{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:39:58Z","timestamp":1780947598557,"version":"3.54.1"},"reference-count":74,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U2336212"],"award-info":[{"award-number":["U2336212"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["226-2022-00051"],"award-info":[{"award-number":["226-2022-00051"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3557637","type":"journal-article","created":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T17:17:07Z","timestamp":1744305427000},"page":"2999-3008","source":"Crossref","is-referenced-by-count":6,"title":["Exploiting EfficientSAM and Temporal Coherence for Audio-Visual Segmentation"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-7473-3155","authenticated-orcid":false,"given":"Yue","family":"Zhu","sequence":"first","affiliation":[{"name":"ReLER, University of Technology Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5083-2145","authenticated-orcid":false,"given":"Kun","family":"Li","sequence":"additional","affiliation":[{"name":"ReLER, CCAI, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8783-8313","authenticated-orcid":false,"given":"Zongxin","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Harvard Medical School, Harvard University, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683226"},{"key":"ref2","first-page":"11449","article-title":"Exploring cross-video and cross-modality signals for weakly-supervised audio-visual video parsing","volume":"34","author":"Lin","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093616"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1631\/fitee.2100463"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.2400250"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2021.08.016"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_26"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00138"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00639"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413581"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5361"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547869"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00833"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16285"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3358415"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548241"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref19","article-title":"SoundNet: Learning sound representations from unlabeled video","volume":"29","author":"Aytar","year":"2016","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01659"},{"key":"ref21","first-page":"10077","article-title":"Discriminative sounding objects localization via self-supervised audiovisual matching","volume":"33","author":"Hu","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_18"},{"key":"ref23","first-page":"386","article-title":"Audiovisual segmentation","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Zhou","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00094"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29104"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01525"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00458"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413869"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2952095"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00621"},{"key":"ref33","first-page":"3222","article-title":"Self-supervised predictive learning: A negative-free method for sound source localization in visual scenes","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Song","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103602"},{"key":"ref35","article-title":"Audio-visual segmentation, sound localization, semantic-aware sounding objects localization","author":"Liu","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27978"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611724"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/97"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02487"},{"key":"ref40","article-title":"Contrastive conditional latent diffusion for audio-visual segmentation","author":"Mao","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3486344"},{"key":"ref42","first-page":"1692","article-title":"One transformer fits all distributions in multi-modal diffusion at scale","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bao","year":"2023"},{"key":"ref43","first-page":"5178","article-title":"Beats: Audio pre-training with acoustic tokenizers","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","volume":"202","author":"Chen","year":"2023"},{"key":"ref44","article-title":"AV-SAM: Segment anything model meets audio-visual localization and segmentation","author":"Mo","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00551"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref47","article-title":"SAD: Segment any RGBD","author":"Cen","year":"2023"},{"key":"ref48","article-title":"Semantic segment anything","author":"Chen","year":"2023"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00361"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.2352\/ei.2025.37.14.coimg-132"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103547"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102918"},{"key":"ref53","article-title":"Segment and track anything","author":"Cheng","year":"2023"},{"key":"ref54","article-title":"Track anything: Segment anything meets videos","author":"Yang","year":"2023"},{"key":"ref55","article-title":"SAM-helps-shadow: When segment anything model meet shadow removal","author":"Zhang","year":"2023"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3320688"},{"key":"ref57","article-title":"Deshadow-anything: When segment anything model meets zero-shot shadow removal","author":"Zhang","year":"2023"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612680"},{"key":"ref59","article-title":"Anything-3D: Towards single-view anything reconstruction in the wild","author":"Shen","year":"2023"},{"key":"ref60","first-page":"25971","article-title":"Segment anything in 3D with NeRFs","volume":"36","author":"Cen","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref61","article-title":"Faster segment anything: Towards lightweight SAM for mobile applications","author":"Zhang","year":"2023"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3405622"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref65","article-title":"Making a case for 3D convolutions for object segmentation in videos","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Mahadevan","year":"2020"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00585"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3469286"},{"key":"ref68","first-page":"15448","article-title":"Learning generative vision transformer with energy-based latent space for saliency prediction","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Zhang","year":"2021"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28378"},{"key":"ref70","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kingma","year":"2017"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02261-x"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10960649.pdf?arnumber=10960649","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T17:30:47Z","timestamp":1748539847000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10960649\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3557637","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}