{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T01:37:28Z","timestamp":1785893848025,"version":"3.56.0"},"reference-count":33,"publisher":"IEEE","license":[{"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\/ijcnn48605.2020.9206964","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":9,"title":["Bilinear Semi-Tensor Product Attention (BSTPA) model for visual question answering"],"prefix":"10.1109","author":[{"given":"Zongwen","family":"Bai","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University,School of Computer Science,Xi’an,CHINA,710072"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Li","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,School of Computer Science,Xi’an,CHINA,710072"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meili","family":"Zhou","sequence":"additional","affiliation":[{"name":"Shaanxi Key Laboratory of Intelligent Processing for Big Energy Data,Yan’an,CHINA,716000"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Di","family":"Li","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,School of Computer Science,Xi’an,CHINA,710072"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Wang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,School of Computer Science,Xi’an,CHINA,710072"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dawid","family":"Po\u0142ap","sequence":"additional","affiliation":[{"name":"Silesian University of Technology,Faculty of Applied Mathematics,Gliwice,POLAND,44-100"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marcin","family":"Wo\u017aniak","sequence":"additional","affiliation":[{"name":"Silesian University of Technology,Faculty of Applied Mathematics,Gliwice,POLAND,44-100"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","first-page":"13","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref32","article-title":"Vl-bert: Pre-training of generic visual-linguistic representations","author":"su","year":"2019"},{"key":"ref31","article-title":"Visualbert: A simple and performant baseline for vision and language","author":"li","year":"2019"},{"key":"ref30","article-title":"Unicoder-vl: A universal encoder for vision and language by cross-modal pre-training","author":"li","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.416"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.12"},{"key":"ref12","first-page":"1378","article-title":"Ask me anything: Dynamic memory networks for natural language processing","author":"kumar","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref13","first-page":"1137","article-title":"A neural probabilistic language model","volume":"3","author":"bengio","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref14","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013"},{"key":"ref15","article-title":"Improving language understanding by generative pre-training","author":"radford","year":"2018"},{"key":"ref16","first-page":"1564","article-title":"Bilinear attention networks","author":"kim","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref17","article-title":"Hyperbolic attention networks","author":"gulcehre","year":"2018"},{"key":"ref18","article-title":"One quivalence of matrices","author":"cheng","year":"2017"},{"key":"ref19","first-page":"361","article-title":"Bilinear classifiers for visual recognition","author":"pirsiavash","year":"2009","journal-title":"Advances in Neural Information Processing Systems 22 23Rd Annual Conference on Neural Information Processing Systems 2009"},{"key":"ref28","article-title":"Learning to count objects in natural images for visual question answering","author":"zhang","year":"2018"},{"key":"ref4","first-page":"219","article-title":"Semi-tensor compressed sensing for hyperspectral image","author":"daizhan","year":"2003","journal-title":"Acta Math Appl Sinica"},{"key":"ref27","article-title":"Tips and tricks for visual question answering:learning form the 2017 challenge","author":"danien tency","year":"2017"},{"key":"ref3","article-title":"On Semitensor Product of Matrices and its Applications","author":"devlin","year":"2018"},{"key":"ref6","article-title":"Abc-cnn: An attention based convolutional neural network for visual question answering","author":"chen","year":"2015"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref5","first-page":"4995","article-title":"Visual7w: Grounded question answering in images","author":"zhu","year":"2016","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref8","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.500"},{"key":"ref1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref20","first-page":"361","article-title":"Multimodal residual learning for visual qa","author":"kim","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref22","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"ref21","first-page":"901","article-title":"Weight normalization: A simple reparameterization to accelerate training of deep neural networks","author":"salimans","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref24","article-title":"Hadamard product for low-rank bilinear pooling","author":"kim","year":"2016"},{"key":"ref23","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref26","article-title":"Bottom-up -up and top-down attention for image caption and visual question answering","author":"peter","year":"2017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817340"}],"event":{"name":"2020 International Joint Conference on Neural Networks (IJCNN)","location":"Glasgow, UK","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\/09206964.pdf?arnumber=9206964","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T20:02:51Z","timestamp":1784145771000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9206964\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/ijcnn48605.2020.9206964","relation":{},"subject":[],"published":{"date-parts":[[2020,7]]}}}