{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T09:13:20Z","timestamp":1760346800802},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/tcsvt.2019.2916167","type":"journal-article","created":{"date-parts":[[2019,5,10]],"date-time":"2019-05-10T20:13:52Z","timestamp":1557519232000},"page":"1-1","source":"Crossref","is-referenced-by-count":20,"title":["Matching Image and Sentence with Multi-faceted Representations"],"prefix":"10.1109","author":[{"given":"Lin","family":"Ma","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhao","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zequn","family":"Jie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"A survey from shallow methods to deep methods","author":"li","year":"0","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2519449"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1049\/iet-ipr.2017.0232"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2747134"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298966"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.201"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_50"},{"key":"ref35","first-page":"169","article-title":"Finding linear structure in large datasets with scalable canonical correlation analysis","author":"ma","year":"2015","journal-title":"Proc ICML"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2010.11.006"},{"key":"ref28","first-page":"1","article-title":"Order-embeddings of images and language","author":"vendrov","year":"2016","journal-title":"Proc ICLR"},{"key":"ref27","first-page":"3294","article-title":"Skip-thought vectors","author":"kiros","year":"2015","journal-title":"Proc NIPS"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref2","first-page":"1","article-title":"Multimodal neural language model","author":"kiros","year":"2014","journal-title":"Proc ICML"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref20","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","author":"karpathy","year":"2014","journal-title":"Proc NIPS"},{"key":"ref22","first-page":"2764","article-title":"Wsabie: Scaling up to large vocabulary image annotation","author":"weston","year":"2011","journal-title":"Proc IJCAI"},{"key":"ref21","author":"kiros","year":"2014","journal-title":"Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00601"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2911527"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299073"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"ref50","first-page":"2042","article-title":"Convolutional neural network architectures for matching natural language sentences","author":"hu","year":"2014","journal-title":"Proc NIPS"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2865280"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2015.10.011"},{"key":"ref57","article-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","author":"szegedy","year":"2016","journal-title":"Proc ICLR Workshop"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.767"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.208"},{"key":"ref53","first-page":"2121","article-title":"DeViSE: A deep visual-semantic embedding model","author":"frome","year":"2013","journal-title":"Proc NIPS"},{"key":"ref52","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc ECCV"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.9"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/83.988962"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.11"},{"key":"ref14","first-page":"1","article-title":"Dynamic memory networks for visual and textual question answering","author":"xiong","year":"2016","journal-title":"Proc ICML"},{"key":"ref15","first-page":"2953","article-title":"Exploring models and data for image question answering","author":"ren","year":"2015","journal-title":"Proc NIPS"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_35"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2911493"},{"key":"ref18","first-page":"1143","article-title":"Im2Text: Describing images using 1 million captioned photographs","author":"ordonez","year":"2011","journal-title":"Proc NIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00177"},{"key":"ref4","article-title":"Explain images with multimodal recurrent neural networks","author":"mao","year":"2014","journal-title":"NIPS Deep Learning Workshop"},{"key":"ref3","first-page":"747","article-title":"Midge: Generating image descriptions from computer vision detections","author":"mitchell","year":"2012","journal-title":"Proc EACL"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964299"},{"key":"ref5","first-page":"2422","article-title":"Mind’s eye: A recurrent visual representation for image caption generation","author":"chen","year":"2015","journal-title":"Proc CVPR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref7","first-page":"1","article-title":"Deep captioning with multimodal recurrent neural networks (M-RNN)","author":"mao","year":"2015","journal-title":"Proc ICLR"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.301"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639346"},{"key":"ref45","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc ICML"},{"key":"ref48","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc ICLR"},{"key":"ref47","author":"hinton","year":"2012","journal-title":"Improving Neural Networks by Preventing Co-adaptation of Feature Detectors"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.183"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972788.74"},{"key":"ref44","first-page":"iii-352","article-title":"Multi-view clustering and feature learning via structured sparsity","author":"wang","year":"2013","journal-title":"Proc ICML"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299066"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/4358651\/08712424.pdf?arnumber=8712424","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:39:16Z","timestamp":1651070356000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8712424\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2019.2916167","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]}}}