{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T11:26:53Z","timestamp":1783423613869,"version":"3.54.6"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032051400","type":"print"},{"value":"9783032051417","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T00:00:00Z","timestamp":1758326400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T00:00:00Z","timestamp":1758326400000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-05141-7_40","type":"book-chapter","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:17:34Z","timestamp":1758269854000},"page":"412-422","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Mission Balance: Generating Under-Represented Class Samples Using Video Diffusion Models"],"prefix":"10.1007","author":[{"given":"Danush Kumar","family":"Venkatesh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Isabel","family":"Funke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Micha","family":"Pfeiffer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fiona","family":"Kolbinger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanna Maria","family":"Schmeiser","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marius","family":"Distler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J\u00fcrgen","family":"Weitz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefanie","family":"Speidel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,20]]},"reference":[{"key":"40_CR1","unstructured":"Alaa, A., Van\u00a0Breugel, B., Saveliev, E.S., van\u00a0der Schaar, M.: How faithful is your synthetic data? Sample-level metrics for evaluating and auditing generative models. In: International Conference on Machine Learning, pp. 290\u2013306. PMLR (2022)"},{"key":"40_CR2","unstructured":"Azizi, S., Kornblith, S., Saharia, C., Norouzi, M., Fleet, D.J.: Synthetic data from diffusion models improves ImageNet classification. TMLR (2023)"},{"key":"40_CR3","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":"40_CR4","unstructured":"Cho, J., et al.: SurGen: text-guided diffusion model for surgical video generation. arXiv preprint arXiv:2408.14028 (2024)"},{"key":"40_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":"40_CR6","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C.: X3D: expanding architectures for efficient video recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 203\u2013213 (2020)","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"40_CR7","doi-asserted-by":"crossref","unstructured":"Frisch, Y., et al.: Synthesising rare cataract surgery samples with guided diffusion models. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 354\u2013364. Springer (2023)","DOI":"10.1007\/978-3-031-43996-4_34"},{"key":"40_CR8","unstructured":"Guo, Y., et al.: AnimateDiff: animate your personalized text-to-image diffusion models without specific tuning. In: International Conference on Learning Representations (2024)"},{"key":"40_CR9","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., Satoh, Y.: Can spatiotemporal 3D CNNs retrace the history of 2D CNNs and ImageNet? In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6546\u20136555 (2018)","DOI":"10.1109\/CVPR.2018.00685"},{"key":"40_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":"40_CR11","unstructured":"He, Y., Yang, T., Zhang, Y., Shan, Y., Chen, Q.: Latent video diffusion models for high-fidelity long video generation. arXiv preprint arXiv:2211.13221 (2022)"},{"key":"40_CR12","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. NeruIPS 35, 8633\u20138646 (2022)","journal-title":"NeruIPS"},{"issue":"8","key":"40_CR13","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"40_CR14","doi-asserted-by":"crossref","unstructured":"Iliash, I., Allmendinger, S., Meissen, F., K\u00fchl, N., R\u00fcckert, D.: Interactive generation of laparoscopic videos with diffusion models. In: MICCAI Workshop on Deep Generative Models, pp. 109\u2013118. Springer (2024)","DOI":"10.1007\/978-3-031-72744-3_11"},{"key":"40_CR15","doi-asserted-by":"crossref","unstructured":"Jayasumana, S., Ramalingam, S., Veit, A., Glasner, D., Chakrabarti, A., Kumar, S.: Rethinking FID: towards a better evaluation metric for image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9307\u20139315 (2024)","DOI":"10.1109\/CVPR52733.2024.00889"},{"issue":"3","key":"40_CR16","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1007\/s11548-023-03030-w","volume":"19","author":"J Kaleta","year":"2024","unstructured":"Kaleta, J., Dall\u2019Alba, D., P\u0142otka, S., Korzeniowski, P.: Minimal data requirement for realistic endoscopic image generation with stable diffusion. Int. J. Comput. Assist. Radiol. Surg. 19(3), 531\u2013539 (2024)","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"40_CR17","doi-asserted-by":"crossref","unstructured":"Li, C., et al.: Endora: video generation models as endoscopy simulators. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 230\u2013240. Springer (2024)","DOI":"10.1007\/978-3-031-72089-5_22"},{"key":"40_CR18","doi-asserted-by":"publisher","first-page":"102306","DOI":"10.1016\/j.media.2021.102306","volume":"76","author":"L Maier-Hein","year":"2022","unstructured":"Maier-Hein, L., et al.: Surgical data science-from concepts toward clinical translation. Med. Image Anal. 76, 102306 (2022)","journal-title":"Med. Image Anal."},{"key":"40_CR19","doi-asserted-by":"crossref","unstructured":"Martyniak, S., et al.: SimuScope: realistic endoscopic synthetic dataset generation through surgical simulation and diffusion models. In: Proceedings of the Winter Conference on Applications of Computer Vision (WACV), pp. 4268\u20134278 (2025)","DOI":"10.1109\/WACV61041.2025.00419"},{"key":"40_CR20","unstructured":"Naeem, M.F., Oh, S.J., Uh, Y., Choi, Y., Yoo, J.: Reliable fidelity and diversity metrics for generative models. In: ICML, pp. 7176\u20137185. PMLR (2020)"},{"key":"40_CR21","doi-asserted-by":"crossref","unstructured":"Parmar, G., Zhang, R., Zhu, J.Y.: On aliased resizing and surprising subtleties in GAN evaluation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11410\u201311420 (2022)","DOI":"10.1109\/CVPR52688.2022.01112"},{"key":"40_CR22","unstructured":"Psychogyios, D., et\u00a0al.: SAR-RARP50: segmentation of surgical instrumentation and action recognition on robot-assisted radical prostatectomy challenge. arXiv preprint arXiv:2401.00496 (2023)"},{"key":"40_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":"40_CR24","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 234\u2013241. Springer (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"40_CR25","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"40_CR26","unstructured":"Venkatesh, D.K., et al.: Exploring semantic consistency in unpaired image translation to generate data for surgical applications. Int. J. Comput. Assist. Radiol. Surg.\u00a01\u20139 (2024)"},{"key":"40_CR27","doi-asserted-by":"crossref","unstructured":"Venkatesh, D.K., Rivoir, D., Pfeiffer, M., Kolbinger, F., Speidel, S.: Data augmentation for surgical scene segmentation with anatomy-aware diffusion models. In: Proceedings of the Winter Conference on Applications of Computer Vision (WACV), pp. 2280\u20132290 (2025)","DOI":"10.1109\/WACV61041.2025.00228"},{"key":"40_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"40_CR29","doi-asserted-by":"publisher","first-page":"941","DOI":"10.1007\/s00464-020-07912-x","volume":"35","author":"G Zimmitti","year":"2021","unstructured":"Zimmitti, G., et al.: Investigation of intraoperative factors associated with postoperative pancreatic fistula following laparoscopic left pancreatectomy with stapled closure: a video review-based analysis. Surg. Endosc. 35, 941\u2013954 (2021)","journal-title":"Surg. Endosc."}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-05141-7_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:17:47Z","timestamp":1758269867000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-05141-7_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,20]]},"ISBN":["9783032051400","9783032051417"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-05141-7_40","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,20]]},"assertion":[{"value":"20 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests."}},{"value":"MICCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Medical Image Computing and Computer-Assisted Intervention","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}