{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:09:23Z","timestamp":1740100163972,"version":"3.37.3"},"reference-count":63,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,8,8]],"date-time":"2021-08-08T00:00:00Z","timestamp":1628380800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,8,8]],"date-time":"2021-08-08T00:00:00Z","timestamp":1628380800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,8,8]]},"DOI":"10.1109\/ro-man50785.2021.9515374","type":"proceedings-article","created":{"date-parts":[[2021,8,23]],"date-time":"2021-08-23T22:07:53Z","timestamp":1629756473000},"page":"633-640","source":"Crossref","is-referenced-by-count":1,"title":["Neural Variational Learning for Grounded Language Acquisition"],"prefix":"10.1109","author":[{"given":"Nisha","family":"Pillai","sequence":"first","affiliation":[{"name":"University of Maryland,Baltimore,MD,USA,21250"}]},{"given":"Cynthia","family":"Matuszek","sequence":"additional","affiliation":[{"name":"University of Maryland,Baltimore,MD,USA,21250"}]},{"given":"Francis","family":"Ferraro","sequence":"additional","affiliation":[{"name":"University of Maryland,Baltimore,MD,USA,21250"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.140"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1045"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.12108","article-title":"Unsupervised end-to-end data selection for grounded language learning","author":"pillai","year":"2018","journal-title":"Int Conference on Artificial Intelligence (AAAI)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_49"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1068"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01354"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S19-1007"},{"key":"ref36","article-title":"Matching networks for one shot learning","author":"vinyals","year":"2016","journal-title":"Neural Information Processing Systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.328"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989492"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460608"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2016.XII.041"},{"key":"ref61","article-title":"Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections","author":"mao","year":"2016","journal-title":"Neural Information Processing Systems"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.321"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00612"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.233"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2852838"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i03.5627"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/0167-2789(90)90087-6"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.080"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1008566"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00819"},{"key":"ref24","article-title":"Information maximization for few-shot learning","author":"boudiaf","year":"2020","journal-title":"Neural Information Processing Systems"},{"key":"ref23","article-title":"Task aligned generative meta-learning for zero-shot learning","author":"liu","year":"2021","journal-title":"Int Conference on Artificial Intelligence (AAAI)"},{"key":"ref26","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"2019","journal-title":"Neural Information Processing Systems"},{"key":"ref25","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL-HLT"},{"key":"ref50","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Neural Information Processing Systems"},{"key":"ref51","article-title":"Learning to connect language and perception","author":"mooney","year":"2008","journal-title":"Int Conference on Artificial Intelligence (AAAI)"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.132"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00573"},{"key":"ref57","article-title":"Object referring in videos with language and human gaze","author":"balajee vasudevan","year":"2018","journal-title":"Computer Vision and Pattern Recognition"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2018.07.006"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref53","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Neural Information Processing Systems"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460699"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15549-9_48"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN46459.2019.8956449"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01288"},{"key":"ref12","article-title":"Improving grounded language acquisition efficiency using interactive labeling","author":"pillai","year":"2016","journal-title":"R SS Workshop on MLHRC"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2016.XII.037"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v32i4.2384"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593942"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.586"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593886"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref19","article-title":"Learning multi-modal grounded linguistic semantics by playing ”I Spy","author":"thomason","year":"2016","journal-title":"Intl Joint Conf on Artificial Intelligence (IJCAI)"},{"key":"ref4","article-title":"Learning to order objects using haptic and proprioceptive exploratory behaviors","author":"sinapov","year":"2016","journal-title":"Intl Joint Conf on Artificial Intelligence (IJCAI)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018909"},{"key":"ref6","article-title":"A Joint Model of Language and Perception for Grounded Attribute Learning","author":"matuszek","year":"2012","journal-title":"Int’l Conf on Mahcine Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref8","article-title":"Experience grounds language","author":"bisk","year":"2020","journal-title":"EMNLP"},{"key":"ref7","article-title":"Learning object attributes with category-free grounded language from deep featurization","author":"richards","year":"2020","journal-title":"Intelligent Robots and Systems"},{"key":"ref49","article-title":"Identifying negative exemplars in grounded language data sets","author":"pillai","year":"2017","journal-title":"RSS Workshop on Spatial-Semantic Representations in Robotics"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2016.1164622"},{"key":"ref46","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"ICLRE"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref48","article-title":"Visually grounded meaning representations","author":"silberer","year":"2016","journal-title":"PAMI"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref42","article-title":"Semi-supervised learning with deep generative models","author":"kingma","year":"2014","journal-title":"Neural Information Processing Systems"},{"key":"ref41","article-title":"Discovering human interactions with novel objects via zero-shot learning","author":"wang","year":"2020","journal-title":"Computer Vision and Pattern Recognition"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995719"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980382"}],"event":{"name":"2021 30th IEEE International Conference on Robot & Human Interactive Communication (RO-MAN)","start":{"date-parts":[[2021,8,8]]},"location":"Vancouver, BC, Canada","end":{"date-parts":[[2021,8,12]]}},"container-title":["2021 30th IEEE International Conference on Robot & Human Interactive Communication (RO-MAN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9515344\/9515312\/09515374.pdf?arnumber=9515374","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,7]],"date-time":"2023-01-07T22:35:02Z","timestamp":1673130902000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9515374\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,8]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/ro-man50785.2021.9515374","relation":{},"subject":[],"published":{"date-parts":[[2021,8,8]]}}}