{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:18:29Z","timestamp":1778048309468,"version":"3.51.4"},"reference-count":57,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00476","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"4901-4911","source":"Crossref","is-referenced-by-count":0,"title":["Robust Multimodal Emotion Recognition from Incomplete Modalities via Query-Based Unimodal and Cross-Modal Learning"],"prefix":"10.1109","author":[{"given":"Ryo","family":"Miyoshi","sequence":"first","affiliation":[{"name":"CyberAgent"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mayu","family":"Otani","sequence":"additional","affiliation":[{"name":"CyberAgent"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuki","family":"Okafuji","sequence":"additional","affiliation":[{"name":"CyberAgent"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-020-01449-0"},{"key":"ref2","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2515617"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref7","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning","author":"Chen"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3518"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref11","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1207"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref15","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref16","article-title":"Perceiver io: A general architecture for structured inputs & outputs","volume-title":"International Conference on Learning Representations","author":"Jaegle"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413620"},{"key":"ref18","article-title":"Paraphrasing complex network: Network compression via factor transfer","volume":"31","author":"Kim","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref19","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i9.28871"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01184"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00641"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3234553"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2026.3653457\/mm1"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102367"},{"key":"ref26","article-title":"AffectGPT: A new dataset, model, and benchmark for emotion understanding with multimodal large language models","volume-title":"Forty-second International Conference on Machine Learning","author":"Lian"},{"key":"ref27","article-title":"OV-MER: Towards open-vocabulary multimodal emotion recognition","volume-title":"Forty-second International Conference on Machine Learning","author":"Lian"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00804"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3536221.3556630"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-27818-1_34"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00258"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16330"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2070481.2070509"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s13278-021-00776-6"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.03.026"},{"key":"ref37","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00806"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016892"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1081"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1050"},{"key":"ref42","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3274829"},{"key":"ref44","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","volume-title":"International conference on machine learning","author":"Sutskever"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00558"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.528"},{"key":"ref47","article-title":"Learning fac-torized multimodal representations","author":"Tsai","year":"2019"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02025"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02013"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0748"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3068045"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475585"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12024"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492153.pdf?arnumber=11492153","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:54:30Z","timestamp":1778046870000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492153\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00476","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}