{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T21:00:26Z","timestamp":1775682026118,"version":"3.50.1"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3679674","type":"journal-article","created":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T20:13:40Z","timestamp":1775074420000},"page":"51558-51575","source":"Crossref","is-referenced-by-count":0,"title":["Architectural Scalability and Attention Stabilization for Robust Impulsive Acoustic Spectrogram Classification Using Swin Transformer V2"],"prefix":"10.1109","volume":"14","author":[{"given":"Pafan","family":"Doungpaisan","sequence":"first","affiliation":[{"name":"Faculty of Industrial Technology and Management, King Mongkut’s University of Technology North Bangkok (KMUTNB), Bangkok, Thailand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4252-078X","authenticated-orcid":false,"given":"Peerapol","family":"Khunarsa","sequence":"additional","affiliation":[{"name":"Faculty of Science and Technology, Uttaradit Rajabhat University, Uttaradit, Thailand"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gunshot detection systems: A review","volume":"169","author":"Valero","year":"2020","journal-title":"Appl. Acoust."},{"issue":"4","key":"ref2","first-page":"92","article-title":"Urban acoustic surveillance: Gunshot detection and localization","volume":"33","author":"Greenberg","year":"2016","journal-title":"IEEE Signal Process. Mag."},{"key":"ref3","first-page":"12214","article-title":"Gunshot detection and classification using convolutional neural networks for real-time surveillance","volume":"10","author":"Khan","year":"2022","journal-title":"IEEE Access"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1111\/2041-210x.13103"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/mlsp.2015.7324337"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2017.7952132"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2017.7952651"},{"key":"ref8","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"33","author":"Baevski"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2017.7952601"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-698"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00986"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging11080281"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01167"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/access.2020.3019084"},{"key":"ref16","first-page":"1205","article-title":"Torchaudio: Building blocks for audio and speech processing in PyTorch","volume":"32","author":"Yang","year":"2024","journal-title":"IEEE\/ACM Trans. Audio, Speech, Language Process."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63450-0"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01170"},{"key":"ref19","article-title":"Architectural stability and scaling laws for vision transformers","author":"Liu","year":"2021","journal-title":"arXiv:2111.09883"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/msp.2021.3090678"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2021.3066303"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/i-smac52330.2021.9640649"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/lsp.2017.2657381"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/machines14010114"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2020.3030497"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01179"},{"key":"ref28","first-page":"10524","article-title":"On layer normalization in the transformer architecture","volume-title":"Proc. 37th Int. Conf. Mach. Learn. (ICML)","volume":"119","author":"Xiong"},{"key":"ref29","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3530811"},{"key":"ref31","first-page":"12116","article-title":"Do vision transformers see like convolutional neural networks?","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Raghu"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n18-2074"},{"key":"ref33","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"139","author":"Touvron"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3317287.3328534"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533234"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2023.109091"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1067\/mod.2000.109032"},{"issue":"184","key":"ref38","first-page":"1","article-title":"Why do deep convolutional networks generalize so poorly to small image transformations?","volume":"20","author":"Azulay","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1186\/s12864-019-6413-7"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"ref41","first-page":"2098","article-title":"Audio spectrogram transformer for environmental sound classification","volume":"29","author":"Chen","year":"2022","journal-title":"IEEE Signal Process. Lett."},{"key":"ref42","first-page":"73245","article-title":"Swin transformer-based spectrogram learning for acoustic event classification","volume":"11","author":"Chen","year":"2023","journal-title":"IEEE Access"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2025.3550866"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICLT63507.2024.11038668"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref47","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. 36th Int. Conf. Mach. Learn. (ICML) (Proceedings of Machine Learning Research)","volume":"97","author":"Tan"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11460128.pdf?arnumber=11460128","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T20:07:15Z","timestamp":1775678835000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11460128\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3679674","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}