{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T18:00:18Z","timestamp":1769536818432,"version":"3.49.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446024","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T14:56:31Z","timestamp":1710773791000},"page":"4430-4434","source":"Crossref","is-referenced-by-count":0,"title":["Think as People: Context-Driven Multi-Image News Captioning with Adaptive Dual Attention"],"prefix":"10.1109","author":[{"given":"Qiang","family":"Yang","sequence":"first","affiliation":[{"name":"King Abdullah University of Science and Technology,Jeddah,Saudi Arabia"}]},{"given":"Xiaodong","family":"Wu","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology,Jeddah,Saudi Arabia"}]},{"given":"Xiuying","family":"Chen","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology,Jeddah,Saudi Arabia"}]},{"given":"Xin","family":"Gao","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology,Jeddah,Saudi Arabia"}]},{"given":"Xiangliang","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Notre Dame,Indiana,United States"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964299"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SCIS-ISIS.2018.00134"},{"key":"ref4","article-title":"Chinese image caption generation via visual attention and topic modeling","author":"Liu","year":"2020","journal-title":"IEEE TOC"},{"key":"ref5","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume-title":"ICML","author":"Xu"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2019.102178"},{"key":"ref9","first-page":"11137","article-title":"Image captioning: Transforming objects into words","volume-title":"NIPS","author":"Herdade"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413576"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01305"},{"key":"ref13","article-title":"Neural caption generation for news images","volume-title":"LREC","author":"Batra"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01275"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.496"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.419"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.542"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3301279"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.752"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591630"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1037\/0096-1523.19.4.878"},{"key":"ref22","first-page":"116618","article-title":"Salient object detection based on global to local visual search guidance","volume":"102","author":"Wu","year":"2022","journal-title":"Signal Processing: Image Communication"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2028"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref27","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","volume-title":"ACL","author":"Papineni"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref29","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446024.pdf?arnumber=10446024","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T04:33:35Z","timestamp":1769488415000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446024\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446024","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}