{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T10:19:11Z","timestamp":1781086751459,"version":"3.54.1"},"reference-count":43,"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:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3041447","type":"journal-article","created":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T22:35:02Z","timestamp":1606862102000},"page":"215505-215515","source":"Crossref","is-referenced-by-count":6,"title":["Multimodal Data Processing Framework for Smart City: A Positional-Attention Based Deep Learning Approach"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6635-2792","authenticated-orcid":false,"given":"Qianxia","family":"Ma","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8718-3422","authenticated-orcid":false,"given":"Yongfang","family":"Nie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9790-8573","authenticated-orcid":false,"given":"Jingyan","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref38","first-page":"2029","article-title":"Convolutional sequence to sequence learning","author":"gehring","year":"2017","journal-title":"Proc Int Conf Mach Learn ICML"},{"key":"ref33","first-page":"1","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc Int Conf Learn Represent ICLR Conf Track"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref31","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref37","first-page":"933","article-title":"Language modeling with gated convolutional networks","author":"dauphin","year":"2017","journal-title":"Proc Int Conf Mach Learn ICML"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00583"},{"key":"ref35","first-page":"6959","article-title":"Learning to guide decoding for image captioning","author":"jiang","year":"2018","journal-title":"Proc AAAI Conf Artif Intell AAAI"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref10","first-page":"1","volume":"1","author":"evans","year":"2011","journal-title":"The Internet of Things How the next Evolution of the Internet Is Changing Everything"},{"key":"ref40","first-page":"4790","article-title":"Conditional image generation with pixelcnn decoders","author":"van den oord","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2016.7474340"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2994551.2994564"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2017.2662008"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04174-7_2"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref16","first-page":"444","article-title":"Corpus-guided sentence generation of natural images","author":"yang","year":"2011","journal-title":"Proc EMNLP - Conf Empir Methods Nat Lang Process Conf"},{"key":"ref17","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":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"ref19","first-page":"220","article-title":"Composing simple image descriptions using web-scale N-Grams","author":"li","year":"2011","journal-title":"Proc CoNLL 15th Conf Comput Nat Lang Learn Conf"},{"key":"ref28","first-page":"101","article-title":"phi-LSTM: A phrase-based hierarchical LSTM model for image captioning","author":"tan","year":"2016","journal-title":"Vision Computer"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2018.2890173"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3115432"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1145\/1721654.1721672","article-title":"A view of cloud computing","volume":"53","author":"josep","year":"2010","journal-title":"Commun ACM"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2016.2579198"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2745201"},{"key":"ref8","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 ICML"},{"key":"ref7","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","first-page":"97","article-title":"That ‘Internet of Things’ thing","volume":"22","author":"ashton","year":"2009","journal-title":"RFID J"},{"key":"ref9","first-page":"1","volume":"1","author":"index","year":"2018","journal-title":"Forecast and methodology 2016–2021 white paper"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCN.2019.8847174"},{"key":"ref20","first-page":"359","article-title":"Collective generation of natural image descriptions","author":"kuznetsova","year":"2012","journal-title":"Proc Annu Meet Assoc Comput Linguist ACL Conf"},{"key":"ref22","first-page":"1239","article-title":"How many words is a picture worth? Automatic caption generation for news images","author":"feng","year":"2010","journal-title":"Proc ACL Annu Meeting Assoc Comput Linguistics Conf"},{"key":"ref21","first-page":"1250","article-title":"Generating image descriptions using dependency relational patterns","author":"aker","year":"2010","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2598339"},{"key":"ref24","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2014","journal-title":"arXiv 1411 2539"},{"key":"ref41","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"chen","year":"2015","journal-title":"arXiv 1504 00325"},{"key":"ref23","first-page":"595","article-title":"Multimodal neural language models","author":"kiros","year":"2014","journal-title":"Proc Int Conf Mach Learn ICML"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2018.1700202"},{"key":"ref25","article-title":"Explain images with multimodal recurrent neural networks","author":"mao","year":"2014","journal-title":"arXiv 1410 1090"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09274421.pdf?arnumber=9274421","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:57:09Z","timestamp":1639771029000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9274421\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3041447","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}