{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:24:28Z","timestamp":1777656268814,"version":"3.51.4"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/tpami.2019.2894139","type":"journal-article","created":{"date-parts":[[2019,1,22]],"date-time":"2019-01-22T04:07:16Z","timestamp":1548130036000},"page":"1-1","source":"Crossref","is-referenced-by-count":120,"title":["Hierarchical LSTMs with Adaptive Attention for Visual Captioning"],"prefix":"10.1109","author":[{"given":"Lianli","family":"Gao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangpeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingkuan","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heng Tao","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","first-page":"2361","article-title":"Review networks for caption generation","author":"yang","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref71","first-page":"382","article-title":"SPICE: Semantic propositional image caption evaluation","author":"anderson","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.100"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984066"},{"key":"ref33","first-page":"2346","article-title":"Jointly modeling deep video and compositional text to bridge vision and language in a unified framework","author":"xu","year":"2015","journal-title":"Proc 29th AAAI Conf Artif Intell"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref31","first-page":"20","article-title":"Temporal segment networks: Towards good practices for deep action recognition","author":"wang","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2749159"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.450"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00013"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.496"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.117"},{"key":"ref60","article-title":"Video captioning with recurrent networks based on frame- and video-level features and visual content classification","author":"shetty","year":"2015","journal-title":"CoRR"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00728"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.347"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.649"},{"key":"ref64","first-page":"740","article-title":"Microsoft common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref68","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":"ref69","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Proc Workshop Text Summarization Branches Out"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2814344"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2601260"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.127"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref24","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref23","first-page":"1782","article-title":"Deliberation networks: Sequence generation beyond one-pass decoding","author":"xia","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref26","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0987-1"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref56","first-page":"65","article-title":"Meteor: An automatic metric for MT evaluation with improved correlation with human judgments","author":"banerjee","year":"2005","journal-title":"Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation"},{"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","article-title":"ADADELTA: An adaptive learning rate method","author":"zeiler","year":"2012","journal-title":"arXiv 1212 5701"},{"key":"ref53","article-title":"Using descriptive video services to create a large data source for video annotation research","author":"torabi","year":"2015","journal-title":"arXiv 1503 01070"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806314"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.111"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_52"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2851077"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2855422"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477044"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1154"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref4","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref6","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","author":"karpathy","year":"2014","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1173"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref49","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","author":"chen","year":"2011","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref46","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 Inf Process"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/72.279181"},{"key":"ref48","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref47","first-page":"190","article-title":"Training and analysing deep recurrent neural networks","author":"hermans","year":"2013","journal-title":"Proc 26th Int Conf Neural Inf Process Syst"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref41","article-title":"Sequence level training with recurrent neural networks","author":"ranzato","year":"2015","journal-title":"arXiv 1511 06732"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.128"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.100"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/4359286\/08620348.pdf?arnumber=8620348","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:00:05Z","timestamp":1651068005000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8620348\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/tpami.2019.2894139","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":[[2019]]}}}