{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T06:48:32Z","timestamp":1758350912324,"version":"3.44.0"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032051400"},{"type":"electronic","value":"9783032051417"}],"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_22","type":"book-chapter","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:18:53Z","timestamp":1758269933000},"page":"219-229","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Future Slot Prediction for\u00a0Unsupervised Object Discovery in\u00a0Surgical Video"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0921-178X","authenticated-orcid":false,"given":"Guiqiu","family":"Liao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3771-3146","authenticated-orcid":false,"given":"Matjaz","family":"Jogan","sequence":"additional","affiliation":[]},{"given":"Marcel","family":"Hussing","sequence":"additional","affiliation":[]},{"given":"Edward","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Eric","family":"Eaton","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4725-3104","authenticated-orcid":false,"given":"Daniel A.","family":"Hashimoto","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,20]]},"reference":[{"key":"22_CR1","unstructured":"Aydemir, G., Xie, W., G\u00fcney, F.: Self-supervised object-centric learning for videos. In: Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems, NeurIPS (2023)"},{"key":"22_CR2","unstructured":"Elsayed, G.F., Mahendran, A., van Steenkiste, S., Greff, K., Mozer, M.C., Kipf, T.: Savi++: towards end-to-end object-centric learning from real-world videos. In: Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems, NeurIPS (2022)"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Fan, K., et al.: Adaptive slot attention: Object discovery with dynamic slot number. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02176"},{"key":"22_CR4","unstructured":"Greff, K., et al.: Multi-object representation learning with iterative variational inference. In: Proceedings of the 36th International Conference on Machine Learning ICML. Proceedings of Machine Learning Research (2019)"},{"key":"22_CR5","unstructured":"Higgins, I., et al.: beta-VAE: learning basic visual concepts with a constrained variational framework. In: 5th International Conference on Learning Representations, ICLR (2017)"},{"key":"22_CR6","unstructured":"Hong, W.Y., Kao, C.L., Kuo, Y.H., Wang, J.R., Chang, W.L., Shih, C.S.: CholecSeg8k: a semantic segmentation dataset for laparoscopic cholecystectomy based on Cholec80. ArXiv preprint (2020)"},{"key":"22_CR7","unstructured":"Jiang, J., Deng, F., Singh, G., Ahn, S.: Object-centric slot diffusion. In: Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems, NeurIPS (2023)"},{"key":"22_CR8","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. In: 2nd International Conference on Learning Representations, ICLR (2014)"},{"key":"22_CR9","unstructured":"Kipf, T., et al.: Conditional object-centric learning from video. In: The Tenth International Conference on Learning Representations, ICLR (2022)"},{"key":"22_CR10","unstructured":"Kipf, T.N., van\u00a0der Pol, E., Welling, M.: Contrastive learning of structured world models. In: 8th International Conference on Learning Representations, ICLR (2020)"},{"key":"22_CR11","unstructured":"Liao, G., et al.: Slot-BERT: self-supervised object discovery in surgical video. ArXiv preprint (2025)"},{"key":"22_CR12","unstructured":"Locatello, F., et al.: Object-centric learning with slot attention. In: Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems, NeurIPS (2020)"},{"key":"22_CR13","unstructured":"Mansouri, A., Hartford, J.S., Zhang, Y., Bengio, Y.: Object centric architectures enable efficient causal representation learning. In: The Twelfth International Conference on Learning Representations, ICLR (2024)"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Pont-Tuset, J., Arbelaez, P., Barron, J.T., Marques, F., Malik, J.: Multiscale combinatorial grouping for image segmentation and object proposal generation. IEEE Transactions on Pattern Analysis and Machine Intelligence (1) (2016)","DOI":"10.1109\/TPAMI.2016.2537320"},{"key":"22_CR15","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et\u00a0al.: Language models are unsupervised multitask learners. OpenAI blog (8) (2019)"},{"key":"22_CR16","unstructured":"Sabour, S., Frosst, N., Hinton, G.E.: Dynamic routing between capsules. In: Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems (2017)"},{"key":"22_CR17","unstructured":"Seitzer, M., et al.: Bridging the gap to real-world object-centric learning. In: The Eleventh International Conference on Learning Representations, ICLR (2023)"},{"key":"22_CR18","unstructured":"Singh, G., et al.: Parallelized spatiotemporal slot binding for videos. In: Forty-first International Conference on Machine Learning, ICML (2024)"},{"key":"22_CR19","unstructured":"Singh, G., Wu, Y., Ahn, S.: Simple unsupervised object-centric learning for complex and naturalistic videos. In: Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems, NeurIPS (2022)"},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Twinanda, A.P., Shehata, S., Mutter, D., Marescaux, J., De\u00a0Mathelin, M., Padoy, N.: EndoNet: a deep architecture for recognition tasks on laparoscopic videos. IEEE Trans. Med. Imag. (1) (2016)","DOI":"10.1109\/TMI.2016.2593957"},{"key":"22_CR21","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems, NeurIPS (2017)"},{"key":"22_CR22","unstructured":"Watters, N., Matthey, L., Burgess, C.P., Lerchner, A.: Spatial broadcast decoder: a simple architecture for learning disentangled representations in VAEs. ArXiv preprint (2019)"},{"key":"22_CR23","unstructured":"Wu, Z., Hu, J., Lu, W., Gilitschenski, I., Garg, A.: SlotDiffusion: object-centric generative modeling with diffusion models. In: Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems, NeurIPS (2023)"},{"key":"22_CR24","unstructured":"Zadaianchuk, A., Seitzer, M., Martius, G.: Object-centric learning for real-world videos by predicting temporal feature similarities. In: Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems, NeurIPS (2023)"},{"key":"22_CR25","doi-asserted-by":"crossref","unstructured":"Zhao, Z., et al.: Object-centric multiple object tracking. In: IEEE\/CVF International Conference on Computer Vision, ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01522"},{"key":"22_CR26","unstructured":"Zia, A., et\u00a0al.: Surgical tool classification and localization: results and methods from the MICCAI 2022 SurgToolLoc challenge. ArXiv preprint (2023)"}],"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_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:19:07Z","timestamp":1758269947000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-05141-7_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,20]]},"ISBN":["9783032051400","9783032051417"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-05141-7_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"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\u00a0that 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"}}]}}