{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T10:46:49Z","timestamp":1771843609781,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Fundamental Research Funds for the Central Universities of China","award":["2024JBMC008"],"award-info":[{"award-number":["2024JBMC008"]}]},{"name":"Natural Science Foundation of China","award":["61972027"],"award-info":[{"award-number":["61972027"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100005089","name":"Beijing Municipal Natural Science Foundation","doi-asserted-by":"publisher","award":["4212041"],"award-info":[{"award-number":["4212041"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100005089","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681232","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"7503-7512","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["OpenAVE: Moving towards Open Set Audio-Visual Event Localization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9335-0151","authenticated-orcid":false,"given":"Jiale","family":"Yu","sequence":"first","affiliation":[{"name":"Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2592-2354","authenticated-orcid":false,"given":"Baopeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1754-4878","authenticated-orcid":false,"given":"Zhu","family":"Teng","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2693-1172","authenticated-orcid":false,"given":"Jianping","family":"Fan","sequence":"additional","affiliation":[{"name":"AI Lab at Lenovo Research, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01310"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00299"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.173"},{"key":"e_1_3_2_1_4_1","volume-title":"Enlarging Instance-specific and Class-specific Information for Open-set Action Recognition. In 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 15295--15304","author":"Cen Jun","year":"2023","unstructured":"Jun Cen, Shiwei Zhang, Xiang Wang, Yixuan Pei, Zhiwu Qing, Yingya Zhang, and Qifeng Chen. 2023. Enlarging Instance-specific and Class-specific Information for Open-set Action Recognition. In 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 15295--15304. https:\/\/doi.org\/10.1109\/ CVPR52729.2023.01468"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01526"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3106743"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3106743"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_30"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01416"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_12"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093355"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01805"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01047"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612506"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612278"},{"key":"e_1_3_2_1_18_1","volume-title":"Egocentric Audio-Visual Object Localization. In 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 22910--22921","author":"Huang Chao","year":"2023","unstructured":"Chao Huang, Yapeng Tian, Anurag Kumar, and Chenliang Xu. 2023. Egocentric Audio-Visual Object Localization. In 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 22910--22921. https:\/\/doi.org\/10.1109\/ CVPR52729.2023.02194"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00123"},{"key":"e_1_3_2_1_20_1","volume-title":"Towards Open World Object Detection. In 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 5826--5836","author":"Joseph K J","year":"2021","unstructured":"K J Joseph, Salman Khan, Fahad Shahbaz Khan, and Vineeth N Balasubramanian. 2021. Towards Open World Object Detection. In 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 5826--5836. https:\/\/doi.org\/10. 1109\/CVPR46437.2021.00577"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683226"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00098"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_38"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00241"},{"key":"e_1_3_2_1_25_1","volume-title":"Haoda Li, Peng Dai, and Juwei Lu.","author":"Rao Varshanth","year":"2022","unstructured":"Varshanth Rao, Md Ibrahim Khalil, Haoda Li, Peng Dai, and Juwei Lu. 2022. Dual Perspective Network for Audio-Visual Event Localization. In Computer Vision - ECCV 2022, Shai Avidan, Gabriel Brostow, Moustapha Ciss\u00e9, Giovanni Maria Farinella, and Tal Hassner (Eds.). Springer Nature Switzerland, Cham, 689--704."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI"},{"key":"e_1_3_2_1_27_1","volume-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv 1409.1556 (09","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv 1409.1556 (09 2014)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613805"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01349"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01349"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00917"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00639"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413581"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5361"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00414"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611824"},{"key":"e_1_3_2_1_40_1","volume-title":"Proceedings of the 29th Pacific Asia Conference on Language, Information and Computation, Hai Zhao (Ed.)","author":"Zhang Shu","year":"2015","unstructured":"Shu Zhang, Dequan Zheng, Xinchen Hu, and Ming Yang. 2015. Bidirectional Long Short-Term Memory Networks for Relation Classification. In Proceedings of the 29th Pacific Asia Conference on Language, Information and Computation, Hai Zhao (Ed.). Shanghai, China, 73--78. https:\/\/aclanthology.org\/Y15-1009"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3119969"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02201"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00833"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681232","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681232","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:03Z","timestamp":1750295883000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681232"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":43,"alternative-id":["10.1145\/3664647.3681232","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681232","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}