{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,23]],"date-time":"2025-04-23T05:30:47Z","timestamp":1745386247357,"version":"3.28.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"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":[[2023,6,18]]},"DOI":"10.1109\/ijcnn54540.2023.10191453","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:30:03Z","timestamp":1690997403000},"page":"1-8","source":"Crossref","is-referenced-by-count":2,"title":["Improving Visual Question Answering by Multimodal Gate Fusion Network"],"prefix":"10.1109","author":[{"given":"Shenxiang","family":"Xiang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Zhejiang Sci-Tech University,Hangzhou,China,310018"}]},{"given":"Qiaohong","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Zhejiang Sci-Tech University,Hangzhou,China,310018"}]},{"given":"Xian","family":"Fang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Zhejiang Sci-Tech University,Hangzhou,China,310018"}]},{"given":"Menghao","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Zhejiang Sci-Tech University,Hangzhou,China,310018"}]}],"member":"263","reference":[{"key":"ref13","first-page":"577","article-title":"Attention-based models for speech recognition","volume":"28","author":"chorowski","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref12","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref37","article-title":"Image as a foreign language: Beit pretraining for all vision and vision-language tasks","author":"wang","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref14","article-title":"Abc-cnn: An attention based convolutional neural network for visual question answering","author":"chen","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref31","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","volume":"29","author":"lu","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-010-0182-0"},{"key":"ref11","first-page":"2204","article-title":"Recurrent models of visual attention","volume":"27","author":"mnih","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref33","first-page":"4655","article-title":"Visual question answering with question representation update (qru)","volume":"29","author":"li","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref10","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892275"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533994"},{"key":"ref17","first-page":"1571","article-title":"Bilinear attention networks","volume":"31","author":"kim","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817340"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00181"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref25","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017216"},{"key":"ref22","first-page":"2953","article-title":"Exploring models and data for image question answering","volume":"28","author":"ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref21","first-page":"2425","article-title":"Vqa: Visual question answering","author":"antol","year":"2015","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref27","first-page":"91","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892392"},{"key":"ref7","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","author":"kim","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892775"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9891887"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413977"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533855"}],"event":{"name":"2023 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2023,6,18]]},"location":"Gold Coast, Australia","end":{"date-parts":[[2023,6,23]]}},"container-title":["2023 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10190990\/10190992\/10191453.pdf?arnumber=10191453","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T17:43:36Z","timestamp":1692639816000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10191453\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/ijcnn54540.2023.10191453","relation":{},"subject":[],"published":{"date-parts":[[2023,6,18]]}}}