{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T18:58:07Z","timestamp":1770577087432,"version":"3.49.0"},"reference-count":68,"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.2025.3599048","type":"journal-article","created":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:01:05Z","timestamp":1755910865000},"page":"7407-7418","source":"Crossref","is-referenced-by-count":2,"title":["Complementary and Contrastive Learning 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"}]},{"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"}]},{"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"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1206-1444","authenticated-orcid":false,"given":"Pingping","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Future Technology, Dalian University of Technology, Dalian, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6668-9758","authenticated-orcid":false,"given":"Huchuan","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Future Technology, Dalian University of Technology, Dalian, China"}]}],"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":"10.1109\/ICASSP40776.2020.9053033"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3199109"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3102605"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00223"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3127029"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3324498"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3270624"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01326"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3417938"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27978"},{"key":"ref12","article-title":"Hear to segment: Unmixing the audio to guide the semantic segmentation","author":"Ling","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29104"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/97"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611724"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_18"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01018"},{"key":"ref19","first-page":"1","article-title":"A closer look at weakly-supervised audio-visual source localization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mo","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2885228"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR-Adjunct.2018.00056"},{"key":"ref22","article-title":"Audio-aware query-enhanced transformer for audio-visual segmentation","author":"Liu","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3405622"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3486344"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3225573"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref27","first-page":"13352","article-title":"Video instance segmentation using inter-frame communication transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Hwang","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref29","first-page":"23109","article-title":"VITA: Video instance segmentation via object token association","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Heo","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2671447"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3159403"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2890361"},{"key":"ref33","first-page":"2491","article-title":"Associating objects with transformers for video object segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Yang","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"ref35","article-title":"SOC: Semantic-assisted object cluster for referring video object segmentation","author":"Luo","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28465"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110535"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref39","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Khosla","year":"2020"},{"key":"ref40","first-page":"6827","article-title":"What makes for good views for contrastive learning?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Tian","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2025.113006"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00715"},{"key":"ref43","article-title":"Weakly-supervised audio-visual segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mo","year":"2023"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3580269"},{"key":"ref45","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref46","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02261-x"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00094"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref58","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00089"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2024.3405622"},{"key":"ref61","article-title":"A tutorial on principal component analysis","author":"Shlens","year":"2014"},{"issue":"11","key":"ref62","first-page":"2579","article-title":"Visualizing data using T-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Represent."},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00183"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02640"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72754-2_5"},{"key":"ref67","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref68","first-page":"1","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu","year":"2024"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11134791.pdf?arnumber=11134791","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T17:25:25Z","timestamp":1761153925000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11134791\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3599048","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}