{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:40:26Z","timestamp":1730266826286,"version":"3.28.0"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"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":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10651217","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["TMMM: Transformer in Multimodal Sentiment Analysis under Missing Modalities"],"prefix":"10.1109","author":[{"given":"Huanyu","family":"Wu","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology,Ministry of Education Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation,Wuhan,China,430074"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siyang","family":"Li","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology,Ministry of Education Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation,Wuhan,China,430074"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongrui","family":"Wu","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology,Ministry of Education Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation,Wuhan,China,430074"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10380"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3275156"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191581"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191461"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS52988.2021.9663793"},{"article-title":"Towards a unified foundation model: Jointly pre-training transformers on unpaired images and text","year":"2021","author":"Li","key":"ref6"},{"article-title":"Improving multi-modal learning with uni-modal teachers","year":"2021","author":"Du","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00120"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.528"},{"article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int\u2019l Conf. on Machine Learning, Virtual Event","author":"Kim","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01028"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Advances in Neural Information Processing Systems","author":"Lu","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01315"},{"article-title":"InterBert: Vision-and-language interaction for multi-modal pretraining","year":"2020","author":"Lin","key":"ref15"},{"article-title":"Zorro: The masked multimodal transformer","year":"2023","author":"Recasens","key":"ref16"},{"article-title":"Attention bottlenecks for multimodal fusion","volume-title":"Proc. Advances in Neural Information Processing Systems, Virtual Event","author":"Nagrani","key":"ref17"},{"issue":"3","key":"ref18","first-page":"1","article-title":"Auto-encoding variational bayes","volume":"1050","author":"Kingma","year":"2014","journal-title":"Stat"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.203"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532064"},{"issue":"5","key":"ref22","first-page":"9","article-title":"Distilling the knowledge in a neural network","volume":"1050","author":"Hinton","year":"2015","journal-title":"Stat"},{"article-title":"Contrastive representation distillation","volume-title":"Proc. Int\u2019l Conf. on Learning Representations","author":"Tian","key":"ref23"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Kenton","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"article-title":"Probing inter-modality: Visual parsing with self-attention for vision- and-language pre-training","volume-title":"Proc. Advances in Neural Information Processing Systems, Virtual Event","author":"Xue","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref28","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int\u2019l Conf. on Machine Learning, Virtual Event","author":"Radford"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.189"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3234553"},{"article-title":"Attention is all you need","volume-title":"Proc. Advances in Neural Information Processing Systems","author":"Vaswani","key":"ref31"},{"article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","volume-title":"Proc. Int\u2019l Conf. on Learning Representations","author":"Shazeer","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00026"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016892"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380000"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01278"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2022.3144317"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM52615.2021.9669556"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191227"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00970"},{"article-title":"Vatt: Transformers for multimodal self-supervised learning from raw video, audio and text","volume-title":"Proc. Advances in Neural Information Processing Systems, Virtual Events","author":"Akbari","key":"ref45"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.586"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2024,6,30]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10651217.pdf?arnumber=10651217","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T06:26:36Z","timestamp":1725949596000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10651217\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10651217","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}