{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T02:35:28Z","timestamp":1777084528742,"version":"3.51.4"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,14]],"date-time":"2025-04-14T00:00:00Z","timestamp":1744588800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,14]],"date-time":"2025-04-14T00:00:00Z","timestamp":1744588800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,14]]},"DOI":"10.1109\/isbi60581.2025.10981288","type":"proceedings-article","created":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T17:38:51Z","timestamp":1747071531000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["CSMAE : Cataract Surgical Masked Autoencoder (MAE) Based Pre-Training"],"prefix":"10.1109","author":[{"given":"Nisarg A.","family":"Shah","sequence":"first","affiliation":[{"name":"Johns Hopkins University,Baltimore,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaminda","family":"Bandara","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Baltimore,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shameema","family":"Sikder","sequence":"additional","affiliation":[{"name":"Wilmer Eye Institute, Johns Hopkins University,Baltimore,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S. Swaroop","family":"Vedula","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Malone Center for Engineering in Healthcare,Baltimore,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vishal M.","family":"Patel","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Baltimore,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43907-0_34"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43987-2_44"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_1"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3207502"},{"key":"ref5","article-title":"Glsformer: Gated-long, short sequence transformer for step recognition in surgical videos","author":"Nisarg","year":"2023","journal-title":"MICCAI"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00784"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01430"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref9","first-page":"10078","article-title":"Videomae: Masked autoencoders are data-efficient learn-ers for self-supervised video pretraining","volume":"35","author":"Tong","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref10","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01394"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"ref14","article-title":"Towards device efficient conditional image generation","author":"Shah","year":"2022","journal-title":"arXiv preprint"},{"key":"ref15","first-page":"35946","article-title":"Masked autoencoders as spatiotemporal learners","volume":"35","author":"Feichtenhofer","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2017.2787657"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32254-0_50"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59716-0_33"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3069471"},{"key":"ref21","first-page":"593","article-title":"Trans-svnet: Accurate phase recog-nition from surgical videos via hybrid embedding aggre-gation transformer","volume-title":"MICCAI 2021","author":"Gao","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/bf00992696"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3204949.3208137"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2019.1860"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2593957"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-019-01956-8"}],"event":{"name":"2025 IEEE 22nd International Symposium on Biomedical Imaging (ISBI)","location":"Houston, TX, USA","start":{"date-parts":[[2025,4,14]]},"end":{"date-parts":[[2025,4,17]]}},"container-title":["2025 IEEE 22nd International Symposium on Biomedical Imaging (ISBI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10980665\/10980666\/10981288.pdf?arnumber=10981288","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T06:40:10Z","timestamp":1747118410000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10981288\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,14]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/isbi60581.2025.10981288","relation":{},"subject":[],"published":{"date-parts":[[2025,4,14]]}}}