{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T23:03:18Z","timestamp":1778799798268,"version":"3.51.4"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172261"],"award-info":[{"award-number":["62172261"]}],"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":["62276155"],"award-info":[{"award-number":["62276155"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"National Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2021MF040"],"award-info":[{"award-number":["ZR2021MF040"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tip.2023.3318949","type":"journal-article","created":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T17:48:34Z","timestamp":1696009714000},"page":"5537-5549","source":"Crossref","is-referenced-by-count":11,"title":["Semantic-Aware Modular Capsule Routing for Visual Question Answering"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7830-9679","authenticated-orcid":false,"given":"Yudong","family":"Han","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Shandong University, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4611-2986","authenticated-orcid":false,"given":"Jianhua","family":"Yin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Shandong University, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0247-5221","authenticated-orcid":false,"given":"Jianlong","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1791-3159","authenticated-orcid":false,"given":"Yinwei","family":"Wei","sequence":"additional","affiliation":[{"name":"NExT++, National University of Singapore, Queenstown, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1476-0273","authenticated-orcid":false,"given":"Liqiang","family":"Nie","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_44"},{"key":"ref12","first-page":"1571","article-title":"Bilinear attention networks","author":"kim","year":"2018","journal-title":"Proc NIPS"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.642"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00208"},{"key":"ref59","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"2016","journal-title":"Proc NIPS"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00680"},{"key":"ref58","article-title":"Incorporating external knowledge to answer open-domain visual questions with dynamic memory networks","author":"li","year":"2017","journal-title":"arXiv 1712 00733"},{"key":"ref53","first-page":"1548","article-title":"Overcoming language priors in visual question answering with adversarial regularization","author":"ramakrishnan","year":"2018","journal-title":"Proc NIPS"},{"key":"ref52","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.265"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref54","first-page":"4971","article-title":"Don’t just assume; look and answer: Overcoming priors for visual question answering","author":"agrawal","year":"2018","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01041"},{"key":"ref16","first-page":"8344","article-title":"Learning conditioned graph structures for interpretable visual question answering","author":"norcliffe-brown","year":"2018","journal-title":"Proc NIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/153"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00678"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"},{"key":"ref47","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc ECCV"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_32"},{"key":"ref41","article-title":"Scene graph reasoning with prior visual relationship for visual question answering","author":"yang","year":"2019","journal-title":"arXiv 1812 09681"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350925"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240513"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_28"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref7","first-page":"3856","article-title":"Dynamic routing between capsules","author":"sabour","year":"2017","journal-title":"Proc NIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018102"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.93"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00857"},{"key":"ref40","first-page":"273","article-title":"Chain of reasoning for visual question answering","author":"wu","year":"2018","journal-title":"Proc NIPS"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref34","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"arXiv 1607 06450"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref36","first-page":"1","article-title":"Hadamard product for low-rank bilinear pooling","author":"kim","year":"2017","journal-title":"Proc ICLR"},{"key":"ref31","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i03.5684"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1282"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00209"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.12"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00637"},{"key":"ref38","first-page":"1","article-title":"Learning to count objects in natural images for visual question answering","author":"zhang","year":"2018","journal-title":"Proc ICLR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00919"},{"key":"ref23","first-page":"1","article-title":"Fine-grained dynamic head for object detection","author":"song","year":"2020","journal-title":"Proc NIPS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16237"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413977"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11164"},{"key":"ref64","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"li","year":"2019","journal-title":"arXiv 1908 03557"},{"key":"ref63","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"2019","journal-title":"Proc NIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413943"},{"key":"ref66","first-page":"2579","article-title":"Viualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref21","first-page":"2659","article-title":"Out of the box: Reasoning with graph convolution nets for factual visual question answering","author":"narasimhan","year":"2018","journal-title":"Proc NIPS"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3004830"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00164"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019324"},{"key":"ref29","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc NIPS"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref62","first-page":"1","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","author":"su","year":"2020","journal-title":"Proc ICLR"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9991910\/10268338.pdf?arnumber=10268338","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,30]],"date-time":"2023-10-30T19:41:43Z","timestamp":1698694903000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10268338\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/tip.2023.3318949","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}