{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T01:28:40Z","timestamp":1755998920954,"version":"3.37.3"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747541","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"4403-4407","source":"Crossref","is-referenced-by-count":3,"title":["Mixed Knowledge Relation Transformer for Image Captioning"],"prefix":"10.1109","author":[{"given":"Tianyu","family":"Chen","sequence":"first","affiliation":[{"name":"Guangxi Normal University,Guangxi Key Lab of Multi-source Information Mining and Security,Guilin,China,541004"}]},{"given":"Zhixin","family":"Li","sequence":"additional","affiliation":[{"name":"Guangxi Normal University,Guangxi Key Lab of Multi-source Information Mining and Security,Guilin,China,541004"}]},{"given":"Jiahui","family":"Wei","sequence":"additional","affiliation":[{"name":"Guangxi Normal University,Guangxi Key Lab of Multi-source Information Mining and Security,Guilin,China,541004"}]},{"given":"Tiantao","family":"Xian","sequence":"additional","affiliation":[{"name":"Guangxi Normal University,Guangxi Key Lab of Multi-source Information Mining and Security,Guilin,China,541004"}]}],"member":"263","reference":[{"key":"ref10","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2020.103068"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-020-05919-y"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3439734"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref16","first-page":"10971","article-title":"Xlinear attention networks for image captioning","author":"pan","year":"2020","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"1655","DOI":"10.1609\/aaai.v35i2.16258","article-title":"Improving image captioning by leveraging intra-and interlayer global representation in transformer network","volume":"35","author":"ji","year":"2021","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00271"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00902"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref5","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/S0016-0032(96)00063-4"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v35i3.16328","article-title":"Dual-level collaborative transformer for image captioning","author":"luo","year":"2021"},{"article-title":"Image captioning: Transforming objects into words","year":"2019","author":"herdade","key":"ref1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747541.pdf?arnumber=9747541","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T03:19:49Z","timestamp":1727061589000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747541\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747541","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}