{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:23:27Z","timestamp":1774419807946,"version":"3.50.1"},"reference-count":29,"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\/501100020487","name":"Nature","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020487","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002703","name":"Jiangsu University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002703","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002703","name":"Jiangsu University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002703","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100020487","name":"Nature","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020487","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","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\/icassp49660.2025.10889807","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Global Enhanced Frame Prompt Tuning for Sound Event Detection"],"prefix":"10.1109","author":[{"given":"Shiyu","family":"Yu","sequence":"first","affiliation":[{"name":"Jiangsu University,School of Computer Science and Communication Engineering,Zhenjiang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lijian","family":"Gao","sequence":"additional","affiliation":[{"name":"Jiangsu University,School of Computer Science and Communication Engineering,Zhenjiang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qirong","family":"Mao","sequence":"additional","affiliation":[{"name":"Jiangsu University,School of Computer Science and Communication Engineering,Zhenjiang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/941"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094788"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-021-11817-9"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-344"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414350"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3369529"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548097"},{"key":"ref8","article-title":"Semi-supervised learning-based sound event detection using frequency dynamic convolution with large kernel attention for DCASE challenge 2023 task 4","volume-title":"DCASE2023 Challenge, Tech. Rep.","author":"Kim","year":"2023"},{"key":"ref9","article-title":"Sound event detection of domestic activities using frequency dynamic convolution and BEATS embeddings","volume-title":"DCASE2023 Challenge, Tech. Rep","author":"Cheimariotis","year":"2023"},{"key":"ref10","first-page":"5178","article-title":"Beats: Audio pre-training with acoustic tokenizers","volume-title":"Proceedings of the International Conference on Machine Learning, ICML","volume":"202","author":"Chen"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446159"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1174"},{"key":"ref13","article-title":"Language models are few-shot learners","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems","author":"Brown"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.4018\/IJSWIS.339187"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01900"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28475"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3436618"},{"key":"ref21","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proceedings of the International Conference on Learning Representations, ICLR","author":"Tarvainen"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.33682\/006b-jx26"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747556"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10127"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747680"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3233468"},{"key":"ref28","article-title":"Sound event detection with heterogeneous training dataset and potentially missing labels for DCASE 2024 task 4","volume-title":"DCASE2024 Challenge, Tech. Rep.","author":"Chen","year":"2024"},{"key":"ref29","article-title":"Dcase 2024 task 4: Sound event detection with heterogeneous data and missing labels","author":"Cornell","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\/10889807.pdf?arnumber=10889807","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:49Z","timestamp":1774416289000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889807\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889807","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}