{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T15:08:37Z","timestamp":1777043317231,"version":"3.51.4"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Sichuan Science and Technology Program","award":["2024YFFK0120"],"award-info":[{"award-number":["2024YFFK0120"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072419"],"award-info":[{"award-number":["62072419"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Affective Comput."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/taffc.2024.3486340","type":"journal-article","created":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T17:27:28Z","timestamp":1729790848000},"page":"999-1015","source":"Crossref","is-referenced-by-count":3,"title":["An Efficient Bi-Modal Fusion Framework for Music Emotion Recognition"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8712-8071","authenticated-orcid":false,"given":"Yao","family":"Xiao","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7587-8306","authenticated-orcid":false,"given":"Haoxin","family":"Ruan","sequence":"additional","affiliation":[{"name":"School of Mathematics and Physics, Southwest University of Science and Technology, Mianyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4717-9231","authenticated-orcid":false,"given":"Xujian","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3871-0548","authenticated-orcid":false,"given":"Peiquan","family":"Jin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Tian","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zihan","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuebo","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Music and Dance, Sichuan University of Culture and Arts, Mianyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yixin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Economics and Management, Southwest University of Science and Technology, Mianyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2021.3106232"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/s23020986"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-021-0569-4"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref5","first-page":"318","article-title":"EMOPIA: A multi-modal pop piano dataset for emotion recognition and emotion-based music generation","volume-title":"Proc. 22nd Int. Soc. Music Inf. Retrieval Conf.","author":"Hung"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2017.02.003"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859812"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-018-3758-9"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.3032373"},{"issue":"8","key":"ref10","article-title":"Language models are unsupervised multitask learners","volume-title":"OpenAI Blog","volume":"1","author":"Radford","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v16i1.7408"},{"key":"ref12","article-title":"A novel multi-task learning method for symbolic music emotion recognition","author":"Qiu","year":"2022"},{"key":"ref13","first-page":"796","article-title":"Extracting ground-truth information from MIDI files: A midifesto","volume-title":"Proc. 17th Int. Soc. Music Inf. Retrieval Conf.","author":"Raffel"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-4752-2_9"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2393367"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654904"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471735"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2598569"},{"key":"ref19","first-page":"221","article-title":"Exploration of music emotion recognition based on MIDI","volume-title":"Proc. 14th Int. Soc. Music Inf. Retrieval Conf.","author":"Lin"},{"key":"ref20","first-page":"570","article-title":"Multi-modal music emotion recognition: A new dataset, methodology and comparative analysis","volume-title":"Proc. 10th Int. Symp. Comput. Music Multidisciplinary Res.","author":"Panda"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2632307"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2018.2820691"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2015.12.003"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2997632"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-50341-3_21"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.11591\/APTIKOM.J.CSIT.118"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133949"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.11591\/eei.v12i1.4231"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2018.8486570"},{"key":"ref30","first-page":"36","article-title":"Attentive RNNs for continuous-time emotion prediction in music clips","volume-title":"Proc. 3 rd Workshop Affect. Content Anal. (AffCon 2020) Co-Located 24th AAAI Conf. Artif. Intell.","author":"Chaki"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-726"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-13577-6"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00182"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01049"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3258900"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108580"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2918739"},{"key":"ref39","article-title":"MidiBERT-Piano: Large-scale pre-training for symbolic music understanding","author":"Chou","year":"2021"},{"key":"ref40","first-page":"370","article-title":"Music mood detection based on audio and lyrics with deep neural net","volume-title":"Proc. 19th Int. Soc. Music Inf. Retrieval Conf.","author":"Delbouys"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-8707-4_3"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/4606027"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.03.007"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747236"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3121991"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413671"},{"key":"ref47","first-page":"1","article-title":"Enabling factorized piano music modeling and generation with the MAESTRO dataset","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Hawthorne"},{"key":"ref48","first-page":"670","article-title":"Adversarial learning for improved onsets and frames music transcription","volume-title":"Proc. 20th Int. Soc. Music Inf. Retrieval Conf.","author":"Kim"},{"key":"ref49","article-title":"Evaluation of CNN-based automatic music tagging models","author":"Won","year":"2020"},{"key":"ref50","first-page":"769","article-title":"Semi-supervised music tagging transformer","volume-title":"Proc. 22nd Int. Soc. Music Inf. Retrieval Conf.","author":"Won"},{"key":"ref51","first-page":"1","article-title":"On the relationship between self-attention and convolutional layers","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Cordonnier"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-021-01249-8"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2020.105506"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-010-0182-0"},{"key":"ref56","article-title":"Multi-modal sensor fusion for auto driving perception: A survey","author":"Huang","year":"2022"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1037\/h0077714"},{"key":"ref58","article-title":"Learning to generate music with sentiment","author":"Ferreira","year":"2019"},{"key":"ref59","article-title":"Experiment tracking with weights and biases","author":"Biewald","year":"2020"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.2307\/2279372"}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5165369\/11018643\/10735097.pdf?arnumber=10735097","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T04:54:34Z","timestamp":1748667274000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10735097\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":60,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2024.3486340","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}