{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T23:12:14Z","timestamp":1768777934128,"version":"3.49.0"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Basic Research Program of China","doi-asserted-by":"publisher","award":["2017YFB0701900"],"award-info":[{"award-number":["2017YFB0701900"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2020,6]]},"DOI":"10.1109\/tmm.2019.2946477","type":"journal-article","created":{"date-parts":[[2019,10,9]],"date-time":"2019-10-09T19:42:45Z","timestamp":1570650165000},"page":"1634-1646","source":"Crossref","is-referenced-by-count":24,"title":["Visual-Texual Emotion Analysis With Deep Coupled Video and Danmu Neural Networks"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9401-765X","authenticated-orcid":false,"given":"Chenchen","family":"Li","sequence":"first","affiliation":[]},{"given":"Jialin","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7474-8271","authenticated-orcid":false,"given":"Hongwei","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4324-1467","authenticated-orcid":false,"given":"Miao","family":"Zhao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7360-8864","authenticated-orcid":false,"given":"Wenjie","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5282-6467","authenticated-orcid":false,"given":"Xiaotie","family":"Deng","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2632856.2632912"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2765820"},{"key":"ref33","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2014"},{"key":"ref32","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"0","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref31","first-page":"1083","article-title":"On deep multi-view representation learning","author":"wang","year":"0","journal-title":"Proc Int Conf Int Conf Mach Learn"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2855081"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540112"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873987"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1162\/0899766042321814"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.2307\/2333955"},{"key":"ref28","first-page":"231","article-title":"Visual sentiment analysis by attending on local image regions","author":"you","year":"0","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2827782"},{"key":"ref29","first-page":"2121","article-title":"Devise: A deep visual-semantic embedding model","author":"frome","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2803520"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2502069.2502079"},{"key":"ref20","first-page":"2418","article-title":"Topical word embeddings","author":"liu","year":"0","journal-title":"Proc 29th AAAI Conf Artif Intell"},{"key":"ref22","first-page":"109","article-title":"Multi-prototype vector-space models of word meaning","author":"reisinger","year":"0","journal-title":"Proc Human Lang Technol Annu Conf North Amer Chapter Assoc Comput Linguistics"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132889"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1645953.1646003"},{"key":"ref23","first-page":"993","article-title":"Latent Dirichlet allocation","volume":"3","author":"blei","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2482228"},{"key":"ref25","first-page":"1371","article-title":"Sentiment analysis with global topics and local dependency","author":"li","year":"0","journal-title":"Proc 24th AAAI Conf Artif Intell"},{"key":"ref50","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref51","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502268"},{"key":"ref11","first-page":"381","article-title":"Robust image sentiment analysis using progressively trained and domain transferred deep networks","author":"you","year":"0","journal-title":"Proc 29th AAAI Conf Artif Intell"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-014-0407-8"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2017.01.011"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2808760"},{"key":"ref14","first-page":"3484","article-title":"Beyond object recognition: Visual sentiment analysis with deep coupled adjective and noun neural networks","author":"wang","year":"0","journal-title":"Proc 25th Int Joint Conf Artif Intell"},{"key":"ref15","first-page":"538","article-title":"Twitter sentiment analysis: The good the bad and the omg!","author":"kouloumpis","year":"0","journal-title":"Proc Int Conf Weblogs Social Media"},{"key":"ref16","first-page":"30","article-title":"Sentiment analysis of twitter data","author":"agarwal","year":"0","journal-title":"Proc Workshop on Language in Social Media 2011"},{"key":"ref17","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1146"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2835776.2835779"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2757769"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCI-CC.2015.7259380"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2575738"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2617741"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874060"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967187"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref9","first-page":"308","article-title":"Building a large scale dataset for image emotion recognition: The fine print and the benchmark","author":"you","year":"0","journal-title":"Proc 30th AAAI Conf Artif Intell"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref45","first-page":"57","article-title":"Diving deep into sentiment: Understanding fine-tuned CNNs for visual sentiment prediction","author":"campos","year":"0","journal-title":"Proc 1st Int Workshop Affect Sentiment Multimedia"},{"key":"ref48","first-page":"4278","article-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","author":"szegedy","year":"0","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref42","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2558463"},{"key":"ref44","first-page":"440","article-title":"Biographies, bollywood, boom-boxes and blenders: Domain adaptation for sentiment classification","author":"blitzer","year":"0","journal-title":"Proc 45th Annu Meeting Assoc Comput Linguistics"},{"key":"ref43","author":"parrott","year":"2001","journal-title":"Emotions in Social Psychology Essential Readings"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9097818\/08863380.pdf?arnumber=8863380","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:56:13Z","timestamp":1651074973000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8863380\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6]]},"references-count":51,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2019.2946477","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,6]]}}}