{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T21:42:44Z","timestamp":1780782164483,"version":"3.54.1"},"reference-count":50,"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":[{"name":"Nature Science Foundation of China","award":["U1705262"],"award-info":[{"award-number":["U1705262"]}]},{"name":"Nature Science Foundation of China","award":["61772443"],"award-info":[{"award-number":["61772443"]}]},{"name":"Nature Science Foundation of China","award":["61572410"],"award-info":[{"award-number":["61572410"]}]},{"name":"Nature Science Foundation of China","award":["61802324"],"award-info":[{"award-number":["61802324"]}]},{"name":"Nature Science Foundation of China","award":["61702136"],"award-info":[{"award-number":["61702136"]}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2017YFC0113000"],"award-info":[{"award-number":["2017YFC0113000"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2016YFB1001503"],"award-info":[{"award-number":["2016YFB1001503"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"publisher","award":["2017J01125"],"award-info":[{"award-number":["2017J01125"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"publisher","award":["2018J01106"],"award-info":[{"award-number":["2018J01106"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013064","name":"Key Research and Development Program of Jiangxi Province","doi-asserted-by":"publisher","award":["20171ACH80022"],"award-info":[{"award-number":["20171ACH80022"]}],"id":[{"id":"10.13039\/501100013064","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.2019.2956699","type":"journal-article","created":{"date-parts":[[2019,11,29]],"date-time":"2019-11-29T21:10:55Z","timestamp":1575061855000},"page":"697-709","source":"Crossref","is-referenced-by-count":13,"title":["Plenty is Plague: Fine-Grained Learning for Visual Question Answering"],"prefix":"10.1109","volume":"44","author":[{"given":"Yiyi","family":"Zhou","sequence":"first","affiliation":[{"name":"Media Analytics and Computing Lab, Informatics and Communication Engineering Department, School of Informatics, Xiamen University, Xiamen, Fujian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9163-2932","authenticated-orcid":false,"given":"Rongrong","family":"Ji","sequence":"additional","affiliation":[{"name":"Media Analytics and Computing Lab, Department of Artificial Intelligence, School of Informatics, Xiamen University, Xiamen, Fujian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3912-9306","authenticated-orcid":false,"given":"Xiaoshuai","family":"Sun","sequence":"additional","affiliation":[{"name":"Media Analytics and Computing Lab, Department of Artificial Intelligence, School of Informatics, Xiamen University, Xiamen, Fujian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5606-7122","authenticated-orcid":false,"given":"Jinsong","family":"Su","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, Fujian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1294-8283","authenticated-orcid":false,"given":"Deyu","family":"Meng","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, The Macau University of Science and Technology, Macao"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4971-590X","authenticated-orcid":false,"given":"Yue","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Software, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8648-8718","authenticated-orcid":false,"given":"Chunhua","family":"Shen","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Adelaide, Adelaide, SA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","volume":"37","author":"Xu"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.41"},{"key":"ref6","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"issue":"55\/66","key":"ref9","article-title":"Active learning literature survey","volume":"52","author":"Settles","year":"2010"},{"key":"ref10","article-title":"Making the V in VQA matter: Elevating the role of image understanding in visual question answering","author":"Goyal","year":"2016","journal-title":"arXiv:1612.00837"},{"key":"ref11","first-page":"1189","article-title":"Self-paced learning for latent variable models","volume-title":"Proc. 23rd Int. Conf. Neural Inf. Process. Syst.","author":"Pawan Kumar"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00444"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1181"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10442"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.145"},{"key":"ref17","article-title":"Structured attention networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kim"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00801"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_28"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.500"},{"key":"ref21","article-title":"The VQA-machine: Learning how to use existing vision algorithms to answer new questions","author":"Wang","year":"2016","journal-title":"arXiv:1612.05386"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref24","article-title":"Pythia v0. 1: The winning entry to the VQA challenge 2018,","author":"Jiang","year":"2018","journal-title":"arXiv: 1807.09956"},{"key":"ref25","first-page":"361","article-title":"Multimodal residual learning for visual QA","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref26","article-title":"Hadamard product for low-rank bilinear pooling","author":"Kim","year":"2016","journal-title":"arXiv:1610.04325"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref28","article-title":"Hadamard product for low-rank bilinear pooling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kim"},{"key":"ref29","first-page":"2078","article-title":"Self-paced learning with diversity","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Jiang"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9608"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-2099-5_1"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3115\/1613715.1613855"},{"issue":"Nov","key":"ref33","first-page":"45","article-title":"Support vector machine active learning with applications to text classification","volume":"2","author":"Tong","year":"2001","journal-title":"J. Mach. Learn. Res."},{"key":"ref34","article-title":"Active learning with support vector machines","author":"Vlachos","year":"2004"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00009"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref37","first-page":"1008","article-title":"Actor-critic algorithms","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Konda"},{"key":"ref38","article-title":"An actor-critic algorithm for sequence prediction","author":"Bahdanau","year":"2016","journal-title":"arXiv:1607.07086"},{"key":"ref39","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref40","article-title":"Sample efficient actor-critic with experience replay","author":"Wang","year":"2016","journal-title":"arXiv:1611.01224"},{"key":"ref41","article-title":"Learning what data to learn","author":"Fan","year":"2017"},{"key":"ref42","first-page":"301","article-title":"Learning algorithms for active learning","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Bachman"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1174"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/bf00115009"},{"key":"ref45","first-page":"759","article-title":"Eligibility traces for off-policy policy evaluation","volume-title":"Proc. 17th Int. Conf. Mach. Learn.","author":"Precup"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.506"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00522"},{"key":"ref48","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv:1504.00325"},{"key":"ref49","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref50","article-title":"Visual genome: Connecting language and vision using crowdsourced dense image annotations","author":"Krishna","year":"2016","journal-title":"arXiv:1602.07332"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9674188\/08918052.pdf?arnumber=8918052","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T17:40:10Z","timestamp":1747849210000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8918052\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,1]]},"references-count":50,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2019.2956699","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]]}}}