{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:01:08Z","timestamp":1783530068407,"version":"3.55.0"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100019356","name":"General Program and Major Project of Shenzhen Science and Technology Research and Development Fund","doi-asserted-by":"publisher","award":["JCYJ20220530164813029"],"award-info":[{"award-number":["JCYJ20220530164813029"]}],"id":[{"id":"10.13039\/501100019356","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019356","name":"General Program and Major Project of Shenzhen Science and Technology Research and Development Fund","doi-asserted-by":"publisher","award":["KJZD20230923113800002"],"award-info":[{"award-number":["KJZD20230923113800002"]}],"id":[{"id":"10.13039\/501100019356","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010822","name":"Project of Chengdu Science and Technology Bureau","doi-asserted-by":"publisher","award":["2023-CY02-00003-GX"],"award-info":[{"award-number":["2023-CY02-00003-GX"]}],"id":[{"id":"10.13039\/501100010822","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Project of Sichuan Provincial Department of Science and Technology","award":["2024YFG0006"],"award-info":[{"award-number":["2024YFG0006"]}]},{"name":"Key Research and Development Project of Sichuan Provincial Department of Science and Technology","award":["NSF CNS-2107216"],"award-info":[{"award-number":["NSF CNS-2107216"]}]},{"name":"Key Research and Development Project of Sichuan Provincial Department of Science and Technology","award":["CNS-2128368"],"award-info":[{"award-number":["CNS-2128368"]}]},{"name":"Key Research and Development Project of Sichuan Provincial Department of Science and Technology","award":["CMMI-2222810"],"award-info":[{"award-number":["CMMI-2222810"]}]},{"name":"Key Research and Development Project of Sichuan Provincial Department of Science and Technology","award":["ECCS-2302469"],"award-info":[{"award-number":["ECCS-2302469"]}]},{"name":"Japan Science and Technology Agency (JST) Adopting Sustainable Partnerships for Innovative Research Ecosystem","award":["JPMJAP2326"],"award-info":[{"award-number":["JPMJAP2326"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1109\/tcsvt.2024.3474101","type":"journal-article","created":{"date-parts":[[2024,10,4]],"date-time":"2024-10-04T17:39:41Z","timestamp":1728063581000},"page":"1897-1909","source":"Crossref","is-referenced-by-count":4,"title":["Tri-Modal Transformers With Mixture-of-Modality-Experts for Social Media Prediction"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2202-601X","authenticated-orcid":false,"given":"Weilong","family":"Chen","sequence":"first","affiliation":[{"name":"College of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6067-1995","authenticated-orcid":false,"given":"Wenhao","family":"Hu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5819-5371","authenticated-orcid":false,"given":"Xiaolu","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weimin","family":"Yuan","sequence":"additional","affiliation":[{"name":"College of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1083-8865","authenticated-orcid":false,"given":"Yan","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4182-2150","authenticated-orcid":false,"given":"Yanru","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Engineering and Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6606-5822","authenticated-orcid":false,"given":"Zhu","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Houston, Houston, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Digital 2023: Global Overview Report","author":"Kemp","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3231437"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2998476"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3001583"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3074259"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416273"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3356060"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3356072"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3356054"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416275"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416274"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3356062"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416294"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3417332"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3356064"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-014-0432-7"},{"key":"ref17","article-title":"VAuLT: Augmenting the vision-and-language transformer for sentiment classification on social media","author":"Chochlakis","year":"2022","journal-title":"arXiv:2208.09021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551607"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551576"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-022-01030-5"},{"key":"ref21","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li"},{"key":"ref22","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref23","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Kim"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551568"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3266439"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1016\/j.eswa.2018.03.042","article-title":"Transfer learning approach for classification and noise reduction on noisy web data","volume":"105","author":"Aghamaleki","year":"2018","journal-title":"Exp. Syst. Appl."},{"key":"ref27","first-page":"32897","article-title":"VLMo: Unified vision-language pre-training with mixture-of-modality-experts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Bao"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3127903"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3127900"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3127902"},{"issue":"3","key":"ref31","doi-asserted-by":"crossref","first-page":"424","DOI":"10.1016\/j.inffus.2022.09.025","article-title":"Multimodal sentiment analysis: A systematic review of history, datasets, multimodal fusion methods, applications, challenges and future directions","volume":"91","author":"Gandhi","year":"2023","journal-title":"Inf. Fusion"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3275156"},{"key":"ref33","article-title":"NExT-GPT: Any-to-any multimodal LLM","author":"Wu","year":"2023","journal-title":"arXiv:2309.05519"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref35","first-page":"689","article-title":"Multimodal deep learning","volume-title":"Proc. 28th Int. Conf. Mach. Learn. (ICML)","author":"Ngiam"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3197420"},{"key":"ref37","article-title":"Meta-transformer: A unified framework for multimodal learning","author":"Zhang","year":"2023","journal-title":"arXiv:2307.10802"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/568"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219903"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2014.2347551"},{"key":"ref41","first-page":"1","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lu"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611762"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.740"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00737"},{"key":"ref45","first-page":"17359","article-title":"The unsurprising effectiveness of pre-trained vision models for control","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Parisi"},{"issue":"5","key":"ref46","first-page":"4276","article-title":"Learning to pre-train graph neural networks","volume-title":"Proc. Conf. Artif. Intell. (AAAI)","volume":"35","author":"Lu"},{"key":"ref47","article-title":"Transfer learning or self-supervised learning? A tale of two pretraining paradigms","author":"Yang","year":"2020","journal-title":"arXiv:2007.04234"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref50","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref51","article-title":"SimVLM: Simple visual language model pretraining with weak supervision","author":"Wang","year":"2021","journal-title":"arXiv:2108.10904"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref53","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Li","year":"2019","journal-title":"arXiv:1908.03557"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00534"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3561970"},{"key":"ref57","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"key":"ref58","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref59","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"ref61","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3332317"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570405"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3282410"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9970"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/2566486.2567996"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/76\/10885778\/10705363-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10885778\/10705363.pdf?arnumber=10705363","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T20:46:23Z","timestamp":1740084383000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10705363\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":67,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3474101","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}