{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T09:09:03Z","timestamp":1777626543361,"version":"3.51.4"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"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":[[2020,7]]},"DOI":"10.1109\/ijcnn48605.2020.9206679","type":"proceedings-article","created":{"date-parts":[[2020,9,29]],"date-time":"2020-09-29T20:40:33Z","timestamp":1601412033000},"page":"1-8","source":"Crossref","is-referenced-by-count":2,"title":["Component Analysis for Visual Question Answering Architectures"],"prefix":"10.1109","author":[{"given":"Camila","family":"Kolling","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonatas","family":"Wehrmann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rodrigo C.","family":"Barros","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"20","article-title":"Deep attention neural tensor network for visual question answering","author":"bai","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref33","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1145\/3019612.3019641","article-title":"Convolutions through time for multilabel movie genre classification","author":"wehrmann","year":"2017","journal-title":"SAC 2017"},{"key":"ref31","first-page":"2384","article-title":"Fast and efficient text classification with class-based embeddings","author":"wehrmann","year":"2017","journal-title":"IJCNN 2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00805"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00757"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817340"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.499"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref28","first-page":"2397","article-title":"Dynamic memory networks for visual and textual question answering","author":"xiong","year":"2016","journal-title":"ICML"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_25"},{"key":"ref29","article-title":"M2: Meshed-memory transformer for image captioning","author":"cornia","year":"2019","journal-title":"arXiv preprint arXiv 1912 08226"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00209"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018102"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.41"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.9"},{"key":"ref25","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"2016","journal-title":"NIPS"},{"key":"ref50","article-title":"Deep learning using rectified linear units (relu)","author":"agarap","year":"2018","journal-title":"arXiv preprint arXiv 1803 08375"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35289-8_3"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00444"},{"key":"ref53","first-page":"551","article-title":"Multimodal learning and reasoning for visual question answering","author":"ilievski","year":"2017","journal-title":"NIPS 2017"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1234"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2661334.2661407"},{"key":"ref11","first-page":"451","article-title":"Ask, attend and answer: Exploring questionguided spatial attention for visual question answering","author":"xu","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CRV.2018.00016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref13","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013","journal-title":"arXiv preprint arXiv 1301 3781"},{"key":"ref14","first-page":"3294","article-title":"Skip-thought vectors","author":"kiros","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref15","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv preprint arXiv 1810 04805"},{"key":"ref16","first-page":"91","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref17","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv preprint arXiv 1409 1556"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref3","first-page":"2422","article-title":"Mind’s eye: A recurrent visual representation for image caption generation","author":"chen","year":"2015","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref6","first-page":"7718","article-title":"Adaptive cross-modal embeddings for image-text alignment","author":"wehrmann","year":"2018","journal-title":"AAAI 2020"},{"key":"ref5","article-title":"Attention on attention: Architectures for visual question answering (vqa)","author":"singh","year":"2018","journal-title":"arXiv preprint arXiv 1803 07724"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1109\/MMUL.2014.29","article-title":"Joint video and text parsing for understanding events and answering queries","volume":"21","author":"tu","year":"2014","journal-title":"IEEE Multimedia"},{"key":"ref7","article-title":"Languageagnostic visual-semantic embeddings","author":"wehrmann","year":"2019","journal-title":"ICCV 2019"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1866029.1866080"},{"key":"ref46","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref45","article-title":"Evalai: Towards better evaluation systems for ai agents","author":"yadav","year":"2019","journal-title":"arXiv preprint arXiv 1902 05023"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref42","article-title":"Hadamard product for low-rank bilinear pooling","author":"kim","year":"2016","journal-title":"arXiv preprint arXiv 1610 09756"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref44","first-page":"740","article-title":"Microsoft coco: Common objects in´ context","author":"lin","year":"2014","journal-title":"European Conference on Computer Vision"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"}],"event":{"name":"2020 International Joint Conference on Neural Networks (IJCNN)","location":"Glasgow, United Kingdom","start":{"date-parts":[[2020,7,19]]},"end":{"date-parts":[[2020,7,24]]}},"container-title":["2020 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9200848\/9206590\/09206679.pdf?arnumber=9206679","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T17:58:03Z","timestamp":1656439083000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9206679\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/ijcnn48605.2020.9206679","relation":{},"subject":[],"published":{"date-parts":[[2020,7]]}}}