{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T05:10:21Z","timestamp":1782364221880,"version":"3.54.5"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2018,3,1]],"date-time":"2018-03-01T00:00:00Z","timestamp":1519862400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61525206"],"award-info":[{"award-number":["61525206"]}],"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":["61572472"],"award-info":[{"award-number":["61572472"]}],"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":["61429201"],"award-info":[{"award-number":["61429201"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Basic Research Program of China","doi-asserted-by":"publisher","award":["2017YFB1002202"],"award-info":[{"award-number":["2017YFB1002202"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Natural Science Foundation of Beijing Municipality","doi-asserted-by":"publisher","award":["4152050"],"award-info":[{"award-number":["4152050"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014380","name":"Beijing Advanced Innovation Center for Imaging Technology","doi-asserted-by":"publisher","award":["BAICIT-2016009"],"award-info":[{"award-number":["BAICIT-2016009"]}],"id":[{"id":"10.13039\/100014380","id-type":"DOI","asserted-by":"publisher"}]},{"name":"ARO","award":["W911NF-15-1-0290"],"award-info":[{"award-number":["W911NF-15-1-0290"]}]},{"name":"Faculty Research Gift Awards by NEC Laboratories of America and Blippar"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2018,3]]},"DOI":"10.1109\/tmm.2017.2751140","type":"journal-article","created":{"date-parts":[[2017,9,11]],"date-time":"2017-09-11T18:11:20Z","timestamp":1505153480000},"page":"726-737","source":"Crossref","is-referenced-by-count":110,"title":["GLA: Global\u2013Local Attention for Image Description"],"prefix":"10.1109","volume":"20","author":[{"given":"Linghui","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3573-2407","authenticated-orcid":false,"given":"Sheng","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1151-1792","authenticated-orcid":false,"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lixi","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1690-9836","authenticated-orcid":false,"given":"Qi","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1218","article-title":"Integrating language and vision to generate natural language descriptions of videos in the wild","author":"thomason","year":"0","journal-title":"Proc Int Conf Comput Linguist"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967258"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref32","article-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","author":"mao","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref30","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":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1173"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.61"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.117"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref27","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref29","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2168198"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-2097"},{"key":"ref22","article-title":"Rethinking the inception architecture for computer vision","author":"szegedy","year":"2015"},{"key":"ref21","first-page":"1","article-title":"Large scale retrieval and generation of image descriptions","author":"ordonez","year":"2015","journal-title":"Int J Comput Vis"},{"key":"ref24","article-title":"Generating sequences with recurrent neural networks","author":"graves","year":"2013"},{"key":"ref23","first-page":"1017","article-title":"Generating text with recurrent neural networks","author":"sutskever","year":"0","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref26","first-page":"1137","article-title":"A neural probabilistic language model","volume":"3","author":"bengio","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref25","first-page":"1045","article-title":"Recurrent neural network based language model","author":"mikolov","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref50","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref51","first-page":"65","article-title":"Meteor: An automatic metric for MT evaluation with improved correlation with human judgments","volume":"29","author":"banerjee","year":"0","journal-title":"Proc ACL Workshop Intrinsic Extrinsic Eval Measures Mach Transl Summarization"},{"key":"ref59","article-title":"Recurrent neural network regularization","author":"zaremba","year":"2014"},{"key":"ref58","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting.","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref56","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1162\/tacl_a_00166","article-title":"From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions","volume":"2","author":"young","year":"2014","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref55","doi-asserted-by":"crossref","first-page":"853","DOI":"10.1613\/jair.3994","article-title":"Framing image description as a ranking task: Data, models and evaluation metrics","volume":"47","author":"hodosh","year":"2013","journal-title":"J Artif Intell Res"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref52","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Proc of Workshop on Text Summarization Branches Out at ACL"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2390499"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2351788"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477044"},{"key":"ref12","first-page":"3","article-title":"CNN image retrieval learns from bow: Unsupervised fine-tuning with hard examples","author":"radenovi?","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21236\/ADA623249"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.277"},{"key":"ref15","first-page":"15","article-title":"Every picture tells a story: Generating sentences from images","author":"farhadi","year":"2010","journal-title":"Proc Eur Conf Comput Vis"},{"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":"747","article-title":"Midge: Generating image descriptions from computer vision detections","author":"mitchell","year":"0","journal-title":"Proc 13th Conf Eur Ch Assoc Comput Linguistics"},{"key":"ref19","first-page":"359","article-title":"Collective generation of natural image descriptions","author":"kuznetsova","year":"0","journal-title":"Proc 50th Annu Meeting Assoc for Comput Linguist Long Papers-Vol 1"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref3","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729786"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298854"},{"key":"ref7","article-title":"Object detection using deep neural networks","author":"szegedy","year":"2016"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref45","article-title":"Aligning where to see and what to tell: image caption with region-based attention and scene factorization","author":"jin","year":"2015"},{"key":"ref48","first-page":"346","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","author":"he","year":"2014","journal-title":"Proc Computer Vision"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref43","first-page":"4133","article-title":"Image caption with global-local attention","author":"li","year":"0","journal-title":"Proc 31st AAAI Conf Artif Intell"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8291714\/08031355.pdf?arnumber=8031355","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:25:31Z","timestamp":1642004731000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8031355\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,3]]},"references-count":59,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2017.2751140","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,3]]}}}