{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T00:01:00Z","timestamp":1777248060370,"version":"3.51.4"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Singapore Ministry of Education (MOE) Academic Research Fund Tier 1 under MOE\u2019s official","award":["T1 251RES1820"],"award-info":[{"award-number":["T1 251RES1820"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3069041","type":"journal-article","created":{"date-parts":[[2021,3,26]],"date-time":"2021-03-26T19:41:28Z","timestamp":1616787688000},"page":"50441-50451","source":"Crossref","is-referenced-by-count":22,"title":["Visual Relationship Detection With Visual-Linguistic Knowledge From Multimodal Representations"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0312-9136","authenticated-orcid":false,"given":"Meng-Jiun","family":"Chiou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7410-2590","authenticated-orcid":false,"given":"Roger","family":"Zimmermann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6843-0064","authenticated-orcid":false,"given":"Jiashi","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2617079"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2943753"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00857"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.344"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2954750"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896516"},{"key":"ref37","first-page":"2","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","author":"su","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref35","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref34","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"harold li","year":"2019","journal-title":"arXiv 1908 03557"},{"key":"ref28","article-title":"Bridging knowledge graphs to generate scene graphs","author":"zareian","year":"2020","journal-title":"arXiv 2001 02314"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00408"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2187436"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995711"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.142"},{"key":"ref22","first-page":"670","article-title":"Graph R-CNN for scene graph generation","author":"yang","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"ref24","first-page":"7211","article-title":"Mapping images to scene graphs with permutation-invariant structured prediction","author":"herzig","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","first-page":"335","article-title":"Factorizable Net: An efficient subgraph-based framework for scene graph generation","author":"li","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01180"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00632"},{"key":"ref50","article-title":"Google’s neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016","journal-title":"arXiv 1609 08144"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00678"},{"key":"ref55","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc 3rd Int Conf Learn Represent (ICLR)"},{"key":"ref54","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.454"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_20"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00112"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IPAS.2018.8708855"},{"key":"ref14","article-title":"Contextual translation embedding for visual relationship detection and scene graph generation","author":"hung","year":"2019","journal-title":"arXiv 1905 11624"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00207"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00527"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR49039.2020.00065"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01390"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.766"},{"key":"ref3","first-page":"852","article-title":"Visual relationship detection with language priors","author":"lu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.352"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.71"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.554"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.331"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00214"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.121"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"},{"key":"ref45","article-title":"Language models are few-shot learners","author":"brown","year":"2020","journal-title":"arXiv 2005 14165"},{"key":"ref48","article-title":"Gaussian error linear units (GELUs)","author":"hendrycks","year":"2016","journal-title":"arXiv 1606 08415"},{"key":"ref47","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume":"1","author":"devlin","year":"2019","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref42","first-page":"1378","article-title":"Ask me anything: Dynamic memory networks for natural language processing","author":"kumar","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-2812"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref43","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09387302.pdf?arnumber=9387302","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T18:25:13Z","timestamp":1643221513000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9387302\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3069041","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}