{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T20:33:56Z","timestamp":1777408436388,"version":"3.51.4"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001659","name":"German Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"National Science Foundation of China through Project \u201cCrossmodal Learning\u201d","doi-asserted-by":"publisher","award":["TRR-169"],"award-info":[{"award-number":["TRR-169"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2020,6]]},"DOI":"10.1109\/tcds.2019.2906685","type":"journal-article","created":{"date-parts":[[2019,10,3]],"date-time":"2019-10-03T18:18:47Z","timestamp":1570126727000},"page":"169-178","source":"Crossref","is-referenced-by-count":19,"title":["Integrating Image-Based and Knowledge-Based Representation Learning"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3170-5647","authenticated-orcid":false,"given":"Ruobing","family":"Xie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9913-3206","authenticated-orcid":false,"given":"Stefan","family":"Heinrich","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7709-2543","authenticated-orcid":false,"given":"Zhiyuan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cornelius","family":"Weber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1343-4775","authenticated-orcid":false,"given":"Stefan","family":"Wermter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maosong","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1745","article-title":"Recognition using visual phrases","author":"farhadi","year":"2011","journal-title":"Proc CVPR"},{"key":"ref38","first-page":"17","article-title":"Modeling mutual context of object and human pose in human-object","author":"yao","year":"2010","journal-title":"Proc CVPR"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1020"},{"key":"ref30","first-page":"1","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2014","journal-title":"Proc NIPS"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref35","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc ICLR"},{"key":"ref34","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc NIPS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1082"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2016.2638425"},{"key":"ref29","first-page":"1859","article-title":"Knowledge base completion using embeddings and rules","author":"wang","year":"2015","journal-title":"Proc IJCAI"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nrn2811"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/9320.001.0001","author":"cangelosi","year":"2015","journal-title":"Developmental Robotics From Babies to Robots"},{"key":"ref20","article-title":"TransA: An adaptive approach for knowledge graph embedding","volume":"abs 1509 5490","author":"xiao","year":"2015","journal-title":"CoRR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/BF02289464"},{"key":"ref21","first-page":"5569","article-title":"StarSpace: Embed all the things","author":"wu","year":"2018","journal-title":"Proc AAAI"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1002\/1099-128X(200005\/06)14:3<105::AID-CEM582>3.0.CO;2-I"},{"key":"ref23","first-page":"809","article-title":"A three-way model for collective learning on multi-relational data","author":"nickel","year":"2011","journal-title":"Proc ICML"},{"key":"ref26","first-page":"2659","article-title":"Representation learning of knowledge graphs with entity descriptions","author":"xie","year":"2016","journal-title":"Proc AAAI"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1167"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-013-5363-6"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref57","first-page":"4985","article-title":"Visual Word2Vec (vis-w2v): Learning visually grounded word embeddings using abstract scenes","author":"kottur","year":"2016","journal-title":"Proc CVPR"},{"key":"ref56","first-page":"746","article-title":"Linguistic regularities in continuous space word representations","author":"mikolov","year":"2013","journal-title":"Proc HLT-NAACL"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.3389\/neuro.06.004.2008"},{"key":"ref54","first-page":"926","article-title":"Reasoning with neural tensor networks for knowledge base completion","author":"socher","year":"2013","journal-title":"Proc NIPS"},{"key":"ref53","first-page":"127","article-title":"Joint learning of words and meaning representations for open-text semantic parsing","author":"bordes","year":"2012","journal-title":"Proc AISTATS"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-0106"},{"key":"ref11","first-page":"2787","article-title":"Translating embeddings for modeling multi-relational data","author":"bordes","year":"2013","journal-title":"Proc NIPS"},{"key":"ref40","article-title":"Learning to generalize to new compositions in image understanding","volume":"abs 1608 7639","author":"atzmon","year":"2016","journal-title":"CoRR"},{"key":"ref12","first-page":"1","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013","journal-title":"Proc ICLR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/438"},{"key":"ref14","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc NIPS"},{"key":"ref15","first-page":"1112","article-title":"Knowledge graph embedding by translating on hyperplanes","author":"wang","year":"2014","journal-title":"Proc AAAI"},{"key":"ref16","first-page":"2181","article-title":"Learning entity and relation embeddings for knowledge graph completion","author":"lin","year":"2015","journal-title":"Proc AAAI"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1067"},{"key":"ref18","first-page":"328","article-title":"Transition-based knowledge graph embedding with relational mapping properties","author":"fan","year":"2014","journal-title":"Proc of PACLIC17"},{"key":"ref19","first-page":"557","article-title":"Knowledge graph embedding by flexible translation","author":"feng","year":"2016","journal-title":"Proc KR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3758\/s13423-015-0909-1"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature17637"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2013.06.004"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.cortex.2011.04.006"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1162\/jocn.2009.21131"},{"key":"ref7","first-page":"563","article-title":"Representing part-whole relationships in recurrent neural networks","author":"jain","year":"2006","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref9","first-page":"1","article-title":"Embedding entities and relations for learning and inference in knowledge bases","author":"yang","year":"2015","journal-title":"Proc ICLR"},{"key":"ref46","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc ICLR"},{"key":"ref45","first-page":"2204","article-title":"Recurrent models of visual attention","author":"mnih","year":"2014","journal-title":"Proc NIPS"},{"key":"ref48","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1044"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459256"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123380"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.331"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274989\/9113770\/08689107.pdf?arnumber=8689107","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T20:00:38Z","timestamp":1639771238000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8689107\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6]]},"references-count":57,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2019.2906685","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"value":"2379-8920","type":"print"},{"value":"2379-8939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,6]]}}}