{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T15:05:36Z","timestamp":1771599936261,"version":"3.50.1"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"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","award":["61772510"],"award-info":[{"award-number":["61772510"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Young Top-Notch Talent Program of Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["QYZDB-SSWJSC015"],"award-info":[{"award-number":["QYZDB-SSWJSC015"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2021,2]]},"DOI":"10.1109\/tcyb.2019.2914351","type":"journal-article","created":{"date-parts":[[2019,5,17]],"date-time":"2019-05-17T20:00:21Z","timestamp":1558123221000},"page":"913-926","source":"Crossref","is-referenced-by-count":46,"title":["Vision-to-Language Tasks Based on Attributes and Attention Mechanism"],"prefix":"10.1109","volume":"51","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2924-946X","authenticated-orcid":false,"given":"Xuelong","family":"Li","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7349-1483","authenticated-orcid":false,"given":"Aihong","family":"Yuan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7037-5188","authenticated-orcid":false,"given":"Xiaoqiang","family":"Lu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref32","first-page":"3567","article-title":"Learning to answer questions from image using convolutional neural network","author":"ma","year":"2016","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.11"},{"key":"ref30","first-page":"2296","article-title":"Are you talking to a machine? Dataset and methods for multilingual image question answering","author":"gao","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","article-title":"Show, ask, attend, and answer: A strong baseline for visual question answering","volume":"abs 1704 3162","author":"kazemi","year":"2017","journal-title":"CoRR"},{"key":"ref36","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref34","first-page":"451","article-title":"Ask, attend and answer: Exploring question-guided spatial attention for visual question answering","author":"xu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref28","first-page":"1682","article-title":"A multi-world approach to question answering about real-world scenes based on uncertain input","author":"malinowski","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2642953"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1109\/MMUL.2014.29","article-title":"Joint video and text parsing for understanding events and answering queries","volume":"21","author":"tu","year":"2014","journal-title":"IEEE Multimedia"},{"key":"ref2","first-page":"4176","article-title":"Attention correctness in neural image captioning","author":"liu","year":"2017","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.681"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2708709"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2761775"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2706264"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2867198"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref25","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.662"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/307"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015332"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123328"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref15","first-page":"1","article-title":"Deep captioning with multimodal recurrent neural networks (M-RNN)","author":"mao","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref16","first-page":"2953","article-title":"Exploring models and data for image question answering","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.446"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.29"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CITS.2016.7546397"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.499"},{"key":"ref5","first-page":"2397","article-title":"Dynamic memory networks for visual and textual question answering","author":"xiong","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3115\/981732.981751"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.339"},{"key":"ref46","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume":"29","author":"banerjee","year":"2005","journal-title":"Proc ACL Workshop Intrinsic Extrinsic Eval Measures Mach Transl Summarization"},{"key":"ref45","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref48","article-title":"ABC-CNN: An attention based convolutional neural network for visual question answering","volume":"abs 1511 5960","author":"chen","year":"2015","journal-title":"CoRR"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref44","first-page":"4188","article-title":"Framing image description as a ranking task: Data, models and evaluation metrics (extended abstract)","author":"hodosh","year":"2015","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/9325889\/08718014.pdf?arnumber=8718014","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:35Z","timestamp":1652194415000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8718014\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2]]},"references-count":50,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2019.2914351","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2]]}}}