{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T12:38:05Z","timestamp":1782391085647,"version":"3.54.5"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,10]]},"DOI":"10.1109\/icpr48806.2021.9413078","type":"proceedings-article","created":{"date-parts":[[2021,5,6]],"date-time":"2021-05-06T02:15:54Z","timestamp":1620267354000},"page":"1173-1180","source":"Crossref","is-referenced-by-count":6,"title":["Answer-checking in Context: A Multi-modal Fully Attention Network for Visual Question Answering"],"prefix":"10.1109","author":[{"given":"Hantao","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deep","family":"Yap","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng-Ming","family":"Chiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.121"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref30","article-title":"Bilinear attention networks for vizwiz challenge","author":"kim","year":"2018","journal-title":"ECCV workshop"},{"key":"ref36","author":"kervadec","year":"2020","journal-title":"Estimating semantic structure for the vqa answer space"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.642"},{"key":"ref34","author":"shi","year":"2020","journal-title":"Multi-layer content interaction through quaternion product for visual question answering"},{"key":"ref10","article-title":"Finding the evidence: Localization-aware answer prediction for text visual question answering","author":"han","year":"2010","journal-title":"ArXiv"},{"key":"ref11","author":"sun","year":"2019","journal-title":"Videobert A joint model for video and language representation learning"},{"key":"ref12","author":"huang","year":"2019","journal-title":"Attention on attention for image captioning"},{"key":"ref13","first-page":"1564","article-title":"Bilinear attention networks","author":"kim","year":"2018","journal-title":"NIPS"},{"key":"ref14","first-page":"91","article-title":"Faster R-CNN: Towards realtime object detection with region proposal networks","author":"ren","year":"2015","journal-title":"NIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref17","author":"face","year":"2019","journal-title":"pytorch-transformers"},{"key":"ref18","author":"joulin","year":"2016","journal-title":"Bag of tricks for efficient text classification"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref4","author":"li","year":"2019","journal-title":"Visualbert A simple and performant baseline for vision and language"},{"key":"ref27","author":"su","year":"2020","journal-title":"Vl-bert Pre-training of generic visual-linguistic representations"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00680"},{"key":"ref6","first-page":"5825","article-title":"Multi-modality latent interaction network for visual question answering","author":"gao","year":"2019","journal-title":"ICCV"},{"key":"ref29","first-page":"841","article-title":"Rubi: Reducing unimodal biases for visual question answering","author":"cadene","year":"2019","journal-title":"NIPS"},{"key":"ref5","first-page":"13","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"2019","journal-title":"NIPS"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref2","author":"devlin","year":"2018","journal-title":"BERT Pre-training of deep bidirectional transformers for language understanding"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref1","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref20","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"ECCV"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00522"},{"key":"ref24","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref23","author":"paszke","year":"2017","journal-title":"Automatic differentiation in pytorch"},{"key":"ref26","author":"yu","year":"2019","journal-title":"Multimodal unified attention networks for vision-and-language interactions"},{"key":"ref25","author":"carion","year":"2020","journal-title":"End-to-End Object Detection with Transformers"}],"event":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","location":"Milan, Italy","start":{"date-parts":[[2021,1,10]]},"end":{"date-parts":[[2021,1,15]]}},"container-title":["2020 25th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9411940\/9411911\/09413078.pdf?arnumber=9413078","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:53Z","timestamp":1652197253000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413078\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,10]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icpr48806.2021.9413078","relation":{},"subject":[],"published":{"date-parts":[[2021,1,10]]}}}