{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T23:17:12Z","timestamp":1784330232962,"version":"3.55.0"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"New Generation of AI","award":["2018AAA0100400"],"award-info":[{"award-number":["2018AAA0100400"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61525306"],"award-info":[{"award-number":["61525306"]}],"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":["61633021"],"award-info":[{"award-number":["61633021"]}],"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":["61721004"],"award-info":[{"award-number":["61721004"]}],"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":["61806194"],"award-info":[{"award-number":["61806194"]}],"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":["U1803261"],"award-info":[{"award-number":["U1803261"]}],"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":["61976132"],"award-info":[{"award-number":["61976132"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["Z201100006820079"],"award-info":[{"award-number":["Z201100006820079"]}],"id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shandong Provincial Key Research and Development Program","award":["2019JZZY010119"],"award-info":[{"award-number":["2019JZZY010119"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2022,6,1]]},"DOI":"10.1109\/tpami.2021.3052490","type":"journal-article","created":{"date-parts":[[2021,2,25]],"date-time":"2021-02-25T19:51:03Z","timestamp":1614282663000},"page":"2968-2983","source":"Crossref","is-referenced-by-count":14,"title":["Few-Shot Image and Sentence Matching via Aligned Cross-Modal Memory"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8239-7229","authenticated-orcid":false,"given":"Yan","family":"Huang","sequence":"first","affiliation":[{"name":"Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), Center for Excellence in Brain Science and Intelligence Technology (CEBSIT), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4888-4445","authenticated-orcid":false,"given":"Jingdong","family":"Wang","sequence":"additional","affiliation":[{"name":"Media Computing Group, Microsoft Research Asia, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Wang","sequence":"additional","affiliation":[{"name":"Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), Center for Excellence in Brain Science and Intelligence Technology (CEBSIT), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref70","article-title":"Dual-path convolutional image-text embedding","volume":"16","author":"zheng","year":"2017"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref38","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_17"},{"key":"ref32","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_50"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.301"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00729"},{"key":"ref35","first-page":"7210","article-title":"Towards affordable semantic searching: Zero-shot retrieval via dominant attributes","author":"long","year":"2018","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.442"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00805"},{"key":"ref62","article-title":"Memory networks","author":"weston","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00590"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00677"},{"key":"ref28","first-page":"3734","article-title":"Self-attention graph pooling","author":"lee","year":"0"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2708709"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00170"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.15"},{"key":"ref66","first-page":"2397","article-title":"Dynamic memory networks for visual and textual question answering","author":"xiong","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298966"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00601"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.8"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref20","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","author":"karpathy","year":"2014","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref22","first-page":"1564","article-title":"Bilinear attention networks","author":"kim","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299073"},{"key":"ref23","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2015","journal-title":"Trans Assoc Comput Linguistics"},{"key":"ref26","first-page":"1378","article-title":"Ask me anything: Dynamic memory networks for natural language processing","author":"kumar","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref50","first-page":"2440","article-title":"End-to-end memory networks","author":"sukhbaatar","year":"2015","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_14"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00717"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00784"},{"key":"ref54","first-page":"3637","article-title":"Matching networks for one shot learning","author":"vinyals","year":"2016","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.130"},{"key":"ref52","article-title":"Order-embeddings of images and language","author":"vendrov","year":"2016","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref10","article-title":"Few-shot learning with graph neural networks","author":"garcia","year":"0"},{"key":"ref11","article-title":"Neural turing machines","author":"graves","year":"2014"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/nature20101"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","first-page":"8489","article-title":"Few-shot image and sentence matching via gated visual-semantic matching","author":"huang","year":"2019","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00587"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.767"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2883466"},{"key":"ref4","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"0"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/92"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.201"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00190"},{"key":"ref8","first-page":"2121","article-title":"Devise: A deep visual-semantic embedding model","author":"frome","year":"2013","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref7","article-title":"VSE++: Improved visual-semantic embeddings","author":"faghri","year":"0"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00807"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.7"},{"key":"ref46","first-page":"4077","article-title":"Prototypical networks for few-shot learning","author":"snell","year":"2017","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref45","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"ref47","first-page":"935","article-title":"Zero-shot learning through cross-modal transfer","author":"socher","year":"2013","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00379"},{"key":"ref43","article-title":"Meta-learning for semi-supervised few-shot classification","author":"ren","year":"2018"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9769881\/09328198.pdf?arnumber=9328198","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,30]],"date-time":"2022-05-30T22:21:52Z","timestamp":1653949312000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9328198\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,1]]},"references-count":70,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2021.3052490","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":[[2022,6,1]]}}}