{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T16:43:29Z","timestamp":1778172209580,"version":"3.51.4"},"reference-count":94,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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 Program of China","doi-asserted-by":"publisher","award":["2018AAA0100403"],"award-info":[{"award-number":["2018AAA0100403"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61876094"],"award-info":[{"award-number":["61876094"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["U1933114"],"award-info":[{"award-number":["U1933114"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["U1903128"],"award-info":[{"award-number":["U1903128"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["U1836109"],"award-info":[{"award-number":["U1836109"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["U1936206"],"award-info":[{"award-number":["U1936206"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006606","name":"Natural Science Foundation of Tianjin, China","doi-asserted-by":"publisher","award":["20JCJQJC00020"],"award-info":[{"award-number":["20JCJQJC00020"]}],"id":[{"id":"10.13039\/501100006606","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006606","name":"Natural Science Foundation of Tianjin, China","doi-asserted-by":"publisher","award":["18JCYBJC15400"],"award-info":[{"award-number":["18JCYBJC15400"]}],"id":[{"id":"10.13039\/501100006606","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006606","name":"Natural Science Foundation of Tianjin, China","doi-asserted-by":"publisher","award":["18ZXZNGX00110"],"award-info":[{"award-number":["18ZXZNGX00110"]}],"id":[{"id":"10.13039\/501100006606","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tip.2021.3097180","type":"journal-article","created":{"date-parts":[[2021,7,20]],"date-time":"2021-07-20T20:09:45Z","timestamp":1626811785000},"page":"6730-6743","source":"Crossref","is-referenced-by-count":88,"title":["Re-Attention for Visual Question Answering"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5609-194X","authenticated-orcid":false,"given":"Wenya","family":"Guo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4906-5828","authenticated-orcid":false,"given":"Ying","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0219-3443","authenticated-orcid":false,"given":"Jufeng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaojie","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00681"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1351"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1348"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00648"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref77","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019324"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00678"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.9"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.11"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00209"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2989701"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00203"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref37","first-page":"8344","article-title":"Learning conditioned graph structures for interpretable visual question answering","author":"norcliffe-brown","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.344"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_14"},{"key":"ref34","first-page":"5824","article-title":"Multi-modality latent interaction network for visual question answering","author":"gao","year":"2019","journal-title":"Proc IEEE Int Conf Comput Vis (ICCV)"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00801"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_2"},{"key":"ref61","first-page":"5428","article-title":"Learning answer embeddings for visual question answering","author":"hu","year":"2018","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_29"},{"key":"ref28","first-page":"1","article-title":"Learning to count objects in natural images for visual question answering","author":"zhang","year":"2018","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1097"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00729"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01002"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.93"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00807"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.651"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1164"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2855415"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5338"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01014"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2229971"},{"key":"ref21","first-page":"10065","article-title":"TA-student VQA: Multi-agents training by self-questioning","author":"xiong","year":"2020","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00444"},{"key":"ref23","first-page":"551","article-title":"Multimodal learning and reasoning for visual question answering","author":"ilievski","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref26","article-title":"Simple baseline for visual question answering","author":"zhou","year":"2015","journal-title":"arXiv 1512 02167"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1155"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00637"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.446"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451103"},{"key":"ref92","first-page":"4655","article-title":"Visual question answering with question representation update (QRU)","author":"li","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref91","article-title":"ABC-CNN: An attention based convolutional neural network for visual question answering","author":"chen","year":"2015","journal-title":"arXiv 1511 05960"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018102"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1349"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331186"},{"key":"ref57","first-page":"18","article-title":"Reducing language biases in visual question answering with visually-grounded question encoder","author":"kv","year":"2020","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref56","first-page":"8601","article-title":"Self-critical reasoning for robust visual question answering","author":"wu","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref55","first-page":"839","article-title":"RUBi: Reducing unimodal biases for visual question answering","author":"cad\u00e8ne","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref54","first-page":"1548","article-title":"Overcoming language priors in visual question answering with adversarial regularization","author":"ramakrishnan","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_1"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.145"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_9"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01039"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00680"},{"key":"ref14","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_10"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2908035"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00640"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_28"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref84","first-page":"2397","article-title":"Dynamic memory networks for visual and textual question answering","author":"xiong","year":"2016","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2708709"},{"key":"ref19","first-page":"2953","article-title":"Exploring models and data for image question answering","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref80","article-title":"Training recurrent answering units with joint loss minimization for VQA","author":"noh","year":"2016","journal-title":"arXiv 1606 03647"},{"key":"ref89","first-page":"275","article-title":"Chain of reasoning for visual question answering","author":"wu","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2963950"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2928144"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2902106"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.416"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"},{"key":"ref7","first-page":"361","article-title":"Multimodal residual learning for visual QA","author":"kim","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref49","first-page":"1571","article-title":"Bilinear attention networks","author":"kim","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref87","first-page":"1682","article-title":"A multi-world approach to question answering about real-world scenes based on uncertain input","author":"malinowski","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref88","first-page":"2672","article-title":"Exploring duality in visual question-driven top-down saliency","volume":"31","author":"he","year":"2020","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817340"},{"key":"ref46","first-page":"7218","article-title":"Co-attending free-form regions and detections with multi-modal multiplicative feature embedding for visual question answering","author":"lu","year":"2018","journal-title":"Proc AAAI Conf Artif Intell (AAAI)"},{"key":"ref45","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 (NeurIPS)"},{"key":"ref48","first-page":"10267","article-title":"In defense of grid features for visual question answering","author":"jiang","year":"2020","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01041"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/586"},{"key":"ref41","first-page":"7300","article-title":"Exploring human-like attention supervision in visual question answering","author":"qiao","year":"2018","journal-title":"Proc AAAI Conf Artif Intell (AAAI)"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.499"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9263394\/09491928.pdf?arnumber=9491928","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:56Z","timestamp":1652194256000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9491928\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":94,"URL":"https:\/\/doi.org\/10.1109\/tip.2021.3097180","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}