{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T04:02:26Z","timestamp":1748404946630,"version":"3.41.0"},"reference-count":59,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["62202329","U21B2024"],"award-info":[{"award-number":["62202329","U21B2024"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2024.3387735","type":"journal-article","created":{"date-parts":[[2024,4,11]],"date-time":"2024-04-11T19:03:28Z","timestamp":1712862208000},"page":"2863-2874","source":"Crossref","is-referenced-by-count":0,"title":["Toward Chinese Food Understanding: A Cross-Modal Ingredient-Level Benchmark"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7696-5330","authenticated-orcid":false,"given":"Lanjun","family":"Wang","sequence":"first","affiliation":[{"name":"Tianjin University, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7822-2517","authenticated-orcid":false,"given":"Chenyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5755-9145","authenticated-orcid":false,"given":"An-An","family":"Liu","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6707-3932","authenticated-orcid":false,"given":"Bo","family":"Yang","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4845-4244","authenticated-orcid":false,"given":"Mingwang","family":"Hu","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9246-9756","authenticated-orcid":false,"given":"Xinran","family":"Qiao","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2627-0877","authenticated-orcid":false,"given":"Lei","family":"Wang","sequence":"additional","affiliation":[{"name":"MeiTuan Group, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6797-4781","authenticated-orcid":false,"given":"Jianlin","family":"He","sequence":"additional","affiliation":[{"name":"MeiTuan Group, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2006-3150","authenticated-orcid":false,"given":"Qiang","family":"Liu","sequence":"additional","affiliation":[{"name":"MeiTuan Group, Beijing, China"}]}],"member":"263","reference":[{"article-title":"DINO: DERT with improved denoising anchor boxes for end-to-end object detection","year":"2022","author":"Zhang","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00986"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00729"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3086066"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_41"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01093"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3254530"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964315"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414031"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3237871"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2018.2831627"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/icprs58416.2023.10179037"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/jbhi.2016.2636441"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.327"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01522"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210036"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw56347.2022.00503"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2021.3083109"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3181116"},{"year":"2023","key":"ref22","article-title":"Chinese cuisine culture"},{"year":"2015","key":"ref23","article-title":"Regulation of food composition data expression"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/icip.2009.5413400"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2638728.2641339"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/icmew.2015.7169816"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2020.3038315"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2020.3028478"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3390\/nu15122751"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2013.2271474"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240627"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401244"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2017.2759499"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-70742-6_41"},{"article-title":"ChineseFoodNet: A large-scale image dataset for chinese food recognition","year":"2017","author":"Chen","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.66"},{"article-title":"Mining discriminative food regions for accurate food recognition","year":"2022","author":"Qiu","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/itnec52019.2021.9587189"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-13321-3_7"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/icme.2012.157"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654869"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/tla.2022.9878168"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16199-0_1"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-51811-4_48"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.519"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16199-0_1"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"article-title":"Yolov5 by ultralytics","year":"2020","author":"Jocher","key":"ref48"},{"key":"ref49","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref51","first-page":"36067","article-title":"GLIPv2: Unifying localization and vision-language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Zhang","year":"2022"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01553"},{"article-title":"A faster PyTorch implementation of faster R-CNN","year":"2017","author":"Yang","key":"ref54"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00636"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2024.104071"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref58"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10844992\/10496846.pdf?arnumber=10496846","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T04:31:20Z","timestamp":1748320280000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10496846\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3387735","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2025]]}}}