{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T12:07:37Z","timestamp":1769861257258,"version":"3.49.0"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":["61906007"],"award-info":[{"award-number":["61906007"]}],"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":["61672065"],"award-info":[{"award-number":["61672065"]}],"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":["61906011"],"award-info":[{"award-number":["61906011"]}],"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":["61902378"],"award-info":[{"award-number":["61902378"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009592","name":"Beijing Municipal Science and Technology Project","doi-asserted-by":"publisher","award":["KM202010005014"],"award-info":[{"award-number":["KM202010005014"]}],"id":[{"id":"10.13039\/501100009592","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/tip.2020.3004729","type":"journal-article","created":{"date-parts":[[2020,6,30]],"date-time":"2020-06-30T20:55:23Z","timestamp":1593550523000},"page":"7615-7628","source":"Crossref","is-referenced-by-count":74,"title":["Spatio-Temporal Memory Attention for Image Captioning"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6951-741X","authenticated-orcid":false,"given":"Junzhong","family":"Ji","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5371-1218","authenticated-orcid":false,"given":"Cheng","family":"Xu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7002-5447","authenticated-orcid":false,"given":"Xiaodan","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2677-8342","authenticated-orcid":false,"given":"Boyue","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0895-1076","authenticated-orcid":false,"given":"Xinhang","family":"Song","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.277"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-2017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00188"},{"key":"ref31","first-page":"790","article-title":"Generalizing image captions for image-text parallel corpus","author":"kuznetsova","year":"2013","journal-title":"Proc Ann Meeting on Assoc for Computational Linguistics (ACL)"},{"key":"ref30","first-page":"1","article-title":"Choosing linguistics over vision to describe images","author":"gupta","year":"2012","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.29"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref35","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc IEEE Int Conf Learn Represent"},{"key":"ref34","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc IEEE Int Conf Learn Represent"},{"key":"ref60","author":"luo","year":"2017","journal-title":"An Image Captioning Codebase in Pytorch"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.3115\/1626355.1626389"},{"key":"ref61","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc ACL"},{"key":"ref63","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume":"8","author":"lin","year":"2004","journal-title":"Proc of Workshop on Text Summarization Branches Out at ACL"},{"key":"ref28","first-page":"1143","article-title":"Im2text: Describing images using 1 million captioned photographs","author":"ordonez","year":"2011","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref27","first-page":"444","article-title":"Corpus-guided sentence generation of natural images","author":"yang","year":"2011","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref29","first-page":"359","article-title":"Collective generation of natural image descriptions","author":"kuznetsova","year":"2012","journal-title":"Proc ACL"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref20","first-page":"432","article-title":"An introductory survey on attention mechanisms in NLP problems","volume":"abs 1811 5544","author":"hu","year":"2018","journal-title":"CoRR"},{"key":"ref22","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":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1168"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"ref26","first-page":"747","article-title":"Midge: Generating image descriptions from computer vision detections","author":"mitchell","year":"2012","journal-title":"Proc Conf Eur Chapter Assoc Comput Linguistics"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/72.963769"},{"key":"ref59","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref58","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref55","first-page":"1","article-title":"Deep captioning with multimodal recurrent neural networks (m-rnn)","author":"mao","year":"2014","journal-title":"Proc IEEE Int Conf Learn Represent"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref52","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst Annu Conf Neural Inf Process Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00754"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/1047-3203(90)90007-I"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.89"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1080\/135062800394667"},{"key":"ref16","first-page":"2204","article-title":"Recurrent models of visual attention","author":"mnih","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-psych-122414-033400"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.psych.52.1.337"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(95)00025-9"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/089892904322984526"},{"key":"ref3","first-page":"115","author":"koch","year":"1987","journal-title":"Shifts in Selective Visual Attention Towards the Underlying Neural Circuitry"},{"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":"10.1162\/neco.1997.9.8.1735"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref49","first-page":"1","article-title":"Neural turing machines","volume":"abs 1410 5401","author":"graves","year":"2014","journal-title":"CoRR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2882225"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2855406"},{"key":"ref48","first-page":"2440","article-title":"End-to-end memory networks","author":"sukhbaatar","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref47","article-title":"Memory networks","author":"weston","year":"2015","journal-title":"Proc IEEE Int Conf Learn Represent"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2855415"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2889922"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/34.977565"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.23.1.315"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/8835130\/09130137.pdf?arnumber=9130137","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:39:01Z","timestamp":1651070341000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9130137\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/tip.2020.3004729","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}