{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:11:17Z","timestamp":1764400277196,"version":"3.46.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"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":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249250","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"282-287","source":"Crossref","is-referenced-by-count":0,"title":["Attention-Based Adaptive Structured Patchout Spectrogram Transformer for Music Classification"],"prefix":"10.1109","author":[{"given":"Yuan","family":"Liu","sequence":"first","affiliation":[{"name":"Waseda University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingqing","family":"Liu","sequence":"additional","affiliation":[{"name":"Waseda University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yichen","family":"Yang","sequence":"additional","affiliation":[{"name":"Waseda University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shoji","family":"Makino","sequence":"additional","affiliation":[{"name":"Waseda University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.804546"},{"key":"ref2","article-title":"Music classification: Beyond supervised learning, towards real-world applications","author":"Won","year":"2021","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121902"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1186\/1687-4722-2013-1"},{"key":"ref5","first-page":"1","article-title":"A large set of audio features for sound description (similarity and classification) in the CUIDADO project","volume":"54","author":"Peeters","year":"2004","journal-title":"CUIDADO Ist Project Report"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.22214\/ijraset.2024.62863"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-698"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-227"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"},{"key":"ref12","first-page":"5178","article-title":"BEATs: Audio Pre-Training with Acoustic Tokenizers","volume-title":"Proc. ICML","volume":"202","author":"Chen","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1723"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA251136"},{"key":"ref15","article-title":"Not all patches are what you need: Expediting vision transformers via token reorganizations","volume-title":"Proc. ICLR","author":"Liang","year":"2022"},{"key":"ref16","first-page":"438","article-title":"OpenMIC2018: An Open Data-set for Multiple Instrument Recognition","volume-title":"Proc. ISMIR","author":"Humphrey","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00085"},{"key":"ref19","first-page":"316","article-title":"FMA: A Dataset For Music Analysis","volume-title":"Proc. ISMIR","author":"Defferrard","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854599"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2390848.2390851"},{"key":"ref22","article-title":"The GTZAN dataset: Its contents, its faults, their effects on evaluation, and its future use","author":"Sturm","year":"2013","journal-title":"arXiv preprint"},{"key":"ref23","first-page":"876","article-title":"Averaging Weights Leads to Wider Optima and Better Generalization","volume-title":"Proc. Uncertainty in Artificial Intelligence (UAI)","author":"Izmailov","year":"2018"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249250.pdf?arnumber=11249250","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:07:22Z","timestamp":1764400042000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249250\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249250","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}