{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T00:29:34Z","timestamp":1755217774176,"version":"3.43.0"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003995","name":"Natural Science Foundation of Anhui Province","doi-asserted-by":"publisher","award":["2308085QF221"],"award-info":[{"award-number":["2308085QF221"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302006"],"award-info":[{"award-number":["62302006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Research Project of Anhui Educational Committee","award":["2024AH040012"],"award-info":[{"award-number":["2024AH040012"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/lsp.2025.3586552","type":"journal-article","created":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T13:54:47Z","timestamp":1751896487000},"page":"2883-2887","source":"Crossref","is-referenced-by-count":0,"title":["X-STA: Cross-Modal Spatial-Temporal Alignment Network for Unified Audio-Visual Segmentation"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4633-2794","authenticated-orcid":false,"given":"Hanyu","family":"Xuan","sequence":"first","affiliation":[{"name":"School of Big Data and Statistics, Anhui University, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6832-3350","authenticated-orcid":false,"given":"Tongxing","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Big Data and Statistics, Anhui University, Hefei, China"}]},{"given":"Wenxiang","family":"Dong","sequence":"additional","affiliation":[{"name":"Institute of Dataspace, Hefei Comprehensive National Science Center, Hefei, China"}]},{"given":"Zhongheng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Cyberspace Security, University of Science and Technology of China, Hefei, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0159-8851","authenticated-orcid":false,"given":"Shuo","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Intelligence Science and Technology, Nanjing University, Suzhou, Jiangsu, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/srep46413"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3106814"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5361"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01936"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00639"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69544-6_17"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3127029"},{"key":"ref9","first-page":"5","article-title":"Audio-visual event localization in the wild","volume-title":"Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. Workshops","author":"Tian","year":"2019"},{"key":"ref10","first-page":"10077","article-title":"Discriminative sounding objects localization via self-supervised audiovisual matching","author":"Hu","year":"2020","journal-title":"Adv. Neural Info. Process. Sys."},{"key":"ref11","first-page":"11449","article-title":"Exploring cross-video and cross-modality signals for weakly-supervised audio-visual video parsing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lin","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547869"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_26"},{"key":"ref14","first-page":"34722","article-title":"Multi-modal grouping network for weakly-supervised audio-visual video parsing","volume":"35","author":"Mo","year":"2022","journal-title":"Adv. Neural Inf. Proces. Sys."},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00552"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00935"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_18"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01659"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00110"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3363508"},{"key":"ref22","first-page":"386","article-title":"Audiovisual segmentation","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Zhou","year":"2022"},{"article-title":"Hear to segment: Unmixing the audio to guide the semantic segmentation","year":"2023","author":"Ling","key":"ref23"},{"article-title":"BcVinet: Unlocking blind","year":"2025","author":"Wu","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28435"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02163"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00551"},{"article-title":"AV-SAM: Segment anything model meets audio-visual localization and segmentation","year":"2023","author":"Mo","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00551"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28378"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.5244\/C.34.65"},{"article-title":"Transformer transforms salient object detection and camouflaged object detection","year":"2021","author":"Mao","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00585"},{"key":"ref35","first-page":"15448","article-title":"Learning generative vision transformer with energy-based latent space for saliency prediction","volume":"34","author":"Zhang","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3532306"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00361"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29104"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27978"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/506"},{"key":"ref42","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov","year":"2019"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9781107298019"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/10802935\/11072277.pdf?arnumber=11072277","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,5]],"date-time":"2025-08-05T18:09:41Z","timestamp":1754417381000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11072277\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/lsp.2025.3586552","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"type":"print","value":"1070-9908"},{"type":"electronic","value":"1558-2361"}],"subject":[],"published":{"date-parts":[[2025]]}}}