{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,30]],"date-time":"2025-08-30T17:00:24Z","timestamp":1756573224325,"version":"3.37.3"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T00:00:00Z","timestamp":1665878400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T00:00:00Z","timestamp":1665878400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,10,16]]},"DOI":"10.1109\/icip46576.2022.9897277","type":"proceedings-article","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T21:27:24Z","timestamp":1667510844000},"page":"4193-4197","source":"Crossref","is-referenced-by-count":5,"title":["Ques-to-Visual Guided Visual Question Answering"],"prefix":"10.1109","author":[{"given":"Xiangyu","family":"Wu","sequence":"first","affiliation":[{"name":"Nanjing University of Science and Technology,School of Computer Science and Engineering,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianfeng","family":"Lu","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology,School of Computer Science and Engineering,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuanfeng","family":"Li","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology,School of Computer Science and Engineering,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fengchao","family":"Xiong","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology,School of Computer Science and Engineering,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00444"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref3","article-title":"Bilinear attention networks","volume-title":"NIPS","volume":"31","author":"Kim"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00637"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00680"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00181"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00220"},{"article-title":"Vl-bert: Pre-training of generic visual-linguistic representations","volume-title":"ICLR","author":"Su","key":"ref8"},{"key":"ref9","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","volume-title":"ICML","author":"Kim"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00161"},{"article-title":"Text to image generation with semantic-spatial aware gan","year":"2021","author":"Hu","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26313-2_33"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413977"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053595"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_25"}],"event":{"name":"2022 IEEE International Conference on Image Processing (ICIP)","start":{"date-parts":[[2022,10,16]]},"location":"Bordeaux, France","end":{"date-parts":[[2022,10,19]]}},"container-title":["2022 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9897158\/9897159\/09897277.pdf?arnumber=9897277","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T20:49:28Z","timestamp":1705956568000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9897277\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,16]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icip46576.2022.9897277","relation":{},"subject":[],"published":{"date-parts":[[2022,10,16]]}}}