{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:55:24Z","timestamp":1784300124324,"version":"3.55.0"},"reference-count":70,"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":["62406053"],"award-info":[{"award-number":["62406053"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62441231"],"award-info":[{"award-number":["62441231"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206039"],"award-info":[{"award-number":["62206039"]}],"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":["DUT24YG119"],"award-info":[{"award-number":["DUT24YG119"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["DUT24RC(3)025"],"award-info":[{"award-number":["DUT24RC(3)025"]}],"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.2025.3542995","type":"journal-article","created":{"date-parts":[[2025,2,17]],"date-time":"2025-02-17T13:36:16Z","timestamp":1739799376000},"page":"5413-5425","source":"Crossref","is-referenced-by-count":15,"title":["AVS-Mamba: Exploring Temporal and Multi-Modal Mamba for Audio-Visual Segmentation"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8661-1093","authenticated-orcid":false,"given":"Sitong","family":"Gong","sequence":"first","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4288-4516","authenticated-orcid":false,"given":"Yunzhi","family":"Zhuge","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4648-4437","authenticated-orcid":false,"given":"Lu","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1911-2526","authenticated-orcid":false,"given":"Yifan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Innovation and Entrepreneurship, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1206-1444","authenticated-orcid":false,"given":"Pingping","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Future Technology and the School of Artificial Intelligence, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2538-8358","authenticated-orcid":false,"given":"Lijun","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Future Technology and the School of Artificial Intelligence, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6668-9758","authenticated-orcid":false,"given":"Huchuan","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Future Technology and the School of Artificial Intelligence, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"386","article-title":"Audiovisual segmentation","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Zhou","year":"2022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02261-x"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27978"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29104"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/97"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611724"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3486344"},{"key":"ref8","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023"},{"key":"ref9","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024"},{"key":"ref10","article-title":"VMamba: Visual state space model","author":"Liu","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3199109"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053033"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3127029"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3324498"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3150469"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3270624"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20073"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3337134"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3309559"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3367599"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3283879"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3418980"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2025.3580269"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00094"},{"key":"ref27","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref28","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf., Mach. Learn.","author":"Touvron","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref30","article-title":"Vivim: A video vision mamba for medical video object segmentation","author":"Yang","year":"2024"},{"key":"ref31","article-title":"MedMamba: Vision mamba for medical image classification","author":"Yue","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-5128-0_27"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.21203\/rs.3.rs-4963037\/v1","article-title":"P-Mamba: Marrying Perona Malik diffusion with mamba for efficient pediatric echocardiographic left ventricular segmentation","author":"Ye","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2024.3414293"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2024.3407111"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2024.3404604"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3417253"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_13"},{"key":"ref39","article-title":"U-shaped vision mamba for single image dehazing","author":"Zheng","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3530090"},{"key":"ref41","article-title":"Vl-Mamba: Exploring state space models for multimodal learning","author":"Qiao","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33131"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_7"},{"key":"ref44","article-title":"RoboMamba: Multimodal state space model for efficient robot reasoning and manipulation","author":"Liu","year":"2024"},{"key":"ref45","article-title":"Video mamba suite: State space model as a versatile alternative for video understanding","author":"Chen","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"ref47","article-title":"VideoMambaPro: A leap forward for mamba in video understanding","author":"Lu","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.129178"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3485721"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32690"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91979-4_2"},{"key":"ref52","article-title":"PlainMamba: Improving non-hierarchical mamba in visual recognition","author":"Yang","year":"2024"},{"key":"ref53","article-title":"Multi-scale VMamba: Hierarchy in hierarchy visual state space model","author":"Shi","year":"2024"},{"key":"ref54","article-title":"AV-Mamba: Cross-modality selective state space models for audio-visual question answering","author":"Huang"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01852"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680926"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1115\/1.3662552"},{"key":"ref58","article-title":"HiViT: A simpler and more efficient design of hierarchical vision transformer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2023"},{"key":"ref59","article-title":"RES-VMamba: Fine-grained food category visual classification using selective state space models with deep residual learning","author":"Chen","year":"2024"},{"key":"ref60","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020"},{"key":"ref61","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3394682"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3405622"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref70","article-title":"A tutorial on principal component analysis","author":"Shlens","year":"2014"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10891410.pdf?arnumber=10891410","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T04:24:05Z","timestamp":1756355045000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10891410\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3542995","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}