{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T18:21:16Z","timestamp":1776277276825,"version":"3.50.1"},"reference-count":25,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61471206"],"award-info":[{"award-number":["61471206"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu province","doi-asserted-by":"publisher","award":["BK20180088"],"award-info":[{"award-number":["BK20180088"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE MultiMedia"],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/mmul.2024.3415643","type":"journal-article","created":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T18:51:50Z","timestamp":1719341510000},"page":"25-36","source":"Crossref","is-referenced-by-count":1,"title":["The Multimodal Scene Recognition Method Based on Self-Attention and Distillation"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6907-3756","authenticated-orcid":false,"given":"Ning","family":"Sun","sequence":"first","affiliation":[{"name":"Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7585-9418","authenticated-orcid":false,"given":"Wei","family":"Xu","sequence":"additional","affiliation":[{"name":"Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8414-4199","authenticated-orcid":false,"given":"Jixin","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9120-0339","authenticated-orcid":false,"given":"Lei","family":"Chai","sequence":"additional","affiliation":[{"name":"Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haian","family":"Sun","sequence":"additional","affiliation":[{"name":"Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Deep learning for scene classification: A survey","author":"Zeng","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.09.066"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2021.3053459"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103373"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2017.02.008"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.02.005"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2019.2933728"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463603"},{"key":"ref9","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01475-7"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01563"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.05.002"},{"key":"ref13","first-page":"10,347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2021.3090902"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2883743"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3310042"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2019.2946102"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref22","article-title":"Large batch optimization for deep learning: Training BERT in 76 minutes","author":"You","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2022.104453"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019176"},{"key":"ref25","article-title":"Centroid based concept learning for RGB-D indoor scene classification","author":"Ayub","year":"2019"}],"container-title":["IEEE MultiMedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/93\/10807513\/10570457.pdf?arnumber=10570457","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,30]],"date-time":"2024-12-30T19:51:15Z","timestamp":1735588275000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10570457\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":25,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/mmul.2024.3415643","relation":{},"ISSN":["1070-986X","1941-0166"],"issn-type":[{"value":"1070-986X","type":"print"},{"value":"1941-0166","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}