{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:27:19Z","timestamp":1781587639224,"version":"3.54.5"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["62125207"],"award-info":[{"award-number":["62125207"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972378"],"award-info":[{"award-number":["61972378"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tip.2024.3374211","type":"journal-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T20:29:12Z","timestamp":1710793752000},"page":"2572-2586","source":"Crossref","is-referenced-by-count":40,"title":["Convolution-Enhanced Bi-Branch Adaptive Transformer With Cross-Task Interaction for Food Category and Ingredient Recognition"],"prefix":"10.1109","volume":"33","author":[{"given":"Yuxin","family":"Liu","sequence":"first","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6668-9208","authenticated-orcid":false,"given":"Weiqing","family":"Min","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1596-4326","authenticated-orcid":false,"given":"Shuqiang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Rui","sequence":"additional","affiliation":[{"name":"Lenovo Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3329168"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1017\/s1368980018000708"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.compind.2017.09.001"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.10.106"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3377049.3377111"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2831627"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2958761"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3237871"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2929447"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414031"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350948"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3193763"},{"key":"ref13","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964315"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2009.5413511"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2014.03.017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654970"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW.2015.203"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2986035.2986042"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-73600-6_12"},{"key":"ref24","first-page":"1","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Krizhevsky"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00068"},{"key":"ref26","article-title":"Mining discriminative food regions for accurate food recognition","author":"Qiu","year":"2022","journal-title":"arXiv:2207.03692"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1201\/9781003394440-10"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3020079"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ac9830"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00042"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref35","first-page":"1","article-title":"Transformer in transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Han"},{"key":"ref36","article-title":"Focal self-attention for local\u2013global interactions in vision transformers","author":"Yang","year":"2021","journal-title":"arXiv:2107.00641"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"ref38","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2010.04159"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref40","article-title":"Conditional positional encodings for vision transformers","author":"Chu","year":"2021","journal-title":"arXiv:2102.10882"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_39"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00015"},{"key":"ref44","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3028478"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00530"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_10"},{"key":"ref50","article-title":"See better before looking closer: Weakly supervised data augmentation network for fine-grained visual classification","author":"Hu","year":"2019","journal-title":"arXiv:1901.09891"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3206108"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-70742-6_37"},{"key":"ref54","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16472"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17098"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414047"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3181789"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3318958"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/10346232\/10471331.pdf?arnumber=10471331","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,2]],"date-time":"2024-04-02T05:13:55Z","timestamp":1712034835000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10471331\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/tip.2024.3374211","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}