{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T08:00:39Z","timestamp":1767772839765,"version":"3.37.3"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004763","name":"Inner Mongolia Natural Science Foundation","doi-asserted-by":"publisher","award":["2020MS06006"],"award-info":[{"award-number":["2020MS06006"]}],"id":[{"id":"10.13039\/501100004763","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61763035"],"award-info":[{"award-number":["61763035"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9891887","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:56:04Z","timestamp":1664567764000},"page":"1-7","source":"Crossref","is-referenced-by-count":7,"title":["Transformer Gate Attention Model: An Improved Attention Model for Visual Question Answering"],"prefix":"10.1109","author":[{"given":"Haotian","family":"Zhang","sequence":"first","affiliation":[{"name":"Inner Mongolia University,Computer Science Department,Hohhot,China"}]},{"given":"Wei","family":"Wu","sequence":"additional","affiliation":[{"name":"Inner Mongolia University,Computer Science Department,Hohhot,China"}]}],"member":"263","reference":[{"key":"ref39","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"tsung-yi","year":"0","journal-title":"European Conference on Computer Vision"},{"key":"ref38","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref33","first-page":"299","article-title":"Dual attention networks for multimodal reasoning and matching","author":"hyeonseob","year":"0","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817340"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref35","first-page":"32","article-title":"Visual genome: Connecting language and vision using crowdsourced dense image annotations","volume":"123 1","author":"ranjay","year":"2017","journal-title":"International Journal of Computer Vision"},{"key":"ref34","first-page":"91","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"shaoqing","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref40","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref11","article-title":"Neural machine translation by jointly learning to align and translate","author":"dzmitry","year":"0","journal-title":"ArXiv Preprint"},{"key":"ref12","first-page":"2204","article-title":"Recurrent models of visual attention","volume":"27","author":"volodymyr","year":"2014","journal-title":"Advances in neural information processing systems"},{"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":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.499"},{"key":"ref15","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","volume":"29","author":"jiasen","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref16","first-page":"1564","article-title":"Bilinear attention networks","volume":"31","author":"kim","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00637"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref19","article-title":"An Improved Attention for Visual Question Answering","author":"tanzila","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref4","first-page":"201","article-title":"Stacked cross attention for image-text matching","author":"kuang-huei","year":"0","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref3","first-page":"154","article-title":"Adversarial cross-modal retrieval","author":"bokun","year":"0","journal-title":"Proceedings of the 25th ACM international conference on Multimedia"},{"key":"ref27","article-title":"Abc-cnn: An attention based convolutional neural network for visual question answering","author":"kan","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref5","first-page":"1508","article-title":"Cross-modal scene graph matching for relationship-aware image-text retrieval","author":"sijin","year":"0","journal-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision"},{"key":"ref29","article-title":"Multimodal compact bilinear pooling for visual question answering and visual grounding","author":"akira","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref7","article-title":"Lxmert: Learning cross-modality encoder representations from transformers","author":"hao","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref2","first-page":"77","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2599174"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00592"},{"key":"ref20","first-page":"6000","article-title":"Attention is all you need","volume":"30","author":"ashish","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9413078"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.9"},{"key":"ref41","article-title":"Learning to count objects in natural images for visual question answering","author":"yan","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref23","article-title":"Simple baseline for visual question answering","author":"bolei","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref26","first-page":"361","article-title":"Multimodal residual learning for visual qa","volume":"29","author":"jin-hwa","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref43","article-title":"Visualbert: A simple and performant baseline for vision and language","author":"li","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref25","article-title":"Are you talking to a machine? dataset and methods for multilingual image question","volume":"28","author":"haoyuan","year":"2015","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2022,7,18]]},"location":"Padua, Italy","end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09891887.pdf?arnumber=9891887","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,14]],"date-time":"2022-10-14T20:52:02Z","timestamp":1665780722000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9891887\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9891887","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}