{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T17:03:24Z","timestamp":1774631004394,"version":"3.50.1"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"European Union through European Regional Development Fund within the Scientific Center of Excellence for Data Science and Advanced Cooperative Systems"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3532745","type":"journal-article","created":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T18:57:45Z","timestamp":1737572265000},"page":"16824-16837","source":"Crossref","is-referenced-by-count":2,"title":["Context-Aware Fine-Grained Product Recognition on Grocery Shelves"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/linproxy.fan.workers.dev:443\/https\/orcid.org\/0000-0003-2146-7067","authenticated-orcid":false,"given":"Lovre","family":"Antonio Budimir","sequence":"first","affiliation":[{"name":"Faculty of Electrical Engineering and Computing, University of Zagreb, Zagreb, Croatia"}]},{"ORCID":"https:\/\/linproxy.fan.workers.dev:443\/https\/orcid.org\/0000-0001-8918-9070","authenticated-orcid":false,"given":"Zoran","family":"Kalafati\u0107","sequence":"additional","affiliation":[{"name":"Faculty of Electrical Engineering and Computing, University of Zagreb, Zagreb, Croatia"}]},{"ORCID":"https:\/\/linproxy.fan.workers.dev:443\/https\/orcid.org\/0000-0002-4321-4557","authenticated-orcid":false,"given":"Marko","family":"Suba\u0161i\u0107","sequence":"additional","affiliation":[{"name":"Faculty of Electrical Engineering and Computing, University of Zagreb, Zagreb, Croatia"}]},{"ORCID":"https:\/\/linproxy.fan.workers.dev:443\/https\/orcid.org\/0000-0002-4857-5351","authenticated-orcid":false,"given":"Sven","family":"Lon\u010dari\u0107","sequence":"additional","affiliation":[{"name":"Faculty of Electrical Engineering and Computing, University of Zagreb, Zagreb, Croatia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2019.03.005"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.108452"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2010.5543576"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68560-1_61"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref6","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref7","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383486"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2022.104571"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/8875910"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.109"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-05148-3"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s12161-022-02384-2"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.jretai.2004.01.006"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10142-3"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2921994"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2023.103646"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108257"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IPAS.2018.8708890"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10223137"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/KST57286.2023.10086714"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10605-2_29"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5220\/0011725100003417"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2019.102865"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IVMSPW.2016.7528213"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124635"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP51287.2024.10647477"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00552"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2822810"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3087709"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240522"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1023\/b:visi.0000029664.99615.94"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33765-9_9"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/11744023_32"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref36","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. 3rd Int. Conf. Learn. Represent.","author":"Simonyan"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_38"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2019.12.023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-50347-5_8"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2019.03.005"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-15633-1"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-024-01549-9"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3400844"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ESTIMedia.2015.7351774"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/MASSP.1986.1165342"},{"key":"ref47","first-page":"282","article-title":"Conditional random fields: Probabilistic models for segmenting and labeling sequence data","volume-title":"Proc. 18th Int. Conf. Mach. Learn.","author":"Lafferty"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12173640"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.47"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00330"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747268"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00052"},{"key":"ref54","first-page":"1","article-title":"Contextual similarity aggregation with self-attention for visual re-ranking","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ouyang"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408891"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1016-8"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2846566"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_11"},{"key":"ref59","first-page":"2241","article-title":"Classification is a strong baseline for deep metric learning","volume-title":"Proc. Brit. Mach. Vis. Conf. (BMVC)","author":"Zhai"},{"key":"ref60","volume-title":"Hierachical Labels for Capg-gp Dataset","author":"Budimir","year":"2024"},{"key":"ref61","article-title":"PyTorch metric learning","author":"Musgrave","year":"2020","journal-title":"arXiv:2008.09164"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"86","key":"ref63","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00655"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_43"},{"key":"ref66","article-title":"RetailKLIP: Finetuning OpenCLIP backbone using metric learning on a single GPU for zero-shot retail product image classification","author":"Srivastava","year":"2023","journal-title":"arXiv:2312.10282"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"https:\/\/linproxy.fan.workers.dev:443\/http\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10849567.pdf?arnumber=10849567","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,25]],"date-time":"2025-02-25T18:55:07Z","timestamp":1740509707000},"score":1,"resource":{"primary":{"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/ieeexplore.ieee.org\/document\/10849567\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":66,"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/doi.org\/10.1109\/access.2025.3532745","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}