{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,9]],"date-time":"2025-07-09T22:52:41Z","timestamp":1752101561850,"version":"3.41.0"},"reference-count":49,"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":[{"name":"Open Project Funding of the Key Laboratory of Intelligent Sensing System and Security"},{"DOI":"10.13039\/501100017589","name":"Hubei University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100017589","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010449","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010449","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972290"],"award-info":[{"award-number":["61972290"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2018YFC1604000"],"award-info":[{"award-number":["2018YFC1604000"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2024.3384672","type":"journal-article","created":{"date-parts":[[2024,4,5]],"date-time":"2024-04-05T18:45:41Z","timestamp":1712342741000},"page":"2783-2794","source":"Crossref","is-referenced-by-count":3,"title":["Cross-Modal Recipe Retrieval With Fine-Grained Prompting Alignment and Evidential Semantic Consistency"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3961-1389","authenticated-orcid":false,"given":"Xu","family":"Huang","sequence":"first","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0359-0248","authenticated-orcid":false,"given":"Jin","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6905-4478","authenticated-orcid":false,"given":"Zhizhong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6945-7437","authenticated-orcid":false,"given":"Yuan","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9333-8200","authenticated-orcid":false,"given":"Yongqiang","family":"Tang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0752-941X","authenticated-orcid":false,"given":"Wensheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6079-009X","authenticated-orcid":false,"given":"Xiaohui","family":"Cui","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00879"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2958761"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3193763"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.327"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01522"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3083109"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref8","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref10","first-page":"3183","article-title":"Evidential deep learning to quantify classification uncertainty","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sensoy","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210036"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01458"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463618"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462965"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2021.3098834"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3490519"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01184"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01174"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00556"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475465"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475422"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547809"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3181294"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01606"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00503"},{"article-title":"Structured vision-language pretraining for computational cooking","year":"2022","author":"Shukor","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475251"},{"key":"ref34","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00512"},{"key":"ref36","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Jia","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"ref38","first-page":"200","article-title":"Multimodal few-shot learning with frozen language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tsimpoukelli","year":"2021"},{"key":"ref39","first-page":"1931","article-title":"Unifying vision-and-language tasks via text generation","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Cho","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref42","first-page":"4383","article-title":"Understanding and improving layer normalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xu","year":"2019"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2015.04.005"},{"key":"ref44","first-page":"1321","article-title":"On calibration of modern neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"70","author":"Guo","year":"2017"},{"key":"ref45","first-page":"14927","article-title":"Deep evidential regression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Amini","year":"2020"},{"key":"ref46","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-42337-1","volume-title":"Subjective Logic: A Formalism for Reasoning Under Uncertainty","author":"Jsang","year":"2016"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00970"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10844992\/10494044.pdf?arnumber=10494044","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T17:22:04Z","timestamp":1748366524000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10494044\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3384672","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2025]]}}}