{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T18:58:03Z","timestamp":1772823483581,"version":"3.50.1"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2016YFB1001000"],"award-info":[{"award-number":["2016YFB1001000"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976214"],"award-info":[{"award-number":["61976214"]}],"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\/100014103","name":"Shandong Provincial Key Research and Development Program","doi-asserted-by":"publisher","award":["2019JZZY010119"],"award-info":[{"award-number":["2019JZZY010119"]}],"id":[{"id":"10.13039\/100014103","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tip.2020.3048627","type":"journal-article","created":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T01:28:19Z","timestamp":1610242099000},"page":"1840-1852","source":"Crossref","is-referenced-by-count":14,"title":["Learning Aligned Image-Text Representations Using Graph Attentive Relational Network"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4179-8210","authenticated-orcid":false,"given":"Ya","family":"Jing","sequence":"first","affiliation":[]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Liang","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Tieniu","family":"Tan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Person re-identification meets image search","author":"zheng","year":"2015","journal-title":"arXiv 1502 02171"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.27"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_8"},{"key":"ref32","article-title":"Gated graph sequence neural networks","author":"li","year":"2015","journal-title":"arXiv 1511 05493"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref30","first-page":"4800","article-title":"Hierarchical graph representation learning with differentiable pooling","author":"ying","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3115\/1118108.1118117"},{"key":"ref36","first-page":"103","article-title":"Skeleton-based action recognition with spatial reasoning and temporal stack learning","author":"si","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.556"},{"key":"ref34","article-title":"Recurrent relational networks","author":"berg palm","year":"2017","journal-title":"arXiv 1711 08028"},{"key":"ref28","first-page":"486","article-title":"Person re-identification with deep similarity-guided graph neural network","author":"shen","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref27","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00226"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.209"},{"key":"ref1","first-page":"201","article-title":"Stacked cross attention for image-text matching","author":"lee","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2014.2359548"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2870946"},{"key":"ref24","first-page":"686","article-title":"Deep cross-modal projection learning for image-text matching","author":"zhang","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref23","article-title":"Dual-path convolutional image-text embedding with instance loss","author":"zheng","year":"2017","journal-title":"arXiv 1711 05535"},{"key":"ref26","first-page":"3844","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","author":"defferrard","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref25","first-page":"1","article-title":"Spectral networks and locally connected networks on graphs","author":"bruna","year":"2014","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref50","first-page":"54","article-title":"Improving deep visual representation for person re-identification by global and local image-language association","author":"chen","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref58","first-page":"3221","article-title":"Accelerating t-SNE using tree-based algorithms","volume":"15","author":"van der maaten","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.442"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-018-3051-y"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299073"},{"key":"ref53","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1080\/00437956.1954.11659520"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.551"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref40","article-title":"End-to-end deep learning for person search","author":"xiao","year":"2016","journal-title":"arXiv 1604 01850"},{"key":"ref12","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2014","journal-title":"arXiv 1411 2539"},{"key":"ref13","article-title":"Vse++: Improving visual-semantic embeddings with hard negatives","author":"faghri","year":"2018","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"ref15","article-title":"Recurrent neural network based language model","author":"mikolov","year":"2010","journal-title":"Proc 11th Annu Conf Int Speech Commun Assoc"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00431"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00051"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.523"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.13"},{"key":"ref6","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2859820"},{"key":"ref8","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2855406"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00208"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref46","first-page":"480","article-title":"Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline)","author":"sun","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref45","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv 1704 04861"},{"key":"ref48","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref42","first-page":"31","article-title":"Human reidentification with transferred metric learning","author":"li","year":"2012","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref41","first-page":"1","article-title":"Evaluating appearance models for recognition, reacquisition, and tracking","author":"gray","year":"2007","journal-title":"Proc IEEE Int Workshop Perform Eval Tracking Surveill"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref43","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9263394\/09318563.pdf?arnumber=9318563","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:06Z","timestamp":1652194206000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9318563\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/tip.2020.3048627","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}