{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T08:27:37Z","timestamp":1765268857443,"version":"3.37.3"},"reference-count":26,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62061146002,61921003"],"award-info":[{"award-number":["62061146002,61921003"]}],"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\/icme52920.2022.9859639","type":"proceedings-article","created":{"date-parts":[[2022,8,26]],"date-time":"2022-08-26T19:45:18Z","timestamp":1661543118000},"page":"1-6","source":"Crossref","is-referenced-by-count":5,"title":["Multi-Head Attention Fusion Network for Visual Question Answering"],"prefix":"10.1109","author":[{"given":"Haiyang","family":"Zhang","sequence":"first","affiliation":[{"name":"School of computer science, Beijing University of Posts and Telecommunications,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruoyu","family":"Li","sequence":"additional","affiliation":[{"name":"School of computer science, Beijing University of Posts and Telecommunications,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of computer science, Beijing University of Posts and Telecommunications,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","first-page":"91","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"NIPS"},{"key":"ref15","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"2016","journal-title":"NIPS"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref17","article-title":"Hadamard product for low-rank bilinear pooling","author":"kim","year":"2017","journal-title":"ICLRE"},{"key":"ref18","first-page":"1839","article-title":"Multi-modal fac-torized bilinear pooling with co-attention learning for visual question answering","author":"yu","year":"2017","journal-title":"ICCV"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-010-0182-0"},{"key":"ref4","first-page":"12637","article-title":"To-wards accurate text-based image captioning with con-tent diversity exploration","author":"xu","year":"2021","journal-title":"CVPR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093548"},{"key":"ref5","first-page":"1571","article-title":"Bilinear attention net-works","author":"kim","year":"2018","journal-title":"NIPS"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.499"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.151"},{"key":"ref2","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"ICML"},{"key":"ref9","first-page":"6087","article-title":"Improved fusion of vi-sual and language representations by dense symmetric co-attention for visual question answering","author":"nguyen","year":"2018","journal-title":"CVPR"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref21","first-page":"4655","article-title":"Visual question answering with question representation update (QRU)","author":"li","year":"2016","journal-title":"NIPS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"ref23","first-page":"12113","article-title":"Deep multimodal multilinear fusion with high-order polynomial pooling","author":"hou","year":"2019","journal-title":"NIPS"},{"key":"ref26","first-page":"414","article-title":"Trrnet: Tiered re-lation reasoning for compositional visual question an-swering","author":"yang","year":"2020","journal-title":"ECCV"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00680"}],"event":{"name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2022,7,18]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2022,7,22]]}},"container-title":["2022 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9859562\/9858923\/09859639.pdf?arnumber=9859639","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,9]],"date-time":"2023-02-09T18:40:24Z","timestamp":1675968024000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9859639\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icme52920.2022.9859639","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}