{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:12:26Z","timestamp":1778051546715,"version":"3.51.4"},"reference-count":65,"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\/wacv61042.2026.00104","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"1000-1010","source":"Crossref","is-referenced-by-count":0,"title":["Beyond the Encoder: Joint Encoder-Decoder Contrastive Pre-Training Improves Dense Prediction"],"prefix":"10.1109","author":[{"given":"S\u00e9bastien","family":"Quetin","sequence":"first","affiliation":[{"name":"McGill University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tapotosh","family":"Ghosh","sequence":"additional","affiliation":[{"name":"University of Calgary,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Farhad","family":"Maleki","sequence":"additional","affiliation":[{"name":"University of Calgary,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"ref2","article-title":"Beit: Bert pre-training of image transformers","author":"Bao","year":"2021"},{"key":"ref3","article-title":"Vicreg: Variance-invariance-covariance regularization for self-supervised learning","volume-title":"ICLR","author":"Bardes"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0640"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00462"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02178"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101539"},{"key":"ref9","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020"},{"key":"ref10","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2018.8363547"},{"key":"ref14","article-title":"MMSegmentation: Openmmlab semantic segmentation toolbox and benchmark","year":"2020"},{"key":"ref15","article-title":"MMSelfSup: Openmmlab self-supervised learning toolbox and benchmark","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00165"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25130"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref22","article-title":"Soft neighbors are positive supporters in contrastive visual representation learning","author":"Ge","year":"2023"},{"key":"ref23","article-title":"Unsupervised representation learning by predicting image rotations","author":"Gidaris","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_8"},{"key":"ref28","author":"Hinton","year":"2015","journal-title":"Distilling the knowledge in a neural network"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02181"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-01008-z"},{"key":"ref31","article-title":"Layer Grafted Pre-training: Bridging Contrastive Learning And Masked Image Modeling For Label-Efficient Representations","author":"Jiang","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00149"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-022-10919-1"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref38","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref40","first-page":"4489","article-title":"Unsupervised learning of dense visual representations","volume-title":"Advances in Neural Information Processing Systems","author":"Pinheiro","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101570"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00180"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref44","article-title":"Mind your augmentation: The key to decoupling dense self-supervised learning","volume-title":"The Twelfth International Conference on Learning Representations","author":"Qiu"},{"key":"ref45","article-title":"Transfusion: Understanding transfer learning for medical imaging","volume-title":"Advances in Neural Information Processing Systems","author":"Raghu","year":"2019"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00941"},{"key":"ref47","article-title":"Detecting diseases dataset","year":"2022"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3371158.3371196"},{"issue":"56","key":"ref50","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298664"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_29"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00304"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-025-06513-4"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1195"},{"key":"ref56","article-title":"Detectron2","author":"Wu","year":"2019"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01448"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref59","first-page":"28864","article-title":"Unsupervised object-level representation learning from scene images","volume-title":"Advances in Neural Information Processing Systems","author":"Xie","year":"2021"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01641"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"ref65","first-page":"3833","article-title":"Rethinking pre-training and self-training","volume-title":"Advances in Neural Information Processing Systems","author":"Zoph","year":"2020"}],"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\/11492330.pdf?arnumber=11492330","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:17:12Z","timestamp":1778048232000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492330\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00104","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}