{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T04:47:28Z","timestamp":1785818848501,"version":"3.56.0"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"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 Trans. Comput. Soc. Syst."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/tcss.2026.3694468","type":"journal-article","created":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T20:07:56Z","timestamp":1780430876000},"page":"4313-4326","source":"Crossref","is-referenced-by-count":0,"title":["SPECTRA-AVQA-Net: Sparse Perceptual Enhancement With Cross-Modal Transformation for Audio\u2013Visual Question Answering"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0803-3566","authenticated-orcid":false,"given":"Debashis","family":"Das","sequence":"first","affiliation":[{"name":"Indian Institute of Technology Patna","place":["Patna, Bihar, India"],"department":["Department of Computer Science & Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4019-0980","authenticated-orcid":false,"given":"Suman Kumar","family":"Maji","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Patna","place":["Patna, Bihar, India"],"department":["Department of Computer Science & Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-025-11163-4"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.128857","article-title":"Multimodal context-aware consistency alignment for vision-language tasks","volume":"295","author":"Shen","year":"2026","journal-title":"Expert Syst. Appl."},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3318220"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01852"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548291"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2789524"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-017-1060-7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00204"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612293"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28116"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680803"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00709"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00228"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01659"},{"key":"ref17","article-title":"Learning in audio-visual context: A review, analysis, and new perspective","author":"Wei","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3162477"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3137988"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223688"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446092"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_3"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73464-9_19"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01591"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0695"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0007"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref30","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2024.103983","article-title":"Cascade transformers with dynamic attention for video question answering","volume":"242","author":"Jiang","year":"2024","journal-title":"Comput. Vis. Image Understand."},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33138"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02289-z"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2024.findings-emnlp.933","article-title":"SaSR-Net: Source-aware semantic representation network for enhancing audio-visual question answering","author":"Yang","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01315"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01277"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"ref40","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020"},{"key":"ref41","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Machine Learn","author":"Radford","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018658"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01919"}],"container-title":["IEEE Transactions on Computational Social Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570650\/11640440\/11547229.pdf?arnumber=11547229","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T04:37:49Z","timestamp":1785818269000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11547229\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":44,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcss.2026.3694468","relation":{},"ISSN":["2329-924X","2373-7476"],"issn-type":[{"value":"2329-924X","type":"electronic"},{"value":"2373-7476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]}}}