{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T21:38:41Z","timestamp":1770154721973,"version":"3.49.0"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"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":["61972115"],"award-info":[{"award-number":["61972115"]}],"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":["61631017"],"award-info":[{"award-number":["61631017"]}],"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":["61872116"],"award-info":[{"award-number":["61872116"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2020,9]]},"DOI":"10.1109\/tmm.2019.2954750","type":"journal-article","created":{"date-parts":[[2019,11,20]],"date-time":"2019-11-20T20:56:37Z","timestamp":1574283397000},"page":"2307-2320","source":"Crossref","is-referenced-by-count":22,"title":["Visual Relationship Embedding Network for Image Paragraph Generation"],"prefix":"10.1109","volume":"22","author":[{"given":"Wenbin","family":"Che","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9660-3636","authenticated-orcid":false,"given":"Xiaopeng","family":"Fan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9796-0478","authenticated-orcid":false,"given":"Ruiqin","family":"Xiong","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3434-9967","authenticated-orcid":false,"given":"Debin","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-008-0140-x"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2869276"},{"key":"ref33","article-title":"Microsoft coco: Common objects in context","author":"tsung-yi","year":"2015"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2888822"},{"key":"ref31","first-page":"1143","article-title":"Im2text: Describing images using 1 million captioned photographs","author":"ordonez","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref30","first-page":"15","article-title":"Every picture tells a story: Generating sentences from images","author":"sadeghi","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.214"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2598339"},{"key":"ref35","article-title":"Visual genome: Connecting language and vision using crowdsourced dense image annotations","author":"krishna","year":"2016"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21236\/ADA623249"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.331"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2644872"},{"key":"ref12","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.245"},{"key":"ref15","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","author":"amodei","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref16","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":"ref17","first-page":"2369","article-title":"Encode, review, and decode: Reviewer module for caption generation","author":"yang","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240695"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref27","first-page":"852","article-title":"Visual relationship detection with language priors","author":"lu","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref3","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref6","article-title":"Generating sequences with recurrent neural networks","author":"graves","year":"2013","journal-title":"Evolutionary and Neural Computation"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1162\/153244303322533223"},{"key":"ref8","article-title":"Explain images with multimodal recurrent neural networks","author":"mao","year":"2014","journal-title":"Comput Vision Pattern Recognit"},{"key":"ref7","first-page":"1045","article-title":"Recurrent neural network based language model","author":"mikolov","year":"0","journal-title":"Proc 11th Annu Conf Int Speech Commun Assoc"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2510329"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2482228"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477044"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref47","first-page":"311","article-title":"Bleu: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Assoc Comput Linguist"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2751140"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.211"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.555"},{"key":"ref41","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.356"},{"key":"ref44","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.83"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21236\/ADA623249"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.352"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9173579\/08907490.pdf?arnumber=8907490","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:57:39Z","timestamp":1651075059000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8907490\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9]]},"references-count":47,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2019.2954750","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9]]}}}