{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:38:52Z","timestamp":1784302732495,"version":"3.55.0"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2022ZD0116309"],"award-info":[{"award-number":["2022ZD0116309"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62236010"],"award-info":[{"award-number":["62236010"]}],"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":["62322607"],"award-info":[{"award-number":["62322607"]}],"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":["62276261"],"award-info":[{"award-number":["62276261"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tpami.2024.3432552","type":"journal-article","created":{"date-parts":[[2024,7,23]],"date-time":"2024-07-23T19:24:14Z","timestamp":1721762654000},"page":"5160-5176","source":"Crossref","is-referenced-by-count":5,"title":["Unpaired Image-Text Matching via Multimodal Aligned Conceptual Knowledge"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8239-7229","authenticated-orcid":false,"given":"Yan","family":"Huang","sequence":"first","affiliation":[{"name":"New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2368-361X","authenticated-orcid":false,"given":"Yuming","family":"Wang","sequence":"additional","affiliation":[{"name":"New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunan","family":"Zeng","sequence":"additional","affiliation":[{"name":"New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junshi","family":"Huang","sequence":"additional","affiliation":[{"name":"AI Lab, Meituan, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1979-1167","authenticated-orcid":false,"given":"Zhenhua","family":"Chai","sequence":"additional","affiliation":[{"name":"AI Lab, Meituan, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5224-8647","authenticated-orcid":false,"given":"Liang","family":"Wang","sequence":"additional","affiliation":[{"name":"New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2021.07.006"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00503"},{"key":"ref8","article-title":"VSE: Improved visual-semantic embeddings","author":"Faghri","year":"2017"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00425"},{"key":"ref10","first-page":"2121","article-title":"DeViSE: A deep visual-semantic embedding model","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Frome"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21310"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00473"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog0702_3"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_31"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01042"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018489"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3052490"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00587"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.767"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3178485"},{"key":"ref22","first-page":"7892","article-title":"MACK: Multimodal aligned conceptual knowledge for unpaired image-text matching","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2883466"},{"key":"ref25","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref26","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"Kiros","year":"2014"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_50"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref31","first-page":"1","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Neural Inf. Process. Syst."},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.420"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-21348-0_30"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"ref39","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1038\/nrn2277"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383266"},{"key":"ref42","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref44","article-title":"ImageNet-21K pretraining for the masses","author":"Ridnik","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018876"},{"key":"ref46","volume-title":"Cognitive Psychology: Mind and Brain: Pearson New International Edition","author":"Smith","year":"2013"},{"key":"ref47","first-page":"1","article-title":"Zero-shot learning through cross-modal transfer","volume":"26","author":"Socher","year":"2013","journal-title":"Neural Inf. Process. Syst."},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350996"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411947"},{"issue":"11","key":"ref50","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00476"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_42"},{"key":"ref55","first-page":"22680","article-title":"VLMixer: Unpaired vision-language pre-training via cross-modal cutmix","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/icme.2019.00256"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.29"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350940"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298966"},{"key":"ref61","article-title":"Chinese CLIP: Contrastive vision-language pretraining in chinese","author":"Yang","year":"2022"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.20"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00141"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2022.3224228"},{"key":"ref67","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020"},{"key":"ref68","article-title":"Building a large-scale multimodal knowledge base system for answering visual queries","author":"Zhu","year":"2015"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/153"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11026037\/10607962.pdf?arnumber=10607962","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T17:42:27Z","timestamp":1749231747000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10607962\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":69,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3432552","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}