{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T14:11:35Z","timestamp":1773843095584,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,9,3]],"date-time":"2023-09-03T00:00:00Z","timestamp":1693699200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,3]],"date-time":"2023-09-03T00:00:00Z","timestamp":1693699200000},"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":[[2023,9,3]]},"DOI":"10.1109\/icce-berlin58801.2023.10375660","type":"proceedings-article","created":{"date-parts":[[2024,1,2]],"date-time":"2024-01-02T20:36:26Z","timestamp":1704227786000},"page":"82-87","source":"Crossref","is-referenced-by-count":9,"title":["Food Recognition with Visual Transformers"],"prefix":"10.1109","author":[{"given":"Simone","family":"Bianco","sequence":"first","affiliation":[{"name":"University of Milano-Bicocca,Department of Informatics, Systems and Communication,Milano,Italy"}]},{"given":"Marco","family":"Buzzelli","sequence":"additional","affiliation":[{"name":"University of Milano-Bicocca,Department of Informatics, Systems and Communication,Milano,Italy"}]},{"given":"Gaetano","family":"Chiriaco","sequence":"additional","affiliation":[{"name":"University of Milano-Bicocca,Department of Informatics, Systems and Communication,Milano,Italy"}]},{"given":"Paolo","family":"Napoletano","sequence":"additional","affiliation":[{"name":"University of Milano-Bicocca,Department of Informatics, Systems and Communication,Milano,Italy"}]},{"given":"Flavio","family":"Piccoli","sequence":"additional","affiliation":[{"name":"University of Milano-Bicocca,Department of Informatics, Systems and Communication,Milano,Italy"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1111\/1541-4337.12492"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3329168"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2196\/mhealth.9232"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.tifs.2021.09.014"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.wasman.2022.02.009"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101859"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20103"},{"key":"ref8","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Imagenet-21k pretraining for the masses","author":"Ridnik","year":"2021","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3237871"},{"key":"ref11","article-title":"Sharpness-aware minimization for efficiently improving generalization","author":"Foret","year":"2020","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Mining discrim-inative food regions for accurate food recognition","author":"Qiu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref14","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International conference on machine learning","author":"Touvron","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-18910-4_50"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"ref18","article-title":"How to train your vit? data, augmentation, and regularization in vision transformers","author":"Steiner","year":"2021","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_30"},{"key":"ref22","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref24","first-page":"12116","article-title":"Do vision transformers see like convolutional neural networks?","volume":"34","author":"Raghu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3347448.3357162"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1979.4310076"}],"event":{"name":"2023 IEEE 13th International Conference on Consumer Electronics - Berlin (ICCE-Berlin)","location":"Berlin, Germany","start":{"date-parts":[[2023,9,3]]},"end":{"date-parts":[[2023,9,5]]}},"container-title":["2023 IEEE 13th International Conference on Consumer Electronics - Berlin (ICCE-Berlin)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10375611\/10375583\/10375660.pdf?arnumber=10375660","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T23:58:43Z","timestamp":1705103923000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10375660\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,3]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icce-berlin58801.2023.10375660","relation":{},"subject":[],"published":{"date-parts":[[2023,9,3]]}}}