{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,14]],"date-time":"2025-06-14T05:24:43Z","timestamp":1749878683512,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T00:00:00Z","timestamp":1693785600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T00:00:00Z","timestamp":1693785600000},"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":[[2023,9,4]]},"DOI":"10.23919\/eusipco58844.2023.10289751","type":"proceedings-article","created":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T13:55:44Z","timestamp":1698846944000},"page":"750-754","source":"Crossref","is-referenced-by-count":2,"title":["Attention-Based Methods For Audio Question Answering"],"prefix":"10.23919","author":[{"given":"Parthasaarathy","family":"Sudarsanam","sequence":"first","affiliation":[{"name":"Audio Research Group, Tampere University,Tampere,Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tuomas","family":"Virtanen","sequence":"additional","affiliation":[{"name":"Audio Research Group, Tampere University,Tampere,Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","author":"dosovitskiy","year":"0","journal-title":"In-ternational Conference on Learning Representations (ICLR)"},{"key":"ref12","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref15","article-title":"Assessment of Self-Attention on Learned Features For Sound Event Localization and Detection","author":"sudarsanam","year":"2021","journal-title":"Detection and Classification of Acoustic Scenes and Events (DCASE)"},{"key":"ref14","article-title":"Convolution-augmented transformer for semisupervised sound event detection","author":"miyazaki","year":"2020","journal-title":"Proceedings of the Detection and Classifi-cation of Acoustic Scenes and Events 2020 Workshop (DCASE2020)"},{"key":"ref20","article-title":"Advances in pretraining distributed word representations","author":"mikolov","year":"2018","journal-title":"Proc Int Conference on Language Resources and Evaluation (LREC)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO55093.2022.9909680"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0966-6"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref2","article-title":"ViLBERT: Pretraining Task- Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","author":"lu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref1","article-title":"Stacked Attention Networks for Image Question An-swering","author":"yang","year":"2016","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682475"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.499"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref8","article-title":"Dynamic coattention networks for question answering","author":"xiong","year":"2017","journal-title":"International Conference on Learning Representations"},{"key":"ref7","article-title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","author":"lan","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2018.2798607","article-title":"Mul-timodal machine learning: A survey and taxonomy","volume":"41","author":"baltru\u0161aitis","year":"2019","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00444"},{"key":"ref6","article-title":"BERT: Pretraining of Deep Bidirectional Transform-ers for Language Understanding","author":"devlin","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1203"}],"event":{"name":"2023 31st European Signal Processing Conference (EUSIPCO)","start":{"date-parts":[[2023,9,4]]},"location":"Helsinki, Finland","end":{"date-parts":[[2023,9,8]]}},"container-title":["2023 31st European Signal Processing Conference (EUSIPCO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10289698\/10289713\/10289751.pdf?arnumber=10289751","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T14:20:34Z","timestamp":1701094834000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10289751\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,4]]},"references-count":21,"URL":"https:\/\/doi.org\/10.23919\/eusipco58844.2023.10289751","relation":{},"subject":[],"published":{"date-parts":[[2023,9,4]]}}}