{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:27:50Z","timestamp":1774420070026,"version":"3.50.1"},"reference-count":9,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888958","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:56:59Z","timestamp":1741787819000},"page":"1-2","source":"Crossref","is-referenced-by-count":3,"title":["Reliable Learning From LLM Features for Multimodal Emotion and Intent Joint Understanding"],"prefix":"10.1109","author":[{"given":"Xiaolin","family":"Xu","sequence":"first","affiliation":[{"name":"Southeast University,Key Laboratory of Child Development and Learning Science (Ministry of Education) and School of Biological Science and Medical Engineering,Nanjing,China,210096"}]},{"given":"Cheng","family":"Lu","sequence":"additional","affiliation":[{"name":"Southeast University,Key Laboratory of Child Development and Learning Science (Ministry of Education) and School of Biological Science and Medical Engineering,Nanjing,China,210096"}]},{"given":"Zhaoyang","family":"Li","sequence":"additional","affiliation":[{"name":"Southeast University,Key Laboratory of Child Development and Learning Science (Ministry of Education) and School of Biological Science and Medical Engineering,Nanjing,China,210096"}]},{"given":"Yuyun","family":"Liu","sequence":"additional","affiliation":[{"name":"Southeast University,Key Laboratory of Child Development and Learning Science (Ministry of Education) and School of Biological Science and Medical Engineering,Nanjing,China,210096"}]},{"given":"Yinghao","family":"Ma","sequence":"additional","affiliation":[{"name":"Southeast University,Key Laboratory of Child Development and Learning Science (Ministry of Education) and School of Biological Science and Medical Engineering,Nanjing,China,210096"}]},{"given":"Jiahao","family":"Luo","sequence":"additional","affiliation":[{"name":"Southeast University,Key Laboratory of Child Development and Learning Science (Ministry of Education) and School of Biological Science and Medical Engineering,Nanjing,China,210096"}]},{"given":"Yuan","family":"Zong","sequence":"additional","affiliation":[{"name":"Southeast University,Key Laboratory of Child Development and Learning Science (Ministry of Education) and School of Biological Science and Medical Engineering,Nanjing,China,210096"}]},{"given":"Wenming","family":"Zheng","sequence":"additional","affiliation":[{"name":"Southeast University,Key Laboratory of Child Development and Learning Science (Ministry of Education) and School of Biological Science and Medical Engineering,Nanjing,China,210096"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Videollama 2: Advancing spatial-temporal modeling and audio understanding in video-llms","author":"Cheng","year":"2024"},{"key":"ref2","article-title":"Auroracap: Efficient, performant video detailed captioning and a new benchmark","author":"Chai","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref4","first-page":"28 492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"ICML.","author":"Radford","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00469"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3124365"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11945"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26138"},{"key":"ref9","article-title":"Emotion and intent joint understanding in multimodal conversation: A benchmarking dataset","author":"Liu","year":"2024"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888958.pdf?arnumber=10888958","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:14Z","timestamp":1774416374000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888958\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":9,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888958","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}