{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T05:31:54Z","timestamp":1775194314633,"version":"3.50.1"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61971296,U19A2078,61836011,61801315"],"award-info":[{"award-number":["61971296,U19A2078,61836011,61801315"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/CAA J. Autom. Sinica"],"published-print":{"date-parts":[[2021,7]]},"DOI":"10.1109\/jas.2020.1003402","type":"journal-article","created":{"date-parts":[[2021,5,31]],"date-time":"2021-05-31T20:38:02Z","timestamp":1622493482000},"page":"1243-1252","source":"Crossref","is-referenced-by-count":21,"title":["Global-Attention-Based Neural Networks for Vision Language Intelligence"],"prefix":"10.1109","volume":"8","author":[{"given":"Pei","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingjie","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dezhong","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dapeng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_31"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.443"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2642953"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.111"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref36","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"Proc 13th European Conf Computer Vision"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01042"},{"key":"ref40","first-page":"311","article-title":"Bleu: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc 40th Annu Meet Association for Computational Linguistics"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc 28th Int Conf Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref15","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref16","article-title":"BERT: Pretraining of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1271"},{"key":"ref18","author":"soh","year":"2016","journal-title":"Learning cnn-lstm architectures for image caption generation"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.11198","article-title":"Reference based LSTM for image captioning","author":"chen","year":"2017","journal-title":"Proc 31st AAAI Conf Artificial Intelligence"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2894139"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.127"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref8","first-page":"8940","article-title":"Adaptively aligned image captioning via adaptive attention time","author":"huang","year":"2019","journal-title":"Proc Advances in Neural Information Processing Systems"},{"key":"ref7","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc 31st Int Conf Neural Information Processing Systems"},{"key":"ref2","first-page":"595","article-title":"Multimodal neural language models","author":"kiros","year":"2014","journal-title":"Proc 31st Int Conf Machine Learning"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00227"},{"key":"ref1","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc 32nd Int Conf Machine Learning"},{"key":"ref20","article-title":"A comparison of transformer and recurrent neural networks on multilingual neural machine translation","author":"lakew","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref21","article-title":"Language models with transformers","author":"wang","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref42","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Proc Workship on Text Summarization Branches Out"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref23","article-title":"Image captioning: Transforming objects into words","author":"herdade","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref43","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"2015","journal-title":"Proc 28th Int Conf Neural Information Processing Systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"}],"container-title":["IEEE\/CAA Journal of Automatica Sinica"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570654\/9444539\/09205690.pdf?arnumber=9205690","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,29]],"date-time":"2022-12-29T05:49:45Z","timestamp":1672292985000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9205690\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7]]},"references-count":43,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/jas.2020.1003402","relation":{},"ISSN":["2329-9266","2329-9274"],"issn-type":[{"value":"2329-9266","type":"print"},{"value":"2329-9274","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7]]}}}