{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:21:24Z","timestamp":1772907684832,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":34,"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":[{"name":"Collaborative Innovation Center of Novel Software Technology and Industrialization"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972192, 62172208, 61906085, 41972111"],"award-info":[{"award-number":["61972192, 62172208, 61906085, 41972111"]}],"id":[{"id":"10.13039\/501100001809","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\/3581783.3612506","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:26:54Z","timestamp":1698391614000},"page":"3446-3454","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Learning Event-Specific Localization Preferences for Audio-Visual Event Localization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9198-5324","authenticated-orcid":false,"given":"Shiping","family":"Ge","sequence":"first","affiliation":[{"name":"Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5243-4992","authenticated-orcid":false,"given":"Zhiwei","family":"Jiang","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9497-6244","authenticated-orcid":false,"given":"Yafeng","family":"Yin","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0916-7803","authenticated-orcid":false,"given":"Cong","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8486-2614","authenticated-orcid":false,"given":"Zifeng","family":"Cheng","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1112-790X","authenticated-orcid":false,"given":"Qing","family":"Gu","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}]}],"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\/CVPR52688.2022.00792"},{"key":"e_1_3_2_1_2_1","volume-title":"Cross-modal memory networks for radiology report generation. arXiv preprint arXiv:2204.13258","author":"Chen Zhihong","year":"2022","unstructured":"Zhihong Chen, Yaling Shen, Yan Song, and Xiang Wan. 2022. Cross-modal memory networks for radiology report generation. arXiv preprint arXiv:2204.13258 (2022)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_1_7_1","volume-title":"Jort F Gemmeke, Aren Jansen, R Channing Moore, Manoj Plakal, Devin Platt, Rif A Saurous, Bryan Seybold, et al.","author":"Hershey Shawn","year":"2017","unstructured":"Shawn Hershey, Sourish Chaudhuri, Daniel PW Ellis, Jort F Gemmeke, Aren Jansen, R Channing Moore, Manoj Plakal, Devin Platt, Rif A Saurous, Bryan Seybold, et al. 2017. CNN architectures for large-scale audio classification. In 2017 ieee international conference on acoustics, speech and signal processing (icassp). IEEE, 131--135."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00196"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00431"},{"key":"e_1_3_2_1_10_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21346"},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the Asian Conference on Computer Vision.","author":"Lin Yan-Bo","year":"2020","unstructured":"Yan-Bo Lin and Yu-Chiang Frank Wang. 2020. Audiovisual transformer with instance attention for audio-visual event localization. In Proceedings of the Asian Conference on Computer Vision."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20058"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01876"},{"key":"e_1_3_2_1_16_1","volume-title":"Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983","author":"Loshchilov Ilya","year":"2016","unstructured":"Ilya Loshchilov and Frank Hutter. 2016. Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 (2016)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00513"},{"key":"e_1_3_2_1_18_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053895"},{"key":"e_1_3_2_1_20_1","volume-title":"Dual Perspective Network for Audio-Visual Event Localization. In European Conference on Computer Vision. Springer, 689--704","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 European Conference on Computer Vision. Springer, 689--704."},{"key":"e_1_3_2_1_21_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"e_1_3_2_1_23_1","article-title":"Visualizing data using t-SNE","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research, Vol. 9, 11 (2008).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_24_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_25_1","volume-title":"Memory networks. arXiv preprint arXiv:1410.3916","author":"Weston Jason","year":"2014","unstructured":"Jason Weston, Sumit Chopra, and Antoine Bordes. 2014. Memory networks. arXiv preprint arXiv:1410.3916 (2014)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548318"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00639"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01936"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413581"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5361"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428373"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547869"},{"key":"e_1_3_2_1_33_1","volume-title":"Topic memory networks for short text classification. arXiv preprint arXiv:1809.03664","author":"Zeng Jichuan","year":"2018","unstructured":"Jichuan Zeng, Jing Li, Yan Song, Cuiyun Gao, Michael R Lyu, and Irwin King. 2018. Topic memory networks for short text classification. arXiv preprint arXiv:1809.03664 (2018)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00833"}],"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\/3581783.3612506","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612506","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:54:51Z","timestamp":1755820491000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612506"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":34,"alternative-id":["10.1145\/3581783.3612506","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612506","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"}}]}}