{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T02:00:17Z","timestamp":1762999217099,"version":"3.37.3"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2017,12,1]],"date-time":"2017-12-01T00:00:00Z","timestamp":1512086400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2017,12,1]],"date-time":"2017-12-01T00:00:00Z","timestamp":1512086400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2017,12,1]],"date-time":"2017-12-01T00:00:00Z","timestamp":1512086400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2017,12,1]],"date-time":"2017-12-01T00:00:00Z","timestamp":1512086400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"US National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1409683","IIS-1218872"],"award-info":[{"award-number":["IIS-1409683","IIS-1218872"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2017,12,1]]},"DOI":"10.1109\/tpami.2016.2643667","type":"journal-article","created":{"date-parts":[[2016,12,29]],"date-time":"2016-12-29T19:27:51Z","timestamp":1483039671000},"page":"2539-2553","source":"Crossref","is-referenced-by-count":16,"title":["Write a Classifier: Predicting Visual Classifiers from Unstructured Text"],"prefix":"10.1109","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6647-6787","authenticated-orcid":false,"given":"Mohamed","family":"Elhoseiny","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmed","family":"Elgammal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Babak","family":"Saleh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-50077-5_2"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.111"},{"key":"ref39","first-page":"2121","article-title":"DeVISE: A deep visual-semantic embedding\n model","author":"frome","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref38","article-title":"Im2Text:\n Describing images using 1 million captioned photographs","author":"ordonez","year":"0","journal-title":"Proc 25th Annu Conf Neural Inf Process Syst"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref32","first-page":"10","article-title":"Generating natural-language video descriptions using text-mined knowledge","author":"krishnamoorthy","year":"0","journal-title":"Proc NAACL HLT Workshop Vis Language"},{"key":"ref31","first-page":"444","article-title":"Corpus-guided sentence generation of natural images","author":"yang","year":"0","journal-title":"Proc Conf Empirical Methods Natural Language Process"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995466"},{"key":"ref37","article-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","author":"mao","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref36","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with\n visual attention","author":"xu","year":"0","journal-title":"Proceedings of the 32nd Intl Conf on Machine Learning"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref60","first-page":"2211","article-title":"Multiple kernel learning algorithms","volume":"12","author":"gonen","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref62","first-page":"325","article-title":"Multi-label multiple kernel learning by stochastic approximation: Application to visual object recognition","author":"bucak","year":"0","journal-title":"Proc 23rd Int Conf Neural Inf Process Syst"},{"key":"ref61","first-page":"244","article-title":"Kernel descriptors for visual\n recognition","author":"bo","year":"0","journal-title":"Proc 23rd Int Conf Neural Inf Process Syst"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2001.990994"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.128"},{"key":"ref65","first-page":"647","article-title":"DeCAF: A deep convolutional activation\n feature for generic visual recognition","author":"donahue","year":"0","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.140"},{"key":"ref29","first-page":"15","article-title":"Every picture tells a story: Generating\n sentences from images","author":"farhadi","year":"0","journal-title":"Proc 11th Eur Conf Comput Vis"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2013.6475038"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995627"},{"key":"ref69","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"article-title":"The Caltech-UCSD birds-200-2011 dataset","year":"2011","author":"wah","key":"ref2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995720"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35749-7_2"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298638"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995451"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15549-9_55"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587410"},{"key":"ref26","first-page":"248","article-title":"ImageNet: A large-scale hierarchical image database","author":"deng","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"journal-title":"Parallel Optimization Theory Algorithms and Applications","year":"1997","author":"censor","key":"ref50"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74690-4_28"},{"key":"ref59","article-title":"Zero-shot learning by convex combination of\n semantic embeddings","author":"norouzi","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref58","article-title":"Order-embeddings of images and language","author":"vendrov","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.247"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298911"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15549-9_56"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972757.75"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/0306-4573(88)90021-0"},{"key":"ref52","article-title":"Efficient estimation of word\n representations in vector space","author":"mikolov","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5244\/C.23.2"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33718-5_13"},{"key":"ref40","first-page":"935","article-title":"Zero shot learning through cross-modal transfer","author":"socher","year":"0","journal-title":"Proc 26th Int Conf Neural Inf Process Syst"},{"article-title":"Fine-grained visual classification of aircraft","year":"2013","author":"maji","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.321"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44581-1_27"},{"article-title":"Caltech-UCSD Birds 200","year":"2010","author":"welinder","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2000.855856"},{"key":"ref17","first-page":"449","article-title":"Object classification from a single example utilizing class\n relevance metrics","author":"fink","year":"0","journal-title":"Proc 17th Int Conf Neural Inf Process Syst"},{"key":"ref18","first-page":"1410","article-title":"Zero-shot learning with\n semantic output codes","author":"palatucci","year":"0","journal-title":"Proc 22nd Int Conf Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206772"},{"article-title":"All about Birds16","year":"2016","author":"belongie","key":"ref4"},{"article-title":"Avibase","year":"2016","author":"lepage","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238476"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15555-0_6"},{"key":"ref8","first-page":"951","article-title":"Learning\n to detect unseen object classes by betweenclass attribute transfer","author":"lampert","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.117"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-008-0204-y"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_16"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/1291233.1291276"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.265"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995702"},{"key":"ref42","first-page":"3478","article-title":"Zero-shot event detection by multimodal distributional semantic\n embedding of videos","author":"elhoseiny","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref41","first-page":"3111","article-title":"Distributed representations of words and phrases and their\n compositionality","author":"mikolov","year":"0","journal-title":"Proc 26th Int Conf Neural Inf Process Syst"},{"journal-title":"Gaussian Processes for Machine Learning","year":"2005","author":"rasmussen","key":"ref44"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.2000.10485983"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/ieeexplore.ieee.org\/ielaam\/34\/8094206\/7801884-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/8094206\/07801884.pdf?arnumber=7801884","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T18:47:36Z","timestamp":1649443656000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7801884\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12,1]]},"references-count":71,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2016.2643667","relation":{},"ISSN":["0162-8828","2160-9292"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"}],"subject":[],"published":{"date-parts":[[2017,12,1]]}}}