{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T06:02:54Z","timestamp":1770530574832,"version":"3.49.0"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"JSPS KAKENHI","award":["20H04269"],"award-info":[{"award-number":["20H04269"]}]},{"name":"JST Moonshot R&D","award":["JPMJMS2011"],"award-info":[{"award-number":["JPMJMS2011"]}]},{"DOI":"10.13039\/501100003051","name":"New Energy and Industrial Technology Development Organization","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003051","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2021,10]]},"DOI":"10.1109\/lra.2021.3108500","type":"journal-article","created":{"date-parts":[[2021,8,30]],"date-time":"2021-08-30T20:55:02Z","timestamp":1630356902000},"page":"8401-8408","source":"Crossref","is-referenced-by-count":16,"title":["Target-Dependent UNITER: A Transformer-Based Multimodal Language Comprehension Model for Domestic Service Robots"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0810-3613","authenticated-orcid":false,"given":"Shintaro","family":"Ishikawa","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0261-0510","authenticated-orcid":false,"given":"Komei","family":"Sugiura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021"},{"key":"ref38","article-title":"Google's neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016"},{"key":"ref33","first-page":"2236","article-title":"Multimodal language analysis in the wild: Cmu-mosei dataset and interpretable dynamic fusion graph","author":"zadeh","year":"2018","journal-title":"Proc Assoc Comput Linguistics"},{"key":"ref32","article-title":"Mosi: Multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos","author":"zadeh","year":"2016"},{"key":"ref31","article-title":"Generalized autoregressive pretraining for language understanding","author":"yang","year":"2019"},{"key":"ref30","article-title":"Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref35","first-page":"84","article-title":"Multi-modal reference resolution in situated dialogue by integrating linguistic and extra-linguistic clues","author":"iida","year":"2011","journal-title":"Proc Int Joint Conf Natural Lang Process"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1252"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.4324\/9781315842011"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3115\/1119239.1119245"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1075"},{"key":"ref13","article-title":"A multi-world approach to question answering about real-world scenes based on uncertain input","author":"malinowski","year":"2014"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00522"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00427"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.333"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3010735"},{"key":"ref18","article-title":"Visual entailment: A novel task for fine-grained image understanding","author":"xie","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref28","first-page":"13","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"2019","journal-title":"Neural Inf Process Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2926223"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2019.1663608"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00323"},{"key":"ref6","article-title":"Trends in integration of vision and language research: A. survey of tasks, datasets, and methods","author":"mogadala","year":"2019"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"ref5","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3115\/990820.990863"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1142\/S0219843608001303"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/COLI_a_00088"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref20","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01096"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2963649"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460699"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00431"},{"key":"ref25","first-page":"5503","author":"vries","year":"2017","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9475905\/09525205.pdf?arnumber=9525205","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:54:12Z","timestamp":1652194452000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9525205\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10]]},"references-count":39,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/lra.2021.3108500","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10]]}}}