{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T18:51:56Z","timestamp":1773773516455,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61971352, 62271239"],"award-info":[{"award-number":["61971352, 62271239"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ningbo Natural Science Foundation","award":["2021J048, 2021J049"],"award-info":[{"award-number":["2021J048, 2021J049"]}]},{"name":"Jiangxi Double Thousand Plan","award":["JXSQ2023201022"],"award-info":[{"award-number":["JXSQ2023201022"]}]},{"DOI":"10.13039\/100020593","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["D5000220190"],"award-info":[{"award-number":["D5000220190"]}],"id":[{"id":"10.13039\/100020593","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Innovative Research Foundation of Ship General Performance","doi-asserted-by":"publisher","award":["25522108"],"award-info":[{"award-number":["25522108"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612502","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:12Z","timestamp":1698391632000},"page":"4042-4052","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Induction Network: Audio-Visual Modality Gap-Bridging for Self-Supervised Sound Source Localization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9098-5944","authenticated-orcid":false,"given":"Tianyu","family":"Liu","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University & Ningbo Institute of Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9690-7026","authenticated-orcid":false,"given":"Peng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University & Ningbo Institute of Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0541-8612","authenticated-orcid":false,"given":"Wei","family":"Huang","sequence":"additional","affiliation":[{"name":"Nanchang University, Nanchang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5013-2501","authenticated-orcid":false,"given":"Yufei","family":"Zha","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University & Ningbo Institute of Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0023-7617","authenticated-orcid":false,"given":"Tao","family":"You","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2977-8057","authenticated-orcid":false,"given":"Yanning","family":"Zhang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"e_1_3_2_1_2_1","first-page":"4660","article-title":"Labelling unlabelled videos from scratch with multi-modal self-supervision","volume":"33","author":"Asano Yuki","year":"2020","unstructured":"Yuki Asano, Mandela Patrick, Christian Rupprecht, and Andrea Vedaldi. 2020. Labelling unlabelled videos from scratch with multi-modal self-supervision. Advances in Neural Information Processing Systems, Vol. 33 (2020), 4660--4671.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383344"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01659"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/0141--9382(92)90100-6"},{"key":"e_1_3_2_1_9_1","volume-title":"Sinkhorn distances: Lightspeed computation of optimal transport. Advances in neural information processing systems","author":"Cuturi Marco","year":"2013","unstructured":"Marco Cuturi. 2013. Sinkhorn distances: Lightspeed computation of optimal transport. Advances in neural information processing systems, Vol. 26 (2013)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_11_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_12_1","volume-title":"Looking to listen at the cocktail party: A speaker-independent audio-visual model for speech separation. arXiv preprint arXiv:1804.03619","author":"Ephrat Ariel","year":"2018","unstructured":"Ariel Ephrat, Inbar Mosseri, Oran Lang, Tali Dekel, Kevin Wilson, Avinatan Hassidim, William T Freeman, and Michael Rubinstein. 2018. Looking to listen at the cocktail party: A speaker-independent audio-visual model for speech separation. arXiv preprint arXiv:1804.03619 (2018)."},{"key":"e_1_3_2_1_13_1","volume-title":"A cortical circuit for audio-visual predictions. Nature neuroscience","author":"Garner Aleena R","year":"2022","unstructured":"Aleena R Garner and Georg B Keller. 2022. A cortical circuit for audio-visual predictions. Nature neuroscience, Vol. 25, 1 (2022), 98--105."},{"key":"e_1_3_2_1_14_1","volume-title":"Zhaohan Guo, Mohammad Gheshlaghi Azar, et al.","author":"Grill Jean-Bastien","year":"2020","unstructured":"Jean-Bastien Grill, Florian Strub, Florent Altch\u00e9, Corentin Tallec, Pierre Richemond, Elena Buchatskaya, Carl Doersch, Bernardo Avila Pires, Zhaohan Guo, Mohammad Gheshlaghi Azar, et al. 2020. Bootstrap your own latent-a new approach to self-supervised learning. Advances in neural information processing systems, Vol. 33 (2020), 21271--21284."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_5"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00947"},{"key":"e_1_3_2_1_18_1","first-page":"10077","article-title":"Discriminative sounding objects localization via self-supervised audiovisual matching","volume":"33","author":"Hu Di","year":"2020","unstructured":"Di Hu, Rui Qian, Minyue Jiang, Xiao Tan, Shilei Wen, Errui Ding, Weiyao Lin, and Dejing Dou. 2020b. Discriminative sounding objects localization via self-supervised audiovisual matching. Advances in Neural Information Processing Systems, Vol. 33 (2020), 10077--10087.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01023"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.3758\/BF03203206"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.274"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"e_1_3_2_1_23_1","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Korbar Bruno","year":"2018","unstructured":"Bruno Korbar, Du Tran, and Lorenzo Torresani. 2018. Cooperative learning of audio and video models from self-supervised synchronization. Advances in Neural Information Processing Systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"e_1_3_2_1_25_1","volume-title":"Oh (Eds.)","volume":"35","author":"Mo Shentong","year":"2022","unstructured":"Shentong Mo and Pedro Morgado. 2022. A Closer Look at Weakly-Supervised Audio-Visual Source Localization. In Advances in Neural Information Processing Systems, S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh (Eds.), Vol. 35. Curran Associates, Inc., 37524--37536. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/f3f2ff9579ba6deeb89caa2fe1f0b99c-Paper-Conference.pdf"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01274"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01229"},{"key":"e_1_3_2_1_28_1","volume-title":"Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748","author":"van den Oord Aaron","year":"2018","unstructured":"Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937237"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_18"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2022.102162"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00458"},{"key":"e_1_3_2_1_34_1","volume-title":"Learning to localize sound sources in visual scenes: Analysis and applications","author":"Senocak Arda","year":"2019","unstructured":"Arda Senocak, Tae-Hyun Oh, Junsik Kim, Ming-Hsuan Yang, and In So Kweon. 2019. Learning to localize sound sources in visual scenes: Analysis and applications. IEEE transactions on pattern analysis and machine intelligence, Vol. 43, 5 (2019), 1605--1619."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00065"},{"key":"e_1_3_2_1_36_1","volume-title":"Cross modal video representations for weakly supervised active speaker localization. arXiv e-prints","author":"Sharma Rahul","year":"2020","unstructured":"Rahul Sharma, Krishna Somandepalli, and Shrikanth Narayanan. 2020. Cross modal video representations for weakly supervised active speaker localization. arXiv e-prints (2020), arXiv-2003."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00222"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.868688"},{"key":"e_1_3_2_1_39_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 3222--3231","author":"Song Zengjie","year":"2022","unstructured":"Zengjie Song, Yuxi Wang, Junsong Fan, Tieniu Tan, and Zhaoxiang Zhang. 2022. Self-Supervised Predictive Learning: A Negative-Free Method for Sound Source Localization in Visual Scenes. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 3222--3231."},{"key":"e_1_3_2_1_40_1","volume-title":"Learning Audio-Visual Source Localization via False Negative Aware Contrastive Learning. arXiv preprint arXiv:2303.11302","author":"Sun Weixuan","year":"2023","unstructured":"Weixuan Sun, Jiayi Zhang, Jianyuan Wang, Zheyuan Liu, Yiran Zhong, Tianpeng Feng, Yandong Guo, Yanhao Zhang, and Nick Barnes. 2023. Learning Audio-Visual Source Localization via False Negative Aware Contrastive Learning. arXiv preprint arXiv:2303.11302 (2023)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2812802"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00277"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00114"},{"key":"e_1_3_2_1_45_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01414"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00110"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00637"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2022.102160"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-021-1293-0"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.95"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612502","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612502","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:01:51Z","timestamp":1755820911000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612502"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":52,"alternative-id":["10.1145\/3581783.3612502","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612502","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}