"21_CR3","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2D pose estimation using part affinity fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7291\u20137299 (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"Ceylan, D., Huang, C.H.P., Mitra, N.J.: Pix2video: video editing using image diffusion. arXiv preprint arXiv:2303.12688 (2023)","DOI":"10.1109\/ICCV51070.2023.02121"},{"key":"21_CR5","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. Adv. Neural. Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_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. arXiv preprint arXiv:2302.03011 (2023)","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Feng, Z., et\u00a0al.: ERNIE-ViLG 2.0: improving text-to-image diffusion model with knowledge-enhanced mixture-of-denoising-experts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10135\u201310145 (2023)","DOI":"10.1109\/CVPR52729.2023.00977"},{"key":"21_CR8","unstructured":"Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"21_CR9","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/j.neucom.2021.12.104","volume":"476","author":"S Han","year":"2022","unstructured":"Han, S., Huang, P., Wang, H., Yu, E., Liu, D., Pan, X.: MAT: motion-aware multi-object tracking. Neurocomputing 476, 75\u201386 (2022)","journal-title":"Neurocomputing"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"21_CR11","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"21_CR12","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. In: NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications (2021)"},{"key":"21_CR13","unstructured":"Hu, E.J., et\u00a0al.: LoRA: low-rank adaptation of large language models. In: International Conference on Learning Representations (2021)"},{"issue":"4","key":"21_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3306346.3323006","volume":"38","author":"O Jamri\u0161ka","year":"2019","unstructured":"Jamri\u0161ka, O., et al.: Stylizing video by example. ACM Transactions on Graphics (TOG) 38(4), 1\u201311 (2019)","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Karras, J., Holynski, A., Wang, T.C., Kemelmacher-Shlizerman, I.: DreamPose: fashion image-to-video synthesis via stable diffusion. arXiv preprint arXiv:2304.06025 (2023)","DOI":"10.1109\/ICCV51070.2023.02073"},{"key":"21_CR16","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":"21_CR17","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. In: International Conference on Learning Representations (2013)"},{"key":"21_CR18","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Lei, C., Ren, X., Zhang, Z., Chen, Q.: Blind video deflickering by neural filtering with a flawed atlas. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10439\u201310448 (2023)","DOI":"10.1109\/CVPR52729.2023.01006"},{"issue":"6","key":"21_CR20","doi-asserted-by":"publisher","first-page":"669","DOI":"10.1063\/1.4822961","volume":"4","author":"WH Press","year":"1990","unstructured":"Press, W.H., Teukolsky, S.A.: Savitzky-Golay smoothing filters. Comput. Phys. 4(6), 669\u2013672 (1990)","journal-title":"Comput. Phys."},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Qi, C., et al.: FateZero: fusing attentions for zero-shot text-based video editing. arXiv preprint arXiv:2303.09535 (2023)","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"21_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":"21_CR23","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":"21_CR24","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":"21_CR25","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: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III","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.) Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III, pp. 234\u2013241. Springer International Publishing, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"21_CR26","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: DreamBooth: fine tuning text-to-image diffusion models for subject-driven generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22500\u201322510 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"21_CR27","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR28","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. Adv. Neural. Inf. Process. Syst. 35, 25278\u201325294 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR29","unstructured":"Singer, U., et\u00a0al.: Make-a-Video: text-to-video generation without text-video data. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"21_CR30","unstructured":"Song, Y., Ermon, S.: Generative modeling by estimating gradients of the data distribution. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"21_CR31","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1007\/978-3-030-58536-5_24","volume-title":"Computer Vision \u2013 ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part II","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.) Computer Vision \u2013 ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part II, pp. 402\u2013419. Springer International Publishing, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_24"},{"key":"21_CR32","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"21_CR33","unstructured":"Witteveen, S., Andrews, M.: Investigating prompt engineering in diffusion models. arXiv preprint arXiv:2211.15462 (2022)"},{"key":"21_CR34","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. arXiv preprint arXiv:2212.11565 (2022)","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"21_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":"21_CR36","unstructured":"Yu, S., et al.: Generating videos with dynamics-aware implicit generative adversarial networks. In: International Conference on Learning Representations (2021)"},{"key":"21_CR37","unstructured":"Zablotskaia, P., Siarohin, A., Zhao, B., Sigal, L.: DwNet: dense warp-based network for pose-guided human video generation. arXiv preprint arXiv:1910.09139 (2019)"},{"key":"21_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, L., Agrawala, M.: Adding conditional control to text-to-image diffusion models. arXiv preprint arXiv:2302.05543 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70381-2_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T10:11:32Z","timestamp":1725185492000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70381-2_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031703805","9783031703812"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70381-2_21","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":"22 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vilnius","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lithuania","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":"8 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2024.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}