{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:18:28Z","timestamp":1778048308239,"version":"3.51.4"},"reference-count":32,"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\/wacv61042.2026.00131","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"1284-1293","source":"Crossref","is-referenced-by-count":0,"title":["MARS: a Multimodal Alignment and Ranking System for Few-Shot Segmentation"],"prefix":"10.1109","author":[{"given":"Nico","family":"Catalano","sequence":"first","affiliation":[{"name":"Politecnico di Milano"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefano","family":"Samele","sequence":"additional","affiliation":[{"name":"Politecnico di Milano"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paolo","family":"Pertino","sequence":"additional","affiliation":[{"name":"Politecnico di Milano"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matteo","family":"Matteucci","sequence":"additional","affiliation":[{"name":"Politecnico di Milano"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01227"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref3","article-title":"Vision transformers need registers","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024","author":"Darcet"},{"key":"ref4","first-page":"79","article-title":"Few-shot semantic segmentation with prototype learning","volume-title":"British Machine Vision Conference 2018, BMVC 2018, Newcastle, UK, September 3-6, 2018","author":"Dong"},{"key":"ref5","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021","author":"Dosovitskiy"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_20"},{"key":"ref7","article-title":"Deep residual learning for image recognition","volume":"abs\/1512.03385","author":"He","year":"2015","journal-title":"CoRR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00294"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01469"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01469"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_9"},{"key":"ref14","article-title":"Matcher: Segment anything with one shot using all-purpose feature matching","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024","author":"Liu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref16","article-title":"Hyper-correlation squeeze for few-shot segmentation","volume":"abs\/2104.01538","author":"Min","year":"2021","journal-title":"CoRR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00071"},{"key":"ref18","article-title":"Dinov2: Learning robust visual features without supervision","volume":"2024","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref19","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event","author":"Radford"},{"key":"ref20","article-title":"Conditional networks for fewshot semantic segmentation","volume-title":"6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Workshop Track Proceedings","author":"Rakelly"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.167"},{"key":"ref22","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings","author":"Simonyan"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02224"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01237"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00057"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00378"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00110"},{"key":"ref28","article-title":"Unlocking the power of sam 2 for few-shot segmentation","volume-title":"Proceedings of the 42nd International Conference on Machine Learning, ICML 2025","author":"Xu"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1047"},{"key":"ref31","article-title":"Personalize segment anything model with one shot","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024","author":"Zhang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2992433"}],"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\/11492068.pdf?arnumber=11492068","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:53:49Z","timestamp":1778046829000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492068\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00131","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}