{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T11:59:44Z","timestamp":1785153584282,"version":"3.55.0"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Project of China","doi-asserted-by":"publisher","award":["2018AAA0101900"],"award-info":[{"award-number":["2018AAA0101900"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61906012"],"award-info":[{"award-number":["61906012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62006012"],"award-info":[{"award-number":["62006012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62132001"],"award-info":[{"award-number":["62132001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"The Hong Kong Jockey Club Charities Trust"},{"DOI":"10.13039\/501100003803","name":"The University of Hong Kong","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003803","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1109\/tcsvt.2022.3229081","type":"journal-article","created":{"date-parts":[[2022,12,14]],"date-time":"2022-12-14T18:44:12Z","timestamp":1671043452000},"page":"2935-2949","source":"Crossref","is-referenced-by-count":34,"title":["Toward Explainable 3D Grounded Visual Question Answering: A New Benchmark and Strong Baseline"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5805-3194","authenticated-orcid":false,"given":"Lichen","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Software, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daigang","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Software, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3516-0111","authenticated-orcid":false,"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Software, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8525-9163","authenticated-orcid":false,"given":"Lu","family":"Sheng","sequence":"additional","affiliation":[{"name":"School of Software, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4279-3542","authenticated-orcid":false,"given":"Dong","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of Hong Kong, Pok Fu Lam, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Software, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yinjie","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Software, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lipeng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Software, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xibo","family":"Fan","sequence":"additional","affiliation":[{"name":"School of Software, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","article-title":"3D question answering","author":"ye","year":"2021","journal-title":"arXiv 2112 08359"},{"key":"ref12","article-title":"ScanQA: 3D question answering for spatial scene understanding","author":"azuma","year":"2021","journal-title":"arXiv 2112 10482"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref14","article-title":"CLEVR3D: Compositional language and elementary visual reasoning for question answering in 3D real-world scenes","author":"yan","year":"2021","journal-title":"arXiv 2112 11691"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.499"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00370"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3105820"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3101847"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3104304"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref48","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref42","first-page":"1","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"lu","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00937"},{"key":"ref43","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"raffel","year":"2020","journal-title":"J Mach Learn Res"},{"key":"ref49","article-title":"How much can CLIP benefit vision-and-language tasks?","author":"shen","year":"2021","journal-title":"arXiv 2107 06383"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00321"},{"key":"ref4","first-page":"1","article-title":"Embodied question answering","author":"das","year":"2018","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref3","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"chen","year":"2015","journal-title":"arXiv 1504 00325"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref40","first-page":"1","article-title":"Hierarchical question-image co-attention for visual question answering","volume":"29","author":"lu","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475397"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00597"},{"key":"ref37","first-page":"1","article-title":"A multi-world approach to question answering about real-world scenes based on uncertain input","author":"malinowski","year":"2014","journal-title":"Proc NIPS"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00068"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16253"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00181"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00187"},{"key":"ref32","first-page":"1046","article-title":"LanguageRefer: Spatial-language model for 3D visual grounding","volume":"164","author":"roh","year":"2022","journal-title":"Mach Learn Res"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.121"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00444"},{"key":"ref38","article-title":"Simple baseline for visual question answering","author":"zhou","year":"2015","journal-title":"arXiv 1512 02167"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2543039"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3051377"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00292"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3098832"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3102025"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3132047"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.16"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00402"},{"key":"ref27","article-title":"D3Net: A unified speaker-listener architecture for 3D dense captioning and visual grounding","author":"chen","year":"2021","journal-title":"arXiv 2112 01551"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00775"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10144449\/09984686.pdf?arnumber=9984686","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,26]],"date-time":"2023-06-26T18:55:18Z","timestamp":1687805718000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9984686\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6]]},"references-count":49,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2022.3229081","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6]]}}}