{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:20:33Z","timestamp":1760710833155,"version":"3.37.3"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,1,1]]},"DOI":"10.1109\/tpami.2022.3144984","type":"journal-article","created":{"date-parts":[[2022,1,25]],"date-time":"2022-01-25T20:38:22Z","timestamp":1643143102000},"page":"1162-1173","source":"Crossref","is-referenced-by-count":26,"title":["Switchable Novel Object Captioner"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1680-8253","authenticated-orcid":false,"given":"Yu","family":"Wu","sequence":"first","affiliation":[{"name":"Baidu Research, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0286-8439","authenticated-orcid":false,"given":"Lu","family":"Jiang","sequence":"additional","affiliation":[{"name":"Google Research, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0512-880X","authenticated-orcid":false,"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995627"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2671188.2749399"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018965"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00754"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.272"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.140"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6620"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2965966"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00504"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2967584"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref2","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"2015","journal-title":"Proc Int Conf Neural Informat Process Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2708709"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.2100463"},{"key":"ref22","first-page":"747","article-title":"Midge: Generating image descriptions from computer vision detections","author":"mitchell","year":"2012","journal-title":"Proc Conf Eur Chapter Assoc Comput Linguistics"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref24","first-page":"1143","article-title":"Im2text: Describing images using 1 million captioned photographs","author":"ordonez","year":"2011","journal-title":"Proc Int Conf Neural Informat Process Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.05.001"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1033-7"},{"key":"ref50","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.8"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2857768"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.130"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.559"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1098"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2587640"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00639"},{"key":"ref18","first-page":"595","article-title":"Multimodal neural language models","author":"kiros","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00138"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240640"},{"key":"ref6","article-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","author":"mao","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref7","article-title":"Sequence level training with recurrent neural networks","author":"ranzato","year":"2016","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref49","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proc 12th USENIX Conf Operating Syst Des Implementation"},{"key":"ref9","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":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref45","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Int Conf Neural Informat Process Syst"},{"key":"ref48","first-page":"65","article-title":"METEOR: An automatic metric for mt evaluation with improved correlation with human judgments","author":"banerjee","year":"2005","journal-title":"Proc 2nd Workshop Statist Mach Transl"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.351"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.500"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806237"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref43","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Representations"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9970415\/09693277.pdf?arnumber=9693277","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:13:44Z","timestamp":1672082024000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9693277\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,1]]},"references-count":51,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3144984","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"},{"type":"electronic","value":"1939-3539"}],"subject":[],"published":{"date-parts":[[2023,1,1]]}}}