{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:18:35Z","timestamp":1761895115391,"version":"build-2065373602"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11210029","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal Conversatioal Emotion Analysis with Robustness to Incomplete Modality Details"],"prefix":"10.1109","author":[{"given":"Sidharth","family":"Anand","sequence":"first","affiliation":[{"name":"The State University of New York,Buffalo,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaitanya Sai Chandu","family":"Yendru","sequence":"additional","affiliation":[{"name":"The State University of New York,Buffalo,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sreyasee","family":"Das Bhattacharjee","sequence":"additional","affiliation":[{"name":"The State University of New York,Buffalo,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junsong","family":"Yuan","sequence":"additional","affiliation":[{"name":"The State University of New York,Buffalo,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"UnI-VAL: Unified model for image, video, audio and language tasks","author":"Shukor","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"article-title":"Generative pretraining in multimodality","year":"2023","author":"Sun","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00511"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.126"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2024.3389453"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2023.3261279"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.861"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1050"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74889-2_41"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.iswa.2022.200171"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3049898"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i02.5492"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993176"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612517"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29876"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.224"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3223517"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/BigMM59094.2023.00013"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS48785.2022.9938005"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612517"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01435"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01524"},{"key":"ref24","article-title":"Taming transformers for high-resolution image synthesis","author":"Esser","year":"2020","journal-title":"CoRR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.336"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"article-title":"Language models are unsupervised multitask learners","year":"2019","author":"Radford","key":"ref27"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref28"},{"key":"ref29","article-title":"Beit: BERT pre-training of image transformers","author":"Bao","year":"2021","journal-title":"CoRR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00679"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.534"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.302"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3244390"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1050"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11210029.pdf?arnumber=11210029","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:43:19Z","timestamp":1761889399000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11210029\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11210029","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}