{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T20:25:43Z","timestamp":1791059143862,"version":"4.1.0"},"reference-count":88,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"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":["62006062"],"award-info":[{"award-number":["62006062"]}],"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":["62176076"],"award-info":[{"award-number":["62176076"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023A1515012922"],"award-info":[{"award-number":["2023A1515012922"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Foundational Research Funding","award":["JCYJ20220818102415032"],"award-info":[{"award-number":["JCYJ20220818102415032"]}]},{"name":"Major Key Project of PCL","award":["PCL2023A09"],"award-info":[{"award-number":["PCL2023A09"]}]},{"name":"Guandong Provincial Key Laboratory","award":["2022B1212010005k"],"award-info":[{"award-number":["2022B1212010005k"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Affective Comput."],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1109\/taffc.2023.3333200","type":"journal-article","created":{"date-parts":[[2023,11,15]],"date-time":"2023-11-15T13:58:28Z","timestamp":1700056708000},"page":"1264-1278","source":"Crossref","is-referenced-by-count":35,"title":["Image-to-Text Conversion and Aspect-Oriented Filtration for Multimodal Aspect-Based Sentiment Analysis"],"prefix":"10.1109","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3011-0580","authenticated-orcid":false,"given":"Qianlong","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9021-4405","authenticated-orcid":false,"given":"Hongling","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4106-1312","authenticated-orcid":false,"given":"Zhiyuan","family":"Wen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7234-1347","authenticated-orcid":false,"given":"Bin","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3814-2728","authenticated-orcid":false,"given":"Min","family":"Yang","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2543-5604","authenticated-orcid":false,"given":"Bing","family":"Qin","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4009-5679","authenticated-orcid":false,"given":"Ruifeng","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/s16-1002"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/s14-2076"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/S14-2149"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1298"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1021"},{"key":"ref6","first-page":"380","article-title":"Utilizing BERT for aspect-based sentiment analysis via constructing auxiliary sentence","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics","author":"Sun","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.188"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/751"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301371"},{"key":"ref11","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lu","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2957872"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-71292-1_31"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-88010-1_1"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3171091"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.388"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475692"},{"key":"ref19","first-page":"127","article-title":"C-Feel-it: A sentiment analyzer for micro-blogs","volume-title":"Proc. Annu. Meeting Assoc. Comput. Linguistics: Hum. Lang. Technol.-HLT Syst. Demonstrations","author":"Joshi","year":"2011"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2008.07.035"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1169"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.04.038"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2120"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3056664"},{"key":"ref26","first-page":"15734","article-title":"Nested graph neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.642"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.08.002"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.49"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17625"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.110182"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3204972"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.347"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2023.3254883"},{"key":"ref35","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Brown","year":"2020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3301275.3308446"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.12.012"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.26"},{"key":"ref39","first-page":"3829","article-title":"SenticNet 7: A commonsense-based neurosymbolic AI framework for explainable sentiment analysis","volume-title":"Proc. Lang. Resour. Eval. Conf.","author":"Cambria","year":"2022"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/945645.945658"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/s16-1049"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/5254.708428"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-2009"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/568"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1087"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107643"},{"key":"ref47","first-page":"241","article-title":"Enhanced sentiment learning using twitter hashtags and smileys","volume-title":"Proc. Int. Conf. Comput. Linguistics","author":"Davidov","year":"2010"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1303"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3035277"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.28"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210093"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859654"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-021-00955-7"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548306"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.152"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462867"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482158"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.08.054"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1005"},{"key":"ref62","first-page":"279","article-title":"Neuro-symbolic visual reasoning: Disentangling","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Amizadeh","year":"2020"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26541"},{"key":"ref64","first-page":"6784","article-title":"Learning from adjective-noun pairs: A knowledge-enhanced framework for target-oriented multimodal sentiment classification","volume-title":"Proc. Int. Conf. Comput. Linguistics","author":"Zhao","year":"2022"},{"key":"ref65","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref67","first-page":"1931","article-title":"Unifying vision-and-language tasks via text generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cho","year":"2021"},{"key":"ref68","first-page":"23318","article-title":"OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2022"},{"key":"ref69","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li","year":"2021"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.185"},{"key":"ref72","first-page":"200","article-title":"Multimodal few-shot learning with frozen language models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"34","author":"Tsimpoukelli","year":"2021"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"ref75","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sutskever","year":"2014"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11962"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1185"},{"key":"ref79","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren","year":"2015"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1058"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d17-1047"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1380"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103477"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.2"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.360"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-27674-8_2"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref88","first-page":"5583","article-title":"VILT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2021"}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5165369\/10666803\/10319094.pdf?arnumber=10319094","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T14:03:33Z","timestamp":1725631413000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10319094\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":88,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2023.3333200","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7]]}}}