{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:18:36Z","timestamp":1778048316815,"version":"3.51.4"},"reference-count":49,"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\/wacv61042.2026.00284","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"2901-2911","source":"Crossref","is-referenced-by-count":0,"title":["From Few-Shot to Zero-Shot Pallet Load Recognition: A Deployed Embedding-Based Vision System for Industrial Logistics"],"prefix":"10.1109","author":[{"given":"Juan Jes\u00fas","family":"Losada Del Olmo","sequence":"first","affiliation":[{"name":"University of Murcia,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emilio Pardo","family":"Ballesteros","sequence":"additional","affiliation":[{"name":"University of Murcia,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pedro E.","family":"L\u00f3pez-de-Teruel","sequence":"additional","affiliation":[{"name":"University of Murcia,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alberto","family":"Ruiz","sequence":"additional","affiliation":[{"name":"University of Murcia,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2022.108512"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_24"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-35990-4_27"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s00170-023-11098-6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-024-02533-w"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/URAI.2018.8441834"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00136"},{"key":"ref8","article-title":"Vision Transformers Need Registers","volume-title":"The Twelfth International Conference on Learning Representations","author":"Darcet"},{"key":"ref9","author":"Darcet","year":"2025","journal-title":"Cluster and Predict Latent Patches for Improved Masked Image Modeling"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00407"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-023-05199-8"},{"key":"ref12","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"International Conference on Learning Representations","author":"Gu"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02703"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02094"},{"key":"ref15","first-page":"38","article-title":"T-rex2: Towards generic object detection vianbsp; text-visual prompt synergy","volume-title":"Computer Vision \u2013 ECCV 2024: 18th European Conference, Milan, Italy, September 29\u2013October 4, 2024, Proceedings, Part XXXIII","author":"Jiang"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02319"},{"key":"ref17","article-title":"Industriallateralloads (revision 9e8e0e0)","author":"Jes\u00fas Losada del Olmo","year":"2025","journal-title":"Dataset, Hugging Face"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3010733"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00851"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/11569596_73"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00534"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/su14020790"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SOLI.2018.8476740"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/app13127320"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/app12083967"},{"key":"ref27","article-title":"DINOv2: Learning Robust Visual Features without Supervision","author":"Oquab","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref28","article-title":"Learning Transferable Visual Models From Natural Language Supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01187"},{"key":"ref30","author":"Ren","year":"2024","journal-title":"DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11554-024-01534-5"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1186\/s13640-024-00623-6"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0966-6_10"},{"key":"ref34","author":"Sim\u00e9oni","year":"2025","journal-title":"DINOv3"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2022.02.019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-01378-7_5"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636270"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2001.990517"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2022.12.285"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02280"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2021.3128208"},{"key":"ref42","article-title":"Frustratingly simple few-shot object detection","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Wang"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00967"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-66336-9_23"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00817"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2024.2316279"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.compind.2022.103628"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3390\/app122010331"}],"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\/11492154.pdf?arnumber=11492154","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:54:32Z","timestamp":1778046872000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492154\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00284","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}