{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T16:53:12Z","timestamp":1779382392831,"version":"3.53.1"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"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. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2021,5,1]]},"DOI":"10.1109\/tpami.2019.2955476","type":"journal-article","created":{"date-parts":[[2019,11,26]],"date-time":"2019-11-26T01:05:58Z","timestamp":1574730358000},"page":"1733-1745","source":"Crossref","is-referenced-by-count":32,"title":["Text-Guided Neural Network Training for Image Recognition in Natural Scenes and Medicine"],"prefix":"10.1109","volume":"43","author":[{"given":"Zizhao","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pingjun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoshuang","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967212"},{"key":"ref38","first-page":"2121","article-title":"Devise: A deep visual-semantic embedding model","author":"frome","year":"2013","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1613\/jair.4900"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00312"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref30","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref36","article-title":"Dynamic coattention networks for question answering","author":"xiong","year":"2017"},{"key":"ref35","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"2016","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref60","doi-asserted-by":"crossref","first-page":"168","DOI":"10.5626\/JCSE.2012.6.2.168","article-title":"Design and development of a multimodal biomedical information retrieval system","volume":"6","author":"dina","year":"2012","journal-title":"J Comput Sci Eng"},{"key":"ref62","article-title":"Simple baseline for visual question answering","author":"zhou","year":"2015"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.369"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00920"},{"key":"ref64","article-title":"Deep captioning with multimodal recurrent neural networks (M-RNN)","author":"mao","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1228"},{"key":"ref65","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref66","first-page":"4601","article-title":"ct with 2-way nets","author":"eisenschtat","year":"2017","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.85"},{"key":"ref67","article-title":"Vse++: Improving visual-semantic embeddings with hard negatives","author":"faghri","year":"2017","journal-title":"Proc British Mach Vis Conf"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref1","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc 25th Int Conf Neural Inf Process Syst"},{"key":"ref20","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc 32nd Int Conf Int Conf Mach Learn"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"ref21","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","author":"simonyan","year":"2014","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref24","first-page":"1885","article-title":"Understanding black-box predictions via influence functions","author":"koh","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.215"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.354"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref50","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc 32nd Int Conf Int Conf Mach Learn"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.558"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.58"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.219"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.251"},{"key":"ref55","article-title":"Deep convolutional ranking for multilabel image annotation","author":"gong","year":"2014"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298664"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.775"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2553401"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66179-7_37"},{"key":"ref13","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref14","article-title":"Visual genome: Connecting language and vision using crowdsourced dense image annotations","author":"krishna","year":"2016"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.356"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.378"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.274"},{"key":"ref18","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref19","article-title":"A structured self-attentive sentence embedding","author":"lin","year":"2017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00963"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref49","first-page":"1310","article-title":"On the difficulty of training recurrent neural networks","author":"pascanu","year":"2013","journal-title":"Proc 30th Int Conf Int Conf Mach Learn"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref46","first-page":"2342","article-title":"An empirical exploration of recurrent network architectures","author":"jozefowicz","year":"2015","journal-title":"Proc 32nd Int Conf Int Conf Mach Learn"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref47","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00943"},{"key":"ref41","article-title":"Pathologist-level interpretable whole-slide cancer diagnosis with deep learning","volume":"1","author":"zhang","year":"2019","journal-title":"Nature Mach Intell"},{"key":"ref44","first-page":"630","article-title":"Identity mappings in deep residual networks","author":"he","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref43","article-title":"Wide residual networks","author":"zagoruyko","year":"2016","journal-title":"Proc British Mach Vis Conf"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9393625\/08911262.pdf?arnumber=8911262","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:49:21Z","timestamp":1652194161000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8911262\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,1]]},"references-count":68,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2019.2955476","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,1]]}}}