{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T05:04:08Z","timestamp":1768626248135,"version":"3.49.0"},"reference-count":89,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Hong Kong Research Grants Council","award":["CityU 11216122"],"award-info":[{"award-number":["CityU 11216122"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1109\/tvcg.2022.3225327","type":"journal-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T19:18:52Z","timestamp":1669749532000},"page":"1772-1786","source":"Crossref","is-referenced-by-count":27,"title":["3D Question Answering"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5121-8040","authenticated-orcid":false,"given":"Shuquan","family":"Ye","sequence":"first","affiliation":[{"name":"City University of Hong Kong, Kowloon Tong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4642-4373","authenticated-orcid":false,"given":"Dongdong","family":"Chen","sequence":"additional","affiliation":[{"name":"Microsoft Cloud AI, Redmond, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6432-8764","authenticated-orcid":false,"given":"Songfang","family":"Han","sequence":"additional","affiliation":[{"name":"University of California San Diego, La Jolla, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7014-5377","authenticated-orcid":false,"given":"Jing","family":"Liao","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Kowloon Tong, Hong Kong"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00522"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00280"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00592"},{"key":"ref9","article-title":"FigureQA: An annotated figure dataset for visual reasoning","author":"Ebrahimi Kahou","year":"2017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1167"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.730"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093269"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00901"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6713"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.121"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00638"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00008"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/s20082281"},{"key":"ref24","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00682"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00321"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00181"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16253"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00370"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00187"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00937"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00086"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00294"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00678"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817340"},{"key":"ref38","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"Lu","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref41","first-page":"5105","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Qi"},{"key":"ref42","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref44","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref45","first-page":"1121","article-title":"Pythia-a platform for vision & language research","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. SysML Workshop","author":"Singh"},{"key":"ref46","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Su"},{"key":"ref47","first-page":"1","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lan"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1203"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref50","first-page":"2296","article-title":"Are you talking to a machine? Dataset and methods for multilingual image question answering","volume-title":"Proc. 28th Int. Conf. Neural Inf. Process. Syst.","author":"Gao"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"key":"ref53","first-page":"2953","article-title":"Exploring models and data for image question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2015.283"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00522"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.542"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref61","article-title":"Object-centric diagnosis of visual reasoning","author":"Yang","year":"2020"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00070"},{"key":"ref63","first-page":"279","article-title":"Neuro-symbolic visual reasoning: Disentangling","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Amizadeh"},{"key":"ref64","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3092570"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2018.2889944"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2022.3160005"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2019.2920817"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3058311"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3114683"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103557"},{"key":"ref72","first-page":"10514","article-title":"Rel3D: A minimally contrastive benchmark for grounding spatial relations in 3D","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Goyal"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/wacv45572.2020.9093452"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2988782"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00439"},{"key":"ref76","first-page":"1682","article-title":"A multi-world approach to question answering about real-world scenes based on uncertain input","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Malinowski"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref79","article-title":"Microsoft coco captions: Data collection and evaluation server","author":"Chen","year":"2015"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"issue":"1","key":"ref81","first-page":"9","article-title":"The paired t test under artificial pairing","volume-title":"Amer. Statistician","volume":"51","author":"David","year":"1997"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.2307\/2286009"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00088"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00192"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_4"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/wacv45572.2020.9093452"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00204"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2021.3114308"},{"key":"ref89","first-page":"1","article-title":"Hadamard product for low-rank bilinear pooling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kim"}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/2945\/10416827\/09965773.pdf?arnumber=9965773","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T13:43:11Z","timestamp":1706794991000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9965773\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3]]},"references-count":89,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2022.3225327","relation":{},"ISSN":["1077-2626","1941-0506","2160-9306"],"issn-type":[{"value":"1077-2626","type":"print"},{"value":"1941-0506","type":"electronic"},{"value":"2160-9306","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3]]}}}