{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:11:26Z","timestamp":1778051486399,"version":"3.51.4"},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00568","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"5864-5874","source":"Crossref","is-referenced-by-count":0,"title":["brat : Aligned Multi-View Embeddings for Brain MRI Analysis"],"prefix":"10.1109","author":[{"given":"Maxime","family":"Kayser","sequence":"first","affiliation":[{"name":"Memorial Sloan Kettering Cancer Center,New York,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maksim","family":"Gridnev","sequence":"additional","affiliation":[{"name":"Memorial Sloan Kettering Cancer Center,New York,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wanting","family":"Wang","sequence":"additional","affiliation":[{"name":"Memorial Sloan Kettering Cancer Center,New York,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Max","family":"Bain","sequence":"additional","affiliation":[{"name":"University of Oxford,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aneesh","family":"Rangnekar","sequence":"additional","affiliation":[{"name":"Memorial Sloan Kettering Cancer Center,New York,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Avijit","family":"Chatterjee","sequence":"additional","affiliation":[{"name":"Memorial Sloan Kettering Cancer Center,New York,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aleksandr","family":"Petrov","sequence":"additional","affiliation":[{"name":"Memorial Sloan Kettering Cancer Center,New York,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Harini","family":"Veeraraghavan","sequence":"additional","affiliation":[{"name":"Memorial Sloan Kettering Cancer Center,New York,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nathaniel C.","family":"Swinburne","sequence":"additional","affiliation":[{"name":"Memorial Sloan Kettering Cancer Center,New York,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","article-title":"The rsna-asnr-miccai brats 2021 benchmark on brain tumor segmentation and radiogenomic classification","author":"Baid","year":"2021"},{"key":"ref3","article-title":"BEiT: BERT pre-training of image transformers","volume-title":"International Conference on Learning Representations","author":"Bao"},{"key":"ref4","article-title":"Vi- creg: Variance-invariance-covariance regularization for self- supervised learning","volume-title":"10th International Conference on Learning Representations, ICLR 2022","author":"Bardes"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101797"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-024-02514-2"},{"key":"ref7","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International Conference on Machine Learning","author":"Chen"},{"key":"ref8","article-title":"Pali: A jointly- scaled multilingual language-image model","volume-title":"International Conference on Learning Representations","author":"Chen"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72120-5_12"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w19-4828"},{"key":"ref12","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72114-4_47"},{"key":"ref18","article-title":"Perceiver: General perception with iterative attention","volume-title":"International Conference on Machine Learning","author":"Jaegle"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16440-8_53"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01958"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1445"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1561\/9781601986290"},{"key":"ref26","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International Conference on Machine Learning","author":"Li"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107677"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.891"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.59275\/j.melba.2025-9bd3"},{"key":"ref30","article-title":"Amaes: Augmented masked autoencoder pretraining on public brain mri data for 3d-native segmentation","author":"Munk","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.669"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.21"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0b013e3181cb3e25"},{"key":"ref35","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.272"},{"key":"ref37","article-title":"Streaming active learning with deep neural networks","volume-title":"International Conference on Machine Learning","author":"Saran"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref39","article-title":"Eva-clip: Improved training techniques for clip at scale","author":"Sun","year":"2023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02007"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2430"},{"key":"ref43","article-title":"Git: A generative image-to-text transformer for vision and language","author":"Wang","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"key":"ref44","article-title":"Vision-language modelling for radiological imaging and reports in the low data regime","author":"Windsor","year":"2023","journal-title":"Medical Imaging with Deep Learning"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01954"},{"key":"ref46","article-title":"Feasibility and benefits of joint learning from mri databases with different brain diseases and modalities for segmentation","author":"Xu","year":"2024","journal-title":"Medical Imaging with Deep Learning"},{"key":"ref47","article-title":"Advancing multimodal medical capabilities of gemini","author":"Yang","year":"2024"},{"key":"ref48","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","volume-title":"International conference on machine learning","author":"Zbontar"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.414"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-40260-7"},{"key":"ref52","article-title":"Contrastive learning of medical visual representations from paired images and text","volume-title":"Machine Learning for Healthcare Conference","author":"Zhang"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492327.pdf?arnumber=11492327","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:13:23Z","timestamp":1778048003000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492327\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00568","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}