{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T11:31:19Z","timestamp":1742988679162,"version":"3.40.3"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031463075"},{"type":"electronic","value":"9783031463082"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-46308-2_17","type":"book-chapter","created":{"date-parts":[[2023,10,29]],"date-time":"2023-10-29T18:01:24Z","timestamp":1698602484000},"page":"200-211","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GLTCM: Global-Local Temporal and Cross-Modal Network for Audio-Visual Event Localization"],"prefix":"10.1007","author":[{"given":"Xiaoyu","family":"Wu","sequence":"first","affiliation":[]},{"given":"Jucheng","family":"Qiu","sequence":"additional","affiliation":[]},{"given":"Qiurui","family":"Yue","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,10,30]]},"reference":[{"key":"17_CR1","doi-asserted-by":"crossref","unstructured":"Xu, J., Mei, T., Yao, T., Rui, Y.: MSR-VTT: a large video description dataset for bridging video and language. In: CVPR 2016, pp. 5288\u20135296 (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Tapaswi, M., Zhu, Y., Stiefelhagen, R., Torralba, A., Urtasun, R., Fidler, S.: MovieQA: understanding stories in movies through question-answering. In: CVPR 2016, pp. 4631\u20134640 (2016)","DOI":"10.1109\/CVPR.2016.501"},{"key":"17_CR3","doi-asserted-by":"crossref","unstructured":"Tian, Y., Shi, J., Li, B., Duan, Z., Xu, C.: Audio-Visual Event Localization in Unconstrained Videos. In: ECCV, vol. 2, pp. 252\u2013268 (2018)","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Lin, Y.B., Li, Y.J., Wang, Y.C.F. Dual-modality Seq2Seq network for audio-visual event localization. In: ICASSP 2019, pp. 2002\u20132006 (2019)","DOI":"10.1109\/ICASSP.2019.8683226"},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Xuan, H., Zhang, Z., Chen, S., Yang, J., Yan, Y.: Cross-modal attention network for temporal inconsistent audio-visual event localization. In: AAAI 2020, pp. 279\u2013286 (2020)","DOI":"10.1609\/aaai.v34i01.5361"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Duan, B., Tang, H., Wang, W., Zong, Z., Yang, G., Yan, Y.: Audio-visual event localization via recursive fusion by joint co-attention. In: WACV 2021, pp. 4012\u20134021 (2021)","DOI":"10.1109\/WACV48630.2021.00406"},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Yu, J., Cheng, Y., Feng, R.: MPN: multimodal parallel network for audio-visual event localization. In: ICME 2021, pp. 1\u20136 (2021)","DOI":"10.1109\/ICME51207.2021.9428373"},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"Wu, Y., Zhu, L., Yan, Y., Yang, Y.: Dual attention matching for audio-visual event localization. In: ICCV 2019, pp. 6291\u20136299 (2019)","DOI":"10.1109\/ICCV.2019.00639"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Ramaswamy, J.: What makes the sound?: A dual-modality interacting network for audio-visual event localization. In: ICASSP 2020, pp. 4372\u20134376 (2020)","DOI":"10.1109\/ICASSP40776.2020.9053895"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Lin, Y.B., Wang, Y.C.F.: Audiovisual transformer with instance attention for audio-visual event localization. In: ACCV, vol. 6, pp. 274\u2013290 (2020)","DOI":"10.1007\/978-3-030-69544-6_17"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Xu, H., Zeng, R., Wu, Q., Tan, M., Gan, C.: Cross-modal relation-aware networks for audio-visual event localization. In: ACM Multimedia 2020, pp. 3893\u20133901 (2020)","DOI":"10.1145\/3394171.3413581"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Zhou, J., Zheng, L., Zhong, Y., Hao, S., Wang, M.: Positive sample propagation along the audio-visual event line. In: CVPR 2021, pp. 8436\u20138444 (2021)","DOI":"10.1109\/CVPR46437.2021.00833"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Zhou, J., Guo, D., Wang, M.: Contrastive positive sample propagation along the audio-visual event line. IEEE Trans. Pattern Anal. Mach. Intell. (2022)","DOI":"10.1109\/CVPR46437.2021.00833"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Lin, Y.B., Sung, Y.L., Lei, J., et al. Vision transformers are parameter-efficient audio-visual learners. arXiv preprint arXiv:2212.07983 (2022)","DOI":"10.1109\/CVPR52729.2023.00228"},{"key":"17_CR15","unstructured":"Wang, H., Zha, Z.J., Li, L., et al.: Multi-modulation network for audio-visual event localization. arXiv preprint arXiv:2108.11773 (2021)"},{"key":"17_CR16","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML 2021, pp. 8748\u20138763 (2017)"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Hershey, S., et al.: CNN architectures for large-scale audio classification. ICASSP 2017, pp. 131\u2013135 (2017)","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Qing, Z., et al.: Temporal context aggregation network for temporal action proposal refinement. In: CVPR 2021, pp. 485\u2013494 (2021)","DOI":"10.1109\/CVPR46437.2021.00055"}],"container-title":["Lecture Notes in Computer Science","Image and Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-46308-2_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,29]],"date-time":"2023-10-29T18:03:38Z","timestamp":1698602618000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-46308-2_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031463075","9783031463082"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-46308-2_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"30 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIG","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image and Graphics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nanjing","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icig2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/icig2023.csig.org.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Conference Management Toolkit","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"409","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"166","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"41% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}