{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,18]],"date-time":"2026-10-18T11:48:45Z","timestamp":1792324125436,"version":"4.4.0"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Shenzhen Key Fundamental Research Project","award":["JCYJ20151030154330711"],"award-info":[{"award-number":["JCYJ20151030154330711"]}]},{"name":"Guangdong Natural Science Fund","award":["2018A030313017"],"award-info":[{"award-number":["2018A030313017"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2019,4]]},"DOI":"10.1109\/tmm.2018.2869276","type":"journal-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T20:02:48Z","timestamp":1537560168000},"page":"1047-1061","source":"Crossref","is-referenced-by-count":114,"title":["Multitask Learning for Cross-Domain Image Captioning"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7345-5071","authenticated-orcid":false,"given":"Min","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yabing","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6121-0384","authenticated-orcid":false,"given":"Zhou","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2818-4652","authenticated-orcid":false,"given":"Xiaojun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9197-895X","authenticated-orcid":false,"given":"Kai","family":"Lei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-5529-2_5"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080706"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2375793"},{"key":"ref32","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","first-page":"4790","article-title":"Conditional image generation with PixelCNN decoders","author":"van den oord","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref30","first-page":"217","article-title":"Learning what and where to draw","author":"reed","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","first-page":"5317","article-title":"Personalizing a dialogue system with transfer learning","author":"mo","year":"0","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2557722"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477044"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2558463"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref27","article-title":"Optimization of image description metrics using policy gradient methods","author":"liu","year":"0","journal-title":"Proc IEEE Int Conf Comput Vision"},{"key":"ref29","first-page":"1099","article-title":"Weakly-supervised disentangling with recurrent transformations for 3D view synthesis","author":"yang","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2644872"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.4900"},{"key":"ref20","article-title":"Sequence level training with recurrent neural networks","author":"ranzato","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref22","first-page":"820","article-title":"Dual learning for machine translation","author":"xia","year":"0","journal-title":"Proc 30th Conf Neural Inf Process Syst"},{"key":"ref21","first-page":"1060","article-title":"Generative adversarial text to image synthesis","author":"reed","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref24","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref23","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"0","journal-title":"Proc Annu Conf Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref51","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref59","first-page":"2234","article-title":"Improved techniques for training GANs","author":"salimans","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"},{"key":"ref55","first-page":"3294","article-title":"Skip-thought vectors","author":"kiros","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref52","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21236\/ADA623249"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref40","article-title":"Multi-task sequence to sequence learning","author":"luong","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref12","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"0","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.64"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.8"},{"key":"ref16","first-page":"25","article-title":"Rouge: A package for automatic evaluation of summaries","volume":"8","author":"lin","year":"0","journal-title":"Proc ACL Workshop Text Summarization Branches Out"},{"key":"ref17","first-page":"65","article-title":"Meteor: An automatic metric for MT evaluation with improved correlation with human judgments","volume":"29","author":"banerjee","year":"0","journal-title":"Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref19","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2390499"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2510329"},{"key":"ref6","first-page":"747","article-title":"Midge: Generating image descriptions from computer vision detections","author":"mitchell","year":"0","journal-title":"Proc 13th Conf European Chapter Assoc for Computational Linguistics"},{"key":"ref5","first-page":"1292","article-title":"Image description using visual dependency representations","volume":"13","author":"elliott","year":"0","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00188"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_35"},{"key":"ref49","volume":"135","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref9","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.310"},{"key":"ref48","article-title":"Bottom-up and top-down attention for image captioning and VQA","author":"anderson","year":"0","journal-title":"Proc IEEE Conf Comput Vision Pattern Recognit"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1117"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1204"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967271"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2484324"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8672836\/08457273.pdf?arnumber=8457273","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:50:18Z","timestamp":1657745418000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8457273\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4]]},"references-count":59,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2018.2869276","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,4]]}}}