{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T22:13:07Z","timestamp":1768860787886,"version":"3.49.0"},"reference-count":61,"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 Plan","award":["2016YFB1001004"],"award-info":[{"award-number":["2016YFB1001004"]}]},{"name":"Guangdong Science and Technology","award":["2017B010123003"],"award-info":[{"award-number":["2017B010123003"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772161"],"award-info":[{"award-number":["61772161"]}],"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":["61906143"],"award-info":[{"award-number":["61906143"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tmm.2020.2976552","type":"journal-article","created":{"date-parts":[[2020,3,2]],"date-time":"2020-03-02T20:47:27Z","timestamp":1583182047000},"page":"92-104","source":"Crossref","is-referenced-by-count":57,"title":["Integrating Part of Speech Guidance for Image Captioning"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9544-9801","authenticated-orcid":false,"given":"Ji","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8119-3726","authenticated-orcid":false,"given":"Kuizhi","family":"Mei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4923-0910","authenticated-orcid":false,"given":"Jianping","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298856"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref33","first-page":"2361","article-title":"Review networks for caption generation","author":"yang","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref31","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.277"},{"key":"ref37","article-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","author":"mao","year":"0"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2708709"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3177745"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2642953"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1080\/00207548808947840"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref28","article-title":"Explain images with multimodal recurrent neural networks","author":"mao","year":"2014"},{"key":"ref27","first-page":"595","article-title":"Multimodal neural language models","author":"kiros","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2587640"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206594"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.306"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref23","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"0","journal-title":"European Conf on Comp Vision Workshop"},{"key":"ref26","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref25","first-page":"1700","article-title":"Recurrent continuous translation models","author":"kalchbrenner","year":"0","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2751140"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref59","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1016\/0004-3702(77)90026-1","article-title":"Speech understanding systems: Report of a steering committee","volume":"9","author":"medress","year":"1977","journal-title":"Artif Intell"},{"key":"ref58","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324918000098"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01095"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.10.018"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"ref11","first-page":"1143","article-title":"Im2text: Describing images using 1 million captioned photographs","author":"ordonez","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref40","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2014"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-2097"},{"key":"ref14","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","author":"karpathy","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref16","first-page":"444","article-title":"Corpus-guided sentence generation of natural images","author":"yang","year":"0","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref18","first-page":"220","article-title":"Composing simple image descriptions using web-scale N-grams","author":"li","year":"0","journal-title":"Proc Computational Natural Language Learning"},{"key":"ref19","first-page":"747","article-title":"Midge: Generating image descriptions from computer vision detections","author":"mitchell","year":"0","journal-title":"Proc Conf Eur Chapter Assoc Comput Linguistics"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.17"},{"key":"ref6","first-page":"487","article-title":"Learning deep features for scene recognition using places database","author":"zhou","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995631"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_26"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2888822"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref46","first-page":"2204","article-title":"Recurrent models of visual attention","author":"mnih","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref45","article-title":"Multiple object recognition with visual attention","author":"ba","year":"2014"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896516"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2904878"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2869276"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2599174"},{"key":"ref44","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2915033"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9296985\/09019658.pdf?arnumber=9019658","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:51:22Z","timestamp":1652194282000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9019658\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/tmm.2020.2976552","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}