{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,10,12]],"date-time":"2022-10-12T05:50:19Z","timestamp":1665553819288},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2017,8,1]],"date-time":"2017-08-01T00:00:00Z","timestamp":1501545600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Comput. Intell. Mag."],"published-print":{"date-parts":[[2017,8]]},"DOI":"10.1109\/mci.2017.2708559","type":"journal-article","created":{"date-parts":[[2017,7,18]],"date-time":"2017-07-18T18:26:06Z","timestamp":1500402366000},"page":"29-42","source":"Crossref","is-referenced-by-count":3,"title":["Learning to Generate Descriptions of Visual Data Anchored in Spatial Relations"],"prefix":"10.1109","volume":"12","author":[{"given":"Adrian","family":"Muscat","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anja","family":"Belz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-3202"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1022"},{"key":"ref33","first-page":"747","article-title":"Midge: Generating image descriptions from computer vision detections","author":"mitchell","year":"0","journal-title":"Proc 13th Conf of the European Chapter of the Association for Computational Linguistics"},{"key":"ref32","first-page":"220","article-title":"Composing simple image descriptions using web-scale n-grams","author":"li","year":"0","journal-title":"Proc 15th Conf Computational Natural Language Learning"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-2816"},{"key":"ref30","first-page":"1292","article-title":"Image description using visual dependency representations","author":"elliott","year":"0","journal-title":"Proc 18th Conf on Empirical Methods in Natural Language Processing"},{"key":"ref37","first-page":"410","article-title":"A game-theoretic approach to generating spatial descriptions","author":"golland","year":"0","journal-title":"Proc 15th Conf on Empirical Methods in Natural Language Processing"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3115\/1708322.1708334"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1162\/tacl_a_00188","article-title":"Treetalk: Composition and compression of trees for image descriptions","volume":"2","author":"kuznetsova","year":"2014","journal-title":"Trans Assoc Comput Linguist"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995466"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref29","first-page":"444","article-title":"Corpus-guided sentence generation of natural images","author":"yang","year":"0","journal-title":"Proc 16th Conf on Empirical Methods in Natural Language Processing"},{"key":"ref2","article-title":"Digital accessibility: A brief landscaping","author":"barton","year":"2015","journal-title":"Tech Rep"},{"key":"ref1","article-title":"Getting connected: Engaging people with sight loss in accessible technology","author":"workman","year":"2013","journal-title":"Tech Rep Royal National Institute of Blind People"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref22","first-page":"606","article-title":"Choosing linguistics over vision to describe images","author":"gupta","year":"0","journal-title":"Proc AAAI Conf Artificial Intelligence"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-2097"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1613\/jair.4900","article-title":"Automatic description generation from images: A survey of models, data sets, and evaluation measures","volume":"55","author":"bernardi","year":"2016","journal-title":"J Artif Intell Res"},{"key":"ref23","first-page":"1143","article-title":"Im2text: Describing images using 1 million captioned photographs","author":"ordonez","year":"0","journal-title":"Proc Advances in Neural Information Processing Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/S14-1015"},{"key":"ref25","first-page":"15","article-title":"Every picture tells a story: Generating sentences from images","author":"farhadi","year":"0","journal-title":"11th European Conf Computer Vision"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511519857"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3115\/1610163.1610167"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1162\/coli.2009.35.1.111"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-585-28322-7_6"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/coli.06-78-prep14"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-4717"},{"key":"ref12","author":"herskovits","year":"1987","journal-title":"Language and Spatial Cognition"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X00029927"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1017\/9781316423530"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/0031-3203(78)90026-2"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref19","first-page":"27","article-title":"Grounded compositional semantics for finding and describing images with sentences","volume":"2","author":"socher","year":"2014","journal-title":"Trans Assoc Comput Linguist"},{"key":"ref4","first-page":"139","article-title":"Collecting image annotations using amazon's mechanical turk","author":"rashtchian","year":"0","journal-title":"NAACL HLT Workshop on Creating Speech and Language Data with Amazon's Mechanical Turk"},{"key":"ref3","year":"2014","journal-title":"Visual Impairment and Blindness"},{"key":"ref6","author":"leech","year":"1969","journal-title":"Towards a Semantic Description of English"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1162\/coli.2009.35.4.35405"},{"key":"ref8","first-page":"161","article-title":"Semantics of spatial expressions","author":"jackendoff","year":"1983","journal-title":"Semantics and Cognition"},{"key":"ref7","author":"bennett","year":"1975","journal-title":"Spatial and Temporal Uses of English Prepositions An Essay in Stratificational Semantics"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1162\/COLI_a_00088"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-9325-6_11"},{"key":"ref46","article-title":"Algorithms for hyper-parameter optimization","author":"bergstra","year":"0","journal-title":"Proc 25th Annu Conf on Neural Information Processing Systems"},{"key":"ref45","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"bergstra","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref48","first-page":"1137","article-title":"A study of cross-validation and bootstrap for accuracy estimation and model selection","author":"kohavi","year":"0","journal-title":"Proc 14th Int Joint Conf on Artificial Intelligence"},{"key":"ref47","first-page":"4033","article-title":"Lg-eval: A toolkit for creating online language evaluation experiments","author":"kow","year":"0","journal-title":"Proc Int Conf on Lang Resources and Evaluation"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-6639"},{"key":"ref41","first-page":"65","article-title":"Exploring different preposition sets, models and feature sets in automatic generation of spatial image descriptions","author":"muscat","year":"0","journal-title":"Proc 5th Workshop on Vision and Language"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"}],"container-title":["IEEE Computational Intelligence Magazine"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10207\/7983366\/07983469.pdf?arnumber=7983469","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:03:32Z","timestamp":1642003412000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7983469\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,8]]},"references-count":53,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/mci.2017.2708559","relation":{},"ISSN":["1556-603X"],"issn-type":[{"value":"1556-603X","type":"print"}],"subject":[],"published":{"date-parts":[[2017,8]]}}}