{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T20:26:35Z","timestamp":1793651195328,"version":"4.5.1"},"reference-count":92,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T00:00:00Z","timestamp":1769990400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100006920","name":"University of Pennsylvania","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006920","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100005405","name":"American Surgical Association","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100005405","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Medical Image Analysis"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1016\/j.media.2026.103972","type":"journal-article","created":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T16:42:00Z","timestamp":1770136920000},"page":"103972","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":3,"special_numbering":"C","title":["Slot-BERT: Self-supervised object discovery in surgical video"],"prefix":"10.1016","volume":"110","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0921-178X","authenticated-orcid":false,"given":"Guiqiu","family":"Liao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3771-3146","authenticated-orcid":false,"given":"Matja\u017e","family":"Jogan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5147-8026","authenticated-orcid":false,"given":"Marcel","family":"Hussing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3740-9577","authenticated-orcid":false,"given":"Kenta","family":"Nakahashi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3053-4156","authenticated-orcid":false,"given":"Kazuhiro","family":"Yasufuku","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0901-9851","authenticated-orcid":false,"given":"Amin","family":"Madani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5689-2234","authenticated-orcid":false,"given":"Eric","family":"Eaton","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4725-3104","authenticated-orcid":false,"given":"Daniel A.","family":"Hashimoto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.media.2026.103972_bib0001","series-title":"2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, October 10\u201317, 2021","first-page":"6816","article-title":"Vivit: a video vision transformer","author":"Arnab","year":"2021"},{"key":"10.1016\/j.media.2026.103972_bib0002","series-title":"European Conference on Computer Vision","first-page":"456","article-title":"Masked siamese networks for label-efficient learning","author":"Assran","year":"2022"},{"key":"10.1016\/j.media.2026.103972_bib0003","series-title":"Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10\u201316, 2023","article-title":"Self-supervised object-centric learning for videos","author":"Aydemir","year":"2023"},{"key":"10.1016\/j.media.2026.103972_bib0004","series-title":"The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25\u201329, 2022","article-title":"Beit: BERT pre-training of image transformers","author":"Bao","year":"2022"},{"key":"10.1016\/j.media.2026.103972_bib0005","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18\u201324, 2022","first-page":"11779","article-title":"Discovering objects that can move","author":"Bao","year":"2022"},{"key":"10.1016\/j.media.2026.103972_bib0006","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17\u201324, 2023","first-page":"22972","article-title":"Object discovery from motion-guided tokens","author":"Bao","year":"2023"},{"key":"10.1016\/j.media.2026.103972_bib0007","series-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, June 27\u201330, 2016","first-page":"2846","article-title":"Weakly supervised deep detection networks","author":"Bilen","year":"2016"},{"key":"10.1016\/j.media.2026.103972_bib0008","series-title":"International Conference on Machine Learning, ICML 2023, 23\u201329 July 2023, Honolulu, Hawaii, USA","first-page":"2507","article-title":"Invariant slot attention: object discovery with slot-centric reference frames","volume":"Vol. 202","author":"Biza","year":"2023"},{"key":"10.1016\/j.media.2026.103972_bib0009","article-title":"Monet: unsupervised scene decomposition and representation","volume":"abs\/1901.11390","author":"Burgess","year":"2019","journal-title":"ArXiv preprint"},{"key":"10.1016\/j.media.2026.103972_bib0010","series-title":"2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, October 10\u201317, 2021","first-page":"9630","article-title":"Emerging properties in self-supervised vision transformers","author":"Caron","year":"2021"},{"key":"10.1016\/j.media.2026.103972_bib0011","series-title":"Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13\u201318 July 2020, Virtual Event","first-page":"1691","article-title":"Generative pretraining from pixels","volume":"Vol. 119","author":"Chen","year":"2020"},{"key":"10.1016\/j.media.2026.103972_bib0012","series-title":"Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13\u201318 July 2020, Virtual Event","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume":"Vol. 119","author":"Chen","year":"2020"},{"key":"10.1016\/j.media.2026.103972_bib0013","series-title":"2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, October 10\u201317, 2021","first-page":"9620","article-title":"An empirical study of training self-supervised vision transformers","author":"Chen","year":"2021"},{"key":"10.1016\/j.media.2026.103972_bib0014","series-title":"IEEE\/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, October 1\u20136, 2023","first-page":"1316","article-title":"Tracking anything with decoupled video segmentation","author":"Cheng","year":"2023"},{"key":"10.1016\/j.media.2026.103972_bib0015","series-title":"33rd British Machine Vision Conference 2022, BMVC 2022, London, UK, November 21\u201324, 2022","first-page":"554","article-title":"Guess what moves: unsupervised video and image segmentation by anticipating motion","author":"Choudhury","year":"2022"},{"key":"10.1016\/j.media.2026.103972_bib0016","doi-asserted-by":"crossref","first-page":"1279","DOI":"10.1007\/s11263-019-01183-3","article-title":"Unsupervised learning of foreground object segmentation","volume":"127","author":"Croitoru","year":"2019","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.media.2026.103972_bib0017","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.media.2026.103972_bib0018","series-title":"International Conference on Learning Representations (ICLR)","article-title":"On the transfer of object-centric representation learning","author":"Didolkar","year":"2025"},{"key":"10.1016\/j.media.2026.103972_bib0019","first-page":"552","article-title":"Peco: perceptual codebook for BERT pre-training of vision transformers","author":"Dong","year":"2023"},{"key":"10.1016\/j.media.2026.103972_bib0020","series-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3\u20137, 2021","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"10.1016\/j.media.2026.103972_bib0021","series-title":"6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30- May 3, 2018, Conference Track Proceedings","article-title":"A framework for the quantitative evaluation of disentangled representations","author":"Eastwood","year":"2018"},{"key":"10.1016\/j.media.2026.103972_bib0022","series-title":"Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28-December 9, 2022","article-title":"Savi++: towards end-to-end object-centric learning from real-world videos","author":"Elsayed","year":"2022"},{"key":"10.1016\/j.media.2026.103972_bib0023","series-title":"8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26\u201330, 2020","article-title":"GENESIS: Generative scene inference and sampling with object-centric latent representations","author":"Engelcke","year":"2020"},{"key":"10.1016\/j.media.2026.103972_bib0024","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"23062","article-title":"Adaptive slot attention: object discovery with dynamic slot number","author":"Fan","year":"2024"},{"key":"10.1016\/j.media.2026.103972_bib0025","series-title":"IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA, June 7\u201312, 2015","first-page":"4083","article-title":"Learning to segment moving objects in videos","author":"Fragkiadaki","year":"2015"},{"key":"10.1016\/j.media.2026.103972_bib0026","series-title":"Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9\u201315 June 2019, Long Beach, California, USA","first-page":"2424","article-title":"Multi-object representation learning with iterative variational inference","volume":"Vol. 97","author":"Greff","year":"2019"},{"key":"10.1016\/j.media.2026.103972_bib0027","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"3749","article-title":"Kubric: a scalable dataset generator","author":"Greff","year":"2022"},{"key":"10.1016\/j.media.2026.103972_bib0028","article-title":"On the binding problem in artificial neural networks","volume":"abs\/2012.05208","author":"Greff","year":"2020","journal-title":"ArXiv preprint"},{"key":"10.1016\/j.media.2026.103972_bib0029","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18\u201324, 2022","first-page":"15979","article-title":"Masked autoencoders are scalable vision learners","author":"He","year":"2022"},{"key":"10.1016\/j.media.2026.103972_bib0030","series-title":"European Conference on Computer Vision","first-page":"123","article-title":"Object discovery and representation networks","author":"H\u00e9naff","year":"2022"},{"key":"10.1016\/j.media.2026.103972_bib0031","series-title":"5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24\u201326, 2017, Conference Track Proceedings","article-title":"Beta-VAE: learning basic visual concepts with a constrained variational framework","author":"Higgins","year":"2017"},{"key":"10.1016\/j.media.2026.103972_bib0032","series-title":"6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30- May 3, 2018, Conference Track Proceedings","article-title":"Matrix capsules with EM routing","author":"Hinton","year":"2018"},{"key":"10.1016\/j.media.2026.103972_bib0033","article-title":"Cholecseg8k: a semantic segmentation dataset for laparoscopic cholecystectomy based on cholec80","volume":"abs\/2012.12453","author":"Hong","year":"2020","journal-title":"ArXiv preprint"},{"key":"10.1016\/j.media.2026.103972_bib0034","series-title":"Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, December 3\u20138, 2018, Montr\u00c9Al, Canada","first-page":"547","article-title":"Self-erasing network for integral object attention","author":"Hou","year":"2018"},{"issue":"5","key":"10.1016\/j.media.2026.103972_bib0035","doi-asserted-by":"crossref","first-page":"5456","DOI":"10.1109\/TITS.2023.3243643","article-title":"Sat3d: slot attention transformer for 3d point cloud semantic segmentation","volume":"24","author":"Ibrahim","year":"2023","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.media.2026.103972_bib0036","series-title":"Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10\u201316, 2023","article-title":"Object-centric slot diffusion","author":"Jiang","year":"2023"},{"issue":"2","key":"10.1016\/j.media.2026.103972_bib0037","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1016\/0010-0285(92)90007-O","article-title":"The reviewing of object files: object-specific integration of information","volume":"24","author":"Kahneman","year":"1992","journal-title":"Cogn. Psychol."},{"key":"10.1016\/j.media.2026.103972_bib0038","series-title":"Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28- December 9, 2022","article-title":"Unsupervised multi-object segmentation by predicting probable motion patterns","author":"Karazija","year":"2022"},{"key":"10.1016\/j.media.2026.103972_bib0039","series-title":"Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4san, Stockholm, Sweden, July 10\u201315, 2018","first-page":"2654","article-title":"Disentangling by factorising","volume":"Vol. 80","author":"Kim","year":"2018"},{"key":"10.1016\/j.media.2026.103972_bib0040","series-title":"2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14\u201316, 2014, Conference Track Proceedings","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2014"},{"key":"10.1016\/j.media.2026.103972_bib0041","series-title":"The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25\u201329, 2022","article-title":"Conditional object-centric learning from video","author":"Kipf","year":"2022"},{"key":"10.1016\/j.media.2026.103972_bib0042","series-title":"8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26\u201330, 2020","article-title":"Contrastive learning of structured world models","author":"Kipf","year":"2020"},{"key":"10.1016\/j.media.2026.103972_bib0043","series-title":"Advances in Neural Information Processing Systems (NeurIPS 2024), Vancouver, Canada, December 10\u201315, 2024","article-title":"Identifiable object-centric representation learning via probabilistic slot attention","author":"Kori","year":"2024"},{"key":"10.1016\/j.media.2026.103972_bib0044","series-title":"8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26\u201330, 2020","article-title":"Structured object-aware physics prediction for video modeling and planning","author":"Kossen","year":"2020"},{"key":"10.1016\/j.media.2026.103972_bib0045","series-title":"IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16\u201320, 2019","first-page":"5267","article-title":"Ficklenet: weakly and semi-supervised semantic image segmentation using stochastic inference","author":"Lee","year":"2019"},{"key":"10.1016\/j.media.2026.103972_bib0046","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3807","article-title":"Guided slot attention for unsupervised video object segmentation","author":"Lee","year":"2024"},{"key":"10.1016\/j.media.2026.103972_bib0047","series-title":"2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","first-page":"8013","article-title":"Disentangling spatio-temporal knowledge for weakly supervised object detection and segmentation in surgical video","author":"Liao","year":"2025"},{"key":"10.1016\/j.media.2026.103972_bib0048","series-title":"8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26\u201330, 2020","article-title":"SPACE: unsupervised object-oriented scene representation via spatial attention and decomposition","author":"Lin","year":"2020"},{"key":"10.1016\/j.media.2026.103972_bib0049","series-title":"Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6\u201314, 2021, Virtual","first-page":"13137","article-title":"The emergence of objectness: learning zero-shot segmentation from videos","author":"Liu","year":"2021"},{"key":"10.1016\/j.media.2026.103972_bib0050","series-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6\u201312, 2020, Virtual","article-title":"Object-centric learning with slot attention","author":"Locatello","year":"2020"},{"issue":"428","key":"10.1016\/j.media.2026.103972_bib0051","article-title":"Complex-valued autoencoders for object discovery","author":"L\u00f6we","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"key":"10.1016\/j.media.2026.103972_bib0052","article-title":"Object-centric architectures enable efficient causal representation learning","volume":"abs\/2310.19054","author":"Mansouri","year":"2023","journal-title":"ArXiv preprint"},{"key":"10.1016\/j.media.2026.103972_bib0053","series-title":"Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9\u201315 June 2019, Long Beach, California, USA","first-page":"4402","article-title":"Disentangling disentanglement in variational autoencoders","volume":"Vol. 97","author":"Mathieu","year":"2019"},{"key":"10.1016\/j.media.2026.103972_bib0054","series-title":"CVPR","article-title":"Mot16: a benchmark for multi-object tracking","author":"Milan","year":"2016"},{"issue":"6","key":"10.1016\/j.media.2026.103972_bib0055","doi-asserted-by":"crossref","first-page":"1059","DOI":"10.1007\/s11548-019-01958-6","article-title":"Weakly supervised convolutional LSTM approach for tool tracking in laparoscopic videos","volume":"14","author":"Nwoye","year":"2019","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"10.1016\/j.media.2026.103972_bib0056","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"5892","article-title":"A simple and powerful global optimization for unsupervised video object segmentation","author":"Ponimatkin","year":"2023"},{"issue":"1","key":"10.1016\/j.media.2026.103972_bib0057","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1109\/TPAMI.2016.2537320","article-title":"Multiscale combinatorial grouping for image segmentation and object proposal generation","volume":"39","author":"Pont-Tuset","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.media.2026.103972_bib0058","series-title":"IEEE\/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, October 1\u20136, 2023","first-page":"16629","article-title":"Semantics meets temporal correspondence: self-supervised object-centric learning in videos","author":"Qian","year":"2023"},{"key":"10.1016\/j.media.2026.103972_bib0059","unstructured":"Radford, A., 2018. Improving language understanding by generative pre-training."},{"key":"10.1016\/j.media.2026.103972_bib0060","series-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18\u201324 July 2021, Virtual Event","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume":"Vol. 139","author":"Radford","year":"2021"},{"key":"10.1016\/j.media.2026.103972_bib0061","series-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18\u201324 July 2021, Virtual Event","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume":"Vol. 139","author":"Ramesh","year":"2021"},{"key":"10.1016\/j.media.2026.103972_bib0062","series-title":"European Conference on Computer Vision (ECCV)","article-title":"Performance measures and a data set for multi-target, multi-camera tracking","author":"Ristani","year":"2016"},{"key":"10.1016\/j.media.2026.103972_bib0063","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10684","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022"},{"key":"10.1016\/j.media.2026.103972_bib0064","series-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4\u20139, 2017, Long Beach, CA, USA","first-page":"3856","article-title":"Dynamic routing between capsules","author":"Sabour","year":"2017"},{"key":"10.1016\/j.media.2026.103972_bib0065","series-title":"Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28- December 9, 2022","article-title":"Object scene representation transformer","author":"Sajjadi","year":"2022"},{"key":"10.1016\/j.media.2026.103972_bib0066","series-title":"The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1\u20135, 2023","article-title":"Bridging the gap to real-world object-centric learning","author":"Seitzer","year":"2023"},{"key":"10.1016\/j.media.2026.103972_bib0067","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2023.102751","article-title":"Fun-sis: a fully unsupervised approach for surgical instrument segmentation","volume":"85","author":"Sestini","year":"2023","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2026.103972_bib0068","unstructured":"Sim\u00e9oni, O., Vo, H. V., Seitzer, M., Baldassarre, F., Oquab, M., Jose, C., Khalidov, V., Szafraniec, M., Yi, S., Ramamonjisoa, M., et al., 2025. Dinov3. arXiv preprint:2508.10104."},{"key":"10.1016\/j.media.2026.103972_bib0069","series-title":"Forty-first International Conference on Machine Learning","article-title":"Parallelized spatiotemporal slot binding for videos","author":"Singh","year":"2024"},{"key":"10.1016\/j.media.2026.103972_bib0070","series-title":"Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28-December 9, 2022","article-title":"Simple unsupervised object-centric learning for complex and naturalistic videos","author":"Singh","year":"2022"},{"key":"10.1016\/j.media.2026.103972_bib0071","series-title":"2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, October 10\u201317, 2021","first-page":"3591","article-title":"Rethinking transformer-based set prediction for object detection","author":"Sun","year":"2021"},{"issue":"6022","key":"10.1016\/j.media.2026.103972_bib0072","doi-asserted-by":"crossref","first-page":"1279","DOI":"10.1126\/science.1192788","article-title":"How to grow a mind: statistics, structure, and abstraction","volume":"331","author":"Tenenbaum","year":"2011","journal-title":"Science"},{"key":"10.1016\/j.media.2026.103972_bib0073","series-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, July 21\u201326, 2017","first-page":"531","article-title":"Learning motion patterns in videos","author":"Tokmakov","year":"2017"},{"key":"10.1016\/j.media.2026.103972_bib0074","series-title":"Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28- December 9, 2022","article-title":"VideoMAE: masked autoencoders are data-efficient learners for self-supervised video pre-training","author":"Tong","year":"2022"},{"key":"10.1016\/j.media.2026.103972_bib0075","series-title":"8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26\u201330, 2020","article-title":"Capsules with inverted dot-product attention routing","author":"Tsai","year":"2020"},{"issue":"1","key":"10.1016\/j.media.2026.103972_bib0076","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1109\/TMI.2016.2593957","article-title":"Endonet: a deep architecture for recognition tasks on laparoscopic videos","volume":"36","author":"Twinanda","year":"2016","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.media.2026.103972_bib0077","series-title":"Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10- 16, 2023","article-title":"From vit features to training-free video object segmentation via streaming-data mixture models","author":"Uziel","year":"2023"},{"key":"10.1016\/j.media.2026.103972_bib0078","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1016\/j.neunet.2020.07.007","article-title":"Investigating object compositionality in generative adversarial networks","volume":"130","author":"Van Steenkiste","year":"2020","journal-title":"Neural Netw."},{"key":"10.1016\/j.media.2026.103972_bib0079","series-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4\u20139, 2017, Long Beach, CA, USA","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.media.2026.103972_bib0080","article-title":"Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion","author":"Vincent","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.media.2026.103972_bib0081","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","article-title":"Bevt: bert pretraining of video transformers","author":"Wang","year":"2022"},{"key":"10.1016\/j.media.2026.103972_bib0082","article-title":"Spatial broadcast decoder: a simple architecture for learning disentangled representations in vaes","volume":"abs\/1901.07017","author":"Watters","year":"2019","journal-title":"ArXiv preprint"},{"key":"10.1016\/j.media.2026.103972_bib0083","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18\u201324, 2022","first-page":"14648","article-title":"Masked feature prediction for self-supervised visual pre-training","author":"Wei","year":"2022"},{"key":"10.1016\/j.media.2026.103972_bib0084","article-title":"Unmasking the inductive biases of unsupervised object representations for video sequences","volume":"abs\/2006.07034","author":"Weis","year":"2020","journal-title":"ArXiv preprint"},{"key":"10.1016\/j.media.2026.103972_bib0085","series-title":"The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1\u20135, 2023","article-title":"Slotformer: unsupervised visual dynamics simulation with object-centric models","author":"Wu","year":"2023"},{"key":"10.1016\/j.media.2026.103972_bib0086","series-title":"Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10-16, 2023","article-title":"Slotdiffusion: object-centric generative modeling with diffusion models","author":"Wu","year":"2023"},{"key":"10.1016\/j.media.2026.103972_bib0087","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"18134","article-title":"Groupvit: semantic segmentation emerges from text supervision","author":"Xu","year":"2022"},{"key":"10.1016\/j.media.2026.103972_bib0088","series-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","article-title":"Slot-VLM: object-event slots for video-language modeling","author":"Xu","year":"2024"},{"key":"10.1016\/j.media.2026.103972_bib0089","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"2012","article-title":"Youtube-VIS: a large-scale video instance segmentation benchmark","author":"Xu","year":"2019"},{"key":"10.1016\/j.media.2026.103972_bib0090","series-title":"Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10\u201316, 2023","article-title":"Object-centric learning for real-world videos by predicting temporal feature similarities","author":"Zadaianchuk","year":"2023"},{"key":"10.1016\/j.media.2026.103972_bib0091","first-page":"13066","article-title":"Motion-attentive transition for zero-shot video object segmentation","author":"Zhou","year":"2020"},{"key":"10.1016\/j.media.2026.103972_bib0092","unstructured":"Zia, A., Bhattacharyya, K., Liu, X., Berniker, M., Wang, Z., Nespolo, R., Kondo, S., Kasai, S., Hirasawa, K., Liu, B., et al., 2023. Surgical tool classification and localization: results and methods from the MICCAI 2022 surgtoolloc challenge. ArXiv preprint: 2305.07152."}],"container-title":["Medical Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841526000411?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841526000411?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T11:12:57Z","timestamp":1783422777000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1361841526000411"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":92,"alternative-id":["S1361841526000411"],"URL":"https:\/\/doi.org\/10.1016\/j.media.2026.103972","relation":{},"ISSN":["1361-8415"],"issn-type":[{"value":"1361-8415","type":"print"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Slot-BERT: Self-supervised object discovery in surgical video","name":"articletitle","label":"Article Title"},{"value":"Medical Image Analysis","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.media.2026.103972","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"103972"}}