{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T03:53:42Z","timestamp":1783655622452,"version":"3.55.0"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T00:00:00Z","timestamp":1643673600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T00:00:00Z","timestamp":1643673600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T00:00:00Z","timestamp":1643673600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2017YFB1300201"],"award-info":[{"award-number":["2017YFB1300201"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61622211"],"award-info":[{"award-number":["61622211"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61620106009"],"award-info":[{"award-number":["61620106009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61525206"],"award-info":[{"award-number":["61525206"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["WK2100100030"],"award-info":[{"award-number":["WK2100100030"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2022,2,1]]},"DOI":"10.1109\/tpami.2019.2909864","type":"journal-article","created":{"date-parts":[[2019,12,5]],"date-time":"2019-12-05T18:07:03Z","timestamp":1575569223000},"page":"710-722","source":"Crossref","is-referenced-by-count":95,"title":["Context-Aware Visual Policy Network for Fine-Grained Image Captioning"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2510-8993","authenticated-orcid":false,"given":"Zheng-Jun","family":"Zha","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8286-0105","authenticated-orcid":false,"given":"Daqing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanwang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1151-1792","authenticated-orcid":false,"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.128"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref5","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. 28th Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref7","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Xu"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00920"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1017\/s0140525x16001837"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1422953112"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.331"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10804"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.325"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_44"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.93"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.100"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref20","article-title":"Actor-critic sequence training for image captioning","author":"Zhang","year":"2017","journal-title":"in Proc. NIPS Workshop"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref23","article-title":"Sequence level training with recurrent neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ranzato"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/7902.7906"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.356"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.364"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_45"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022672621406"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00437"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3115\/1073445.1073478"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref39","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Translation Summarization","author":"Banerjee"},{"key":"ref40","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. ACL Workshop Text Summarization Branches Out","author":"Lin"},{"key":"ref41","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12266"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref47","article-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mao"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref49","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9674188\/08684270.pdf?arnumber=8684270","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T22:29:14Z","timestamp":1704839354000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8684270\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,1]]},"references-count":49,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2019.2909864","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,1]]}}}