{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:22:49Z","timestamp":1763191369665,"version":"3.45.0"},"reference-count":38,"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\/ijcnn64981.2025.11227919","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Emotion-Aware Text Generation for Instructing Audio-Visual Emotion Recognition"],"prefix":"10.1109","author":[{"given":"Lin","family":"Wei","sequence":"first","affiliation":[{"name":"China University of Geosciences (Wuhan),School of Computer Science,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanyuan","family":"Liu","sequence":"additional","affiliation":[{"name":"China University of Geosciences (Wuhan),School of Computer Science,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kejun","family":"Liu","sequence":"additional","affiliation":[{"name":"China University of Geosciences (Wuhan),School of Computer Science,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxuan","family":"Huang","sequence":"additional","affiliation":[{"name":"China University of Geosciences (Wuhan),School of Computer Science,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaoze","family":"Feng","sequence":"additional","affiliation":[{"name":"China University of Geosciences (Wuhan),School of Computer Science,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1140.001.0001"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2018.1700274"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3223444"},{"key":"ref4","first-page":"689","article-title":"Multimodal deep learning","volume":"11","author":"Ngiam","year":"2011","journal-title":"ICML"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/FG52635.2021.9667055"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.01.048"},{"article-title":"Multimodal emotion recognition using audio-video transformer fusion with cross attention","year":"2024","author":"Venkatraman","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102382"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017216"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.93"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2024.3422823"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2911996.2912051"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00056"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2024.3440924"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-13557-w"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052916"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1613\/jair.5477"},{"issue":"2","key":"ref18","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of naacL-HLT","volume":"1","author":"Kenton"},{"key":"ref19","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref20","first-page":"12 888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref21","first-page":"19 730","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":"ref22","first-page":"8","article-title":"Knowledge transfer with visual prompt in multi-modal dialogue understanding and generation","volume-title":"Proceedings of the First Workshop On Transcript Understanding","author":"Zhu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00693"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2015.7284869"},{"key":"ref25","first-page":"28 492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.25080\/majora-7b98e3ed-003"},{"article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","year":"2019","author":"Sanh","key":"ref27"},{"key":"ref28","first-page":"1298","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"International conference on machine learning","author":"Baevski"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548190"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413620"},{"article-title":"Decoupled weight decay regularization","year":"2017","author":"Loshchilov","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054229"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3312858"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00470"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681228"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"article-title":"Neural machine translation by jointly learning to align and translate","year":"2014","author":"Bahdanau","key":"ref38"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11227919.pdf?arnumber=11227919","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:18:34Z","timestamp":1763191114000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11227919\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11227919","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}