{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:01Z","timestamp":1777865341230,"version":"3.51.4"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62136007,62036011,U20B2065,6202781,62036005"],"award-info":[{"award-number":["62136007,62036011,U20B2065,6202781,62036005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02226","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24014-24023","source":"Crossref","is-referenced-by-count":0,"title":["TAViS: Text-bridged Audio-Visual Segmentation with Foundation Models"],"prefix":"10.1109","author":[{"given":"Ziyang","family":"Luo","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nian","family":"Liu","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuguang","family":"Yang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Salman","family":"Khan","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rao Muhammad","family":"Anwer","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hisham","family":"Cholakkal","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fahad Shahbaz","family":"Khan","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junwei","family":"Han","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i15.33709"},{"key":"ref3","article-title":"Leveraging foundation models for unsupervised audiovisual segmentation","author":"Bhosale","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01659"},{"key":"ref5","article-title":"Beats: Audio pre-training with acoustic tokenizers","author":"Chen","year":"2022","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00361"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02502"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01524"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29104"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681586"},{"key":"ref12","article-title":"Imagebind-llm: Multi-modality instruction tuning","volume":"3","author":"Han","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27978"},{"key":"ref14","first-page":"10077","article-title":"Discriminative sounding objects localization via self-supervised audiovisual matching","volume-title":"NeurIPS","volume":"33","author":"Hu","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3137988"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00559"},{"key":"ref17","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref19","article-title":"Cross-attentional audio-visual fusion for weakly-supervised action localization","volume-title":"ICLR","author":"Lee","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_27"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611724"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00327"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8683226"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446516"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3405622"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02487"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00551"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00513"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2025.3580269"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00094"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3419446"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02567"},{"key":"ref33","article-title":"Av-sam: Segment anything model meets audio-visual localization and segmentation","author":"Mo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2025.104460"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_18"},{"key":"ref36","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP51287.2024.10647485"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_21"},{"issue":"11","key":"ref39","article-title":"Visualizing data using t-sne","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"Journal of machine learning research"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28378"},{"key":"ref41","article-title":"Omnibind: Large-scale omni multimodal representation via binding spaces","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747669"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01464"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02562"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02261-x"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02261-x"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_22"},{"key":"ref48","article-title":"Languagebind: Extending video-language pretraining to n-modality by language-based semantic alignment","author":"Zhu","year":"2023","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11443362.pdf?arnumber=11443362","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:18:13Z","timestamp":1777529893000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443362\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02226","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}