{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:39:49Z","timestamp":1730266789562,"version":"3.28.0"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"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":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10651146","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["HKFNet: Fine-Grained External Knowledge Fusion for Fact-Based Visual Question Answering"],"prefix":"10.1109","author":[{"given":"Bojin","family":"Li","sequence":"first","affiliation":[{"name":"Shanghai University,School of Computer Engineering and Science,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Sun","sequence":"additional","affiliation":[{"name":"Shanghai University,School of Computer Engineering and Science,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xue","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai University,School of Computer Engineering and Science,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luo","family":"Xiangfeng","sequence":"additional","affiliation":[{"name":"Shanghai University,School of Computer Engineering and Science,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/int.22701"},{"key":"ref3","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","first-page":"32897","article-title":"Vlmo: Unified vision-language pre-training with mixture-of-modality-experts","volume":"35","author":"Bao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413943"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.44"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2629489"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1023\/B:BTTJ.0000047600.45421.6d"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/153"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-88361-4_9"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.9"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref15","article-title":"Hierarchical question-image coattention for visual question answering","volume":"29","author":"Lu","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref18","article-title":"How much can clip benefit visionand-language tasks?","volume":"3","author":"Shen","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00206"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548122"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00501"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.517"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20174"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20215"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018876"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/179"},{"key":"ref28","article-title":"Wikipedia the free encyclopedia","volume":"13","author":"Scale","year":"2009","journal-title":"Last modified on Oct"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450042"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/597"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01046"},{"article-title":"An empirical evaluation of visual question answering for novel objects","volume-title":"The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).(cited on pages 26 and 73)","author":"Patro","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00569"},{"article-title":"Visual question answering with prior class semantics","year":"2020","author":"Shevchenko","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref38","article-title":"Supervised sequence labelling with recurrent neural networks","volume-title":"Ph.D. dissertation","author":"Kawakami","year":"2008"},{"article-title":"Graph attention networks","year":"2017","author":"Veli\u010dkovi\u0107","key":"ref39"},{"key":"ref40","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":"ref41","article-title":"Bilinear attention networks","volume":"31","author":"Kim","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3318949"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547870"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2024,6,30]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10651146.pdf?arnumber=10651146","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T05:59:12Z","timestamp":1725947952000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10651146\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10651146","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}