乐胖代购免代理版

{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T04:07:07Z","timestamp":1743134827591,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819985364"},{"type":"electronic","value":"9789819985371"}],"license":[{"start":{"date-parts":[[2023,12,26]],"date-time":"2023-12-26T00:00:00Z","timestamp":1703548800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,26]],"date-time":"2023-12-26T00:00:00Z","timestamp":1703548800000},"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":[[2024]]},"DOI":"10.1007\/978-981-99-8537-1_17","type":"book-chapter","created":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T19:02:17Z","timestamp":1703530937000},"page":"207-219","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Unimodal-Multimodal Collaborative Enhancement for\u00a0Audio-Visual Event Localization"],"prefix":"10.1007","author":[{"given":"Huilin","family":"Tian","sequence":"first","affiliation":[]},{"given":"Jingke","family":"Meng","sequence":"additional","affiliation":[]},{"given":"Yuhan","family":"Yao","sequence":"additional","affiliation":[]},{"given":"Weishi","family":"Zheng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,12,26]]},"reference":[{"key":"17_CR1","first-page":"1882","volume":"32","author":"Y Cao","year":"2023","unstructured":"Cao, Y., Min, X., Sun, W., Zhai, G.: Attention-guided neural networks for full-reference and no-reference audio-visual quality assessment. TIP 32, 1882\u20131896 (2023)","journal-title":"TIP"},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Gemmeke, J.F., et al.: Audio set: an ontology and human-labeled dataset for audio events. In: ICASSP (2017)","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"17_CR3","doi-asserted-by":"crossref","unstructured":"Hershey, S., et al.: CNN architectures for large-scale audio classification. In: ICASSP (2017)","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"17_CR4","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60, 84\u201390 (2017)","journal-title":"Commun. ACM"},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Lin, Y., Li, Y., Wang, Y.F.: Dual-modality seq2seq network for audio-visual event localization. In: ICASSP (2019)","DOI":"10.1109\/ICASSP.2019.8683226"},{"key":"17_CR6","unstructured":"Lin, Y.B., Tseng, H.Y., Lee, H.Y., Lin, Y.Y., Yang, M.H.: Exploring cross-video and cross-modality signals for weakly-supervised audio-visual video parsing. NIPS (2021)"},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Lin, Y.B., Wang, Y.C.F.: Audiovisual transformer with instance attention for audio-visual event localization. In: ACCV (2020)","DOI":"10.1007\/978-3-030-69544-6_17"},{"key":"17_CR8","unstructured":"Lin, Z., et al.: A structured self-attentive sentence embedding. In: ICLR (2017)"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Liu, S., Quan, W., Liu, Y., Yan, D.: Bi-directional modality fusion network for audio-visual event localization. In: ICASSP (2022)","DOI":"10.1109\/ICASSP43922.2022.9746280"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Liu, S., Quan, W., Wang, C., Liu, Y., Liu, B., Yan, D.M.: Dense modality interaction network for audio-visual event localization. TMM (2022)","DOI":"10.1109\/ICASSP43922.2022.9746280"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Mercea, O.B., Riesch, L., Koepke, A., Akata, Z.: Audio-visual generalised zero-shot learning with cross-modal attention and language. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01030"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Qin, S., Li, Z., Liu, L.: Robust 3D shape classification via non-local graph attention network. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00520"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Ramaswamy, J.: What makes the sound?: A dual-modality interacting network for audio-visual event localization. In: ICASSP (2020)","DOI":"10.1109\/ICASSP40776.2020.9053895"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Ramaswamy, J., Das, S.: See the sound, hear the pixels. In: WACV (2020)","DOI":"10.1109\/WACV45572.2020.9093616"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)","DOI":"10.1109\/ICCV.2015.314"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Stergiou, A., Damen, D.: The wisdom of crowds: temporal progressive attention for early action prediction. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01413"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Tang, Z., Qiu, Z., Hao, Y., Hong, R., Yao, T.: 3D human pose estimation with spatio-temporal criss-cross attention. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00464"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Tian, Y., Shi, J., Li, B., Duan, Z., Xu, C.: Audio-visual event localization in unconstrained videos. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"17_CR19","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS (2017)"},{"key":"17_CR20","unstructured":"Wang, H., Zha, Z., Li, L., Chen, X., Luo, J.: Multi-modulation network for audio-visual event localization. CoRR (2021)"},{"key":"17_CR21","doi-asserted-by":"crossref","unstructured":"Wu, Y., Zhu, L., Yan, Y., Yang, Y.: Dual attention matching for audio-visual event localization. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00639"},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"Xia, Y., Zhao, Z.: Cross-modal background suppression for audio-visual event localization. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01936"},{"key":"17_CR23","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 MM (2020)","DOI":"10.1145\/3394171.3413581"},{"key":"17_CR24","first-page":"7878","volume":"30","author":"H Xuan","year":"2021","unstructured":"Xuan, H., Luo, L., Zhang, Z., Yang, J., Yan, Y.: Discriminative cross-modality attention network for temporal inconsistent audio-visual event localization. TIP 30, 7878\u20137888 (2021)","journal-title":"TIP"},{"key":"17_CR25","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)","DOI":"10.1609\/aaai.v34i01.5361"},{"key":"17_CR26","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: Modeling point clouds with self-attention and gumbel subset sampling. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00344"},{"key":"17_CR27","doi-asserted-by":"crossref","unstructured":"Yu, J., Cheng, Y., Feng, R.: MPN: multimodal parallel network for audio-visual event localization. In: ICME (2021)","DOI":"10.1109\/ICME51207.2021.9428373"},{"key":"17_CR28","doi-asserted-by":"crossref","unstructured":"Zhou, J., Guo, D., Wang, M.: Contrastive positive sample propagation along the audio-visual event line. TPAMI (2023)","DOI":"10.1109\/TPAMI.2022.3223688"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8537-1_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T20:49:09Z","timestamp":1730926149000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8537-1_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,26]]},"ISBN":["9789819985364","9789819985371"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8537-1_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,12,26]]},"assertion":[{"value":"26 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xiamen","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":"13 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/prcv2023.xmu.edu.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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1420","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":"532","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":"37% - 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":"3,78","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":"3,69","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}