{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T06:49:58Z","timestamp":1780987798858,"version":"3.54.1"},"reference-count":51,"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":[{"name":"NSF of Guangdong Province","award":["2019A1515010833"],"award-info":[{"award-number":["2019A1515010833"]}]},{"name":"NSF of Guangdong Province","award":["2022A1515011573"],"award-info":[{"award-number":["2022A1515011573"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61725204"],"award-info":[{"award-number":["61725204"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Tsinghua University Initiative Scientific Research Program","award":["20211080093"],"award-info":[{"award-number":["20211080093"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3216770","type":"journal-article","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T22:27:09Z","timestamp":1667514429000},"page":"6997-7009","source":"Crossref","is-referenced-by-count":30,"title":["Positional Attention Guided Transformer-Like Architecture for Visual Question Answering"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6861-9414","authenticated-orcid":false,"given":"Aihua","family":"Mao","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9768-2356","authenticated-orcid":false,"given":"Zhi","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ken","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Xuan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5774-1916","authenticated-orcid":false,"given":"Yong-Jin","family":"Liu","sequence":"additional","affiliation":[{"name":"BNRist, Department of Computer Science and Technology, Tsinghua University, and MOE-Key Laboratory of Pervasive Computing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"Proc Conf North Amer Chapter Assoc Computat Linguistics Human Lang Technol"},{"key":"ref12","article-title":"How much position information do convolutional neural networks encode ?","author":"islam","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3049537"},{"key":"ref14","first-page":"1","article-title":"Rethinking positional encoding in language pre-training","author":"ke","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref10","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","first-page":"2953","article-title":"Exploring models and data for image question answering","volume":"28","author":"ren","year":"2015","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"ref19","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.11"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.469"},{"key":"ref50","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01001"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00444"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475397"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.642"},{"key":"ref44","first-page":"1","article-title":"Layer normalization","author":"ba","year":"0","journal-title":"Proc Adv Neural Inf Process Syst deep Learn Symp"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref49","first-page":"1682","article-title":"A multi-world approach to question answering about real-world scenes based on uncertain input","author":"malinowski","year":"0"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00680"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref9","first-page":"1","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","author":"su","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475392"},{"key":"ref3","first-page":"201","article-title":"Stacked cross attention for image-text matching","author":"lee","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref6","first-page":"1","article-title":"Learning to count objects in natural images for visual question answering","author":"zhang","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2956975"},{"key":"ref40","first-page":"1","article-title":"Graph attention networks","author":"veli?kovi?","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref34","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","first-page":"1","article-title":"Encoding word order in complex embeddings","author":"wang","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref36","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":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.10.001"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3029423"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00181"},{"key":"ref32","first-page":"91","article-title":"Re-attention for visual question answering","volume":"34","author":"guo","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01041"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref23","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"0","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240513"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/126"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.12"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"1264","DOI":"10.1109\/TMM.2020.2995278","article-title":"Self-adaptive neural module transformer for visual question answering","volume":"23","author":"huasong","year":"2021","journal-title":"IEEE Trans Multimedia"},{"key":"ref28","first-page":"1564","article-title":"Bilinear attention networks","author":"kim","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3026892"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12240"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09927339.pdf?arnumber=9927339","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,11]],"date-time":"2023-12-11T20:20:07Z","timestamp":1702326007000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9927339\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3216770","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}