{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:09:13Z","timestamp":1761894553491,"version":"build-2065373602"},"reference-count":27,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11208972","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":["Pop-Diffuseq: Controllable Symbolic Music Multi-Instrument Infilling and Accompaniment Generation with Long-Axis Attention"],"prefix":"10.1109","author":[{"given":"Yi","family":"Zou","sequence":"first","affiliation":[{"name":"Communication University of China,School of Information and Communication Engineering,Beijing,China"}]},{"given":"Haonan","family":"Cheng","sequence":"additional","affiliation":[{"name":"Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing,China,100024"}]},{"given":"Long","family":"Ye","sequence":"additional","affiliation":[{"name":"Communication University of China,School of Data Science and Intelligent Media,Beijing,China,100024"}]},{"given":"Qin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Media Audio & Video, (Communication University of China),Ministry of Education,Beijing,China,100024"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1198","article-title":"Pop-mag: Pop music accompaniment generation","volume-title":"ACM Multimedia, ACM MM","author":"Ren"},{"key":"ref2","first-page":"551","article-title":"Symphony generation with permutation invariant language model","volume-title":"International Society for Music Information Retrieval, ISMIR","author":"Liu"},{"key":"ref3","article-title":"Anticipatory music transformer","author":"Thickstun","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref4","first-page":"833","article-title":"Accomontage: Accompaniment arrangement via phrase selection and style transfer","volume-title":"ISMIR","author":"Zhao"},{"key":"ref5","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Conference on Neural Information Processing Systems, NeurIPS","volume":"33","author":"Brown"},{"article-title":"Music transformer: Generating music with long-term structure","volume-title":"7th International Conference on Learning Representations, ICLR","author":"Huang","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16091"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref9","first-page":"5156","article-title":"Transformers are rnns: Fast autoregressive transformers with linear attention","volume-title":"International Conference on Machine Learning, ICML","author":"Katharopoulos"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25650"},{"key":"ref11","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/648"},{"key":"ref13","first-page":"468","article-title":"Symbolic music generation with diffusion models","volume-title":"ISMIR","author":"Mittal"},{"article-title":"Diffuseq: Sequence to sequence text generation with diffusion models","volume-title":"ICLR","author":"Gong","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.660"},{"key":"ref16","first-page":"2","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of North American Chapter of the Association for Computational Linguistics, naacL-HLT","volume":"1","author":"Kenton"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11312"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413671"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.70"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.123"},{"key":"ref21","first-page":"231","article-title":"Polyffusion: A diffusion model for polyphonic score generation with internal and external controls","volume-title":"ISMIR","author":"Min"},{"article-title":"Whole-song hierarchical generation of symbolic music using cascaded diffusion models","volume-title":"The Twelfth ICLR","author":"Wang","key":"ref22"},{"article-title":"Structured multi-track accompaniment arrangement via style prior modelling","volume-title":"NeurIPS","author":"Zhao","key":"ref23"},{"key":"ref24","first-page":"427","article-title":"Norm-based curriculum learning for neural machine translation","volume-title":"ACL","author":"Xuebo"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.261"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-018-3849-7"}],"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\/11208972.pdf?arnumber=11208972","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:30:30Z","timestamp":1761888630000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11208972\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11208972","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}