{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T04:29:47Z","timestamp":1780633787518,"version":"3.54.1"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["91646207"],"award-info":[{"award-number":["91646207"]}],"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":["61773377"],"award-info":[{"award-number":["61773377"]}],"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":["61573352"],"award-info":[{"award-number":["61573352"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"crossref","award":["L172053"],"award-info":[{"award-number":["L172053"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2019,11]]},"DOI":"10.1109\/tmm.2019.2915033","type":"journal-article","created":{"date-parts":[[2019,5,9]],"date-time":"2019-05-09T19:53:50Z","timestamp":1557431630000},"page":"2942-2956","source":"Crossref","is-referenced-by-count":108,"title":["Deep Hierarchical Encoder\u2013Decoder Network for Image Captioning"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4895-632X","authenticated-orcid":false,"given":"Xinyu","family":"Xiao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3707-0267","authenticated-orcid":false,"given":"Lingfeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0657-1608","authenticated-orcid":false,"given":"Kun","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2089-9733","authenticated-orcid":false,"given":"Shiming","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunhong","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299073"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.201"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-51811-4_34"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2530399"},{"key":"ref74","article-title":"Order-embeddings of images and language","author":"vendrov","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126717"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2616298"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref33","first-page":"1292","article-title":"Image description using visual dependency representations","author":"elliott","year":"2013","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.337"},{"key":"ref31","first-page":"747","article-title":"Midge: Generating image descriptions from computer vision detections","author":"mitchell","year":"2012","journal-title":"Proc 13th Conf Eur Chapter Assoc Comput Linguistics"},{"key":"ref30","first-page":"444","article-title":"Corpus-guided sentence generation of natural images","author":"yang","year":"2011","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref37","first-page":"4176","article-title":"Attention correctness in neural image captioning","author":"liu","year":"2017","journal-title":"Proc Conf Artif Intell"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-2017"},{"key":"ref35","first-page":"359","article-title":"Collective generation of natural image descriptions","author":"kuznetsova","year":"2012","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"ref60","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref61","first-page":"4278","article-title":"Inception-v4, inception-ResNet and the impact of residual connections on learning","author":"szegedy","year":"2017","journal-title":"Proc Conf Artif Intell"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref64","article-title":"Recurrent image captioner: Describing images with spatial-invariant transformation and attention filtering","author":"liu","year":"2016","journal-title":"Comput Res Repository"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref65","first-page":"6837","article-title":"Stack-captioning: Coarse-to-fine learning for image captioning","author":"gu","year":"0","journal-title":"Proc Conf Artif Intell"},{"key":"ref66","first-page":"898","article-title":"Contrastive learning for image captioning","author":"dai","year":"2017","journal-title":"Proc Conf Neural Inform Process Syst"},{"key":"ref29","first-page":"220","article-title":"Composing simple image descriptions using web-scale n-grams","author":"li","year":"2011","journal-title":"Proc Computational Natural Language Learning"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.100"},{"key":"ref68","first-page":"6706","article-title":"Temporal-difference learning with sampling baseline for image captioning","author":"chen","year":"2018","journal-title":"Proc Conf Artif Intell"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref1","article-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","author":"mao","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref20","article-title":"Google's neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1002"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.140"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00105"},{"key":"ref26","article-title":"Sequence level training with recurrent neural networks","author":"ranzato","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref50","first-page":"595","article-title":"Multimodal neural language models","author":"kiros","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref51","first-page":"101","article-title":"phi-LSTM: A phrase-based hierarchical LSTM model for image captioning","author":"tan","year":"2016","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref59","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","author":"karpathy","year":"2014","journal-title":"Proc Conf Neural Inform Process Syst"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref57","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume":"8","author":"lin","year":"0","journal-title":"Proc of Workshop on Text Summarization Branches Out"},{"key":"ref56","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":"Proc ACL Workshop Intrinsic Extrinsic Eval Measures Mach Transl Summarization"},{"key":"ref55","first-page":"311","article-title":"Bleu: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref54","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref52","first-page":"139","article-title":"Collecting image annotations using amazon's mechanical turk","author":"rashtchian","year":"0","journal-title":"NAACL HLT Workshop"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.29"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2582379"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/089892904322984526"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126281"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","first-page":"1106","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Conf Neural Inform Process Syst"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2598092"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref4","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2014","journal-title":"Comput Res Repository"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref6","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc IEEE Int Conf Mach Learn"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00188"},{"key":"ref8","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc Conf Neural Inform Process Syst"},{"key":"ref7","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2599174"},{"key":"ref45","article-title":"Generating sequences with recurrent neural networks","author":"graves","year":"2013","journal-title":"Comput Res Repository"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref47","article-title":"Understanding the exploding gradient problem","author":"pascanu","year":"2012","journal-title":"Comput Res Repository"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964299"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.127"},{"key":"ref43","first-page":"2361","article-title":"Review networks for caption generation","author":"yang","year":"2016","journal-title":"Proc Conf Neural Inform Process Syst"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8882528\/08710315.pdf?arnumber=8710315","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:50:17Z","timestamp":1657745417000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8710315\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":76,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2019.2915033","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,11]]}}}