{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T07:59:53Z","timestamp":1771919993765,"version":"3.50.1"},"reference-count":72,"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\/100007567","name":"City University of Hong Kong","doi-asserted-by":"publisher","award":["7004682"],"award-info":[{"award-number":["7004682"]}],"id":[{"id":"10.13039\/100007567","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007567","name":"City University of Hong Kong","doi-asserted-by":"publisher","award":["7005218"],"award-info":[{"award-number":["7005218"]}],"id":[{"id":"10.13039\/100007567","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007065","name":"Nvidia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007065","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.2020.3013834","type":"journal-article","created":{"date-parts":[[2020,8,4]],"date-time":"2020-08-04T21:36:52Z","timestamp":1596577012000},"page":"1035-1049","source":"Crossref","is-referenced-by-count":30,"title":["On Diversity in Image Captioning: Metrics and Methods"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1562-8098","authenticated-orcid":false,"given":"Qingzhong","family":"Wang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8198-1629","authenticated-orcid":false,"given":"Jia","family":"Wan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2886-2513","authenticated-orcid":false,"given":"Antoni B.","family":"Chan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.445"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref7","first-page":"1","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","first-page":"2369","article-title":"Review networks for caption generation","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54193-8_7"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.127"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.29"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.140"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.138"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00583"},{"key":"ref19","article-title":"CNN+CNN: Convolutional decoders for image captioning","author":"Wang","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.100"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.323"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_2"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00728"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_21"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2824816"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref28","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. ACL Workshop","author":"Lin"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00608"},{"key":"ref33","first-page":"5758","article-title":"Diverse and accurate image description using a variational auto-encoder with an additive gaussian encoding space","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1037\/h0070888"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300017467"},{"key":"ref36","first-page":"419","article-title":"Learning determinantal point processes","volume-title":"Proc. Int. Conf. Uncertainty Artif. Intell.","author":"Kulesza"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00432"},{"key":"ref38","first-page":"957","article-title":"From word embeddings to document distances","volume-title":"Proc. 32nd Int. Conf. Int. Conf. Mach. Learn.","author":"Kusner"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-1019"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3295748"},{"key":"ref41","first-page":"220","article-title":"Composing simple image descriptions using Web-scale n-grams","volume-title":"Proc. 15th Conf. Comput. Natural Lang. Learn.","author":"Li"},{"key":"ref42","first-page":"1","article-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","volume-title":"Proc. ICLR","author":"Mao"},{"key":"ref43","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume-title":"Proc. NIPS","author":"Krizhevsky"},{"key":"ref44","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. ICLR","author":"Simonyan"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref49","first-page":"1243","article-title":"Convolutional sequence to sequence learning","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Gehring"},{"key":"ref50","first-page":"933","article-title":"Language modeling with gated convolutional networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Dauphin"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1083"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.128"},{"key":"ref53","first-page":"1","article-title":"Contrastive learning for image captioning","volume-title":"Proc. 31st Conf. Neural Inf. Process. Syst.","author":"Dai"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01071"},{"key":"ref55","first-page":"2672","article-title":"Generative adversarial nets","volume-title":"Proc. NIPS","author":"Goodfellow"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00859"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01095"},{"key":"ref58","first-page":"2957","article-title":"Diverse image captioning via grouptalk","volume-title":"Proc. 25h Int. Joint Conf. Artif. Intell.","author":"Wang"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00146"},{"key":"ref60","article-title":"Generating diverse and accurate visual captions by comparative adversarial learning","author":"Li","year":"2018"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-2812"},{"key":"ref63","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","volume-title":"Proc. 26th Int. Conf. Neural Inf. Process. Syst.","author":"Mikolov"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809682"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-31865-1_25"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45054-8_36"},{"key":"ref68","first-page":"5627","article-title":"Fast greedy MAP inference for determinantal point process to improve recommendation diversity","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref70","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00850"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018957"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9674188\/09158555.pdf?arnumber=9158555","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T23:59:09Z","timestamp":1704844749000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9158555\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,1]]},"references-count":72,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2020.3013834","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]]}}}