{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:02:09Z","timestamp":1777568529851,"version":"3.51.4"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726835","type":"print"},{"value":"9783031726842","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72684-2_3","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T19:02:45Z","timestamp":1730574165000},"page":"35-51","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Label-Anticipated Event Disentanglement for\u00a0Audio-Visual Video Parsing"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6402-7593","authenticated-orcid":false,"given":"Jinxing","family":"Zhou","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2594-254X","authenticated-orcid":false,"given":"Dan","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Yuxin","family":"Mao","sequence":"additional","affiliation":[]},{"given":"Yiran","family":"Zhong","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7778-8807","authenticated-orcid":false,"given":"Xiaojun","family":"Chang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3094-7735","authenticated-orcid":false,"given":"Meng","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Chen, H., Zhu, D., Zhang, G., Shi, W., Zhang, X., Li, J.: CM-CS: cross-modal common-specific feature learning for audio-visual video parsing. In: ICASSP, pp.\u00a01\u20135 (2023)","DOI":"10.1109\/ICASSP49357.2023.10097072"},{"key":"3_CR2","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1007\/978-3-031-19830-4_25","volume-title":"ECCV 2022","author":"H Cheng","year":"2022","unstructured":"Cheng, H., Liu, Z., Zhou, H., Qian, C., Wu, W., Wang, L.: Joint-modal label denoising for weakly-supervised audio-visual video parsing. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13694, pp. 431\u2013448. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19830-4_25"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"3_CR4","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805, pp. 1\u201316 (2018)"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Gao, J., Chen, M., Xu, C.: Collecting cross-modal presence-absence evidence for weakly-supervised audio-visual event perception. In: CVPR, pp. 18827\u201318836 (2023)","DOI":"10.1109\/CVPR52729.2023.01805"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Gemmeke, J.F., et al.: Audio set: an ontology and human-labeled dataset for audio events. In: ICASSP, pp. 776\u2013780 (2017)","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Guo, D., Li, K., Hu, B., Zhang, Y., Wang, M.: Benchmarking micro-action recognition: dataset, methods, and applications. IEEE TCSVT 6238\u20136252 (2024)","DOI":"10.1109\/TCSVT.2024.3358415"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Hershey, S., et\u00a0al.: CNN architectures for large-scale audio classification. In: ICASSP, pp. 131\u2013135 (2017)","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Hu, D., Nie, F., Li, X.: Deep multimodal clustering for unsupervised audiovisual learning. In: CVPR, pp. 9248\u20139257 (2019)","DOI":"10.1109\/CVPR.2019.00947"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Jiang, X., et al.: DHHN: dual hierarchical hybrid network for weakly-supervised audio-visual video parsing. In: ACM MM, pp. 719\u2013727 (2022)","DOI":"10.1145\/3503161.3548309"},{"key":"3_CR12","unstructured":"Kay, W., et\u00a0al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950, pp. 1\u201322 (2017)"},{"key":"3_CR13","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR, pp. 1\u201315 (2014)"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Li, G., Wei, Y., Tian, Y., Xu, C., Wen, J.R., Hu, D.: Learning to answer questions in dynamic audio-visual scenarios. In: CVPR, pp. 19108\u201319118 (2022)","DOI":"10.1109\/CVPR52688.2022.01852"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Li, Z., Guo, D., Zhou, J., Zhang, J., Wang, M.: Object-aware adaptive-positivity learning for audio-visual question answering. In: AAAI, pp. 3306\u20133314 (2024)","DOI":"10.1609\/aaai.v38i4.28116"},{"key":"3_CR16","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. In: NeurIPS, pp. 1\u201313 (2021)"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Mao, Y., Zhang, J., Xiang, M., Zhong, Y., Dai, Y.: Multimodal variational auto-encoder based audio-visual segmentation. In: ICCV, pp. 954\u2013965 (2023)","DOI":"10.1109\/ICCV51070.2023.00094"},{"key":"3_CR18","unstructured":"Mo, S., Tian, Y.: Multi-modal grouping network for weakly-supervised audio-visual video parsing. In: NeurIPS, pp. 1\u201312 (2022)"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: EMNLP, pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Rachavarapu, K.: Boosting positive segments for weakly-supervised audio-visual video parsing. In: ICCV, pp. 10192\u201310202 (2023)","DOI":"10.1109\/ICCV51070.2023.00935"},{"key":"3_CR21","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763 (2021)"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Shen, X., et\u00a0al.: Fine-grained audible video description. In: CVPR, pp. 10585\u201310596 (2023)","DOI":"10.1109\/CVPR52729.2023.01020"},{"key":"3_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1007\/978-3-030-58580-8_26","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Tian","year":"2020","unstructured":"Tian, Y., Li, D., Xu, C.: Unified multisensory perception: weakly-supervised audio-visual video\u00a0parsing. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 436\u2013454. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_26"},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Tian, Y., Shi, J., Li, B., Duan, Z., Xu, C.: Audio-visual event localization in unconstrained videos. In: ECCV, pp. 247\u2013263 (2018)","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: CVPR, pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"3_CR26","unstructured":"Wei, Y., Hu, D., Tian, Y., Li, X.: Learning in audio-visual context: a review, analysis, and new perspective. arXiv preprint arXiv:2208.09579 (2022)"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Wu, Y., Yang, Y.: Exploring heterogeneous clues for weakly-supervised audio-visual video parsing. In: CVPR, pp. 1326\u20131335 (2021)","DOI":"10.1109\/CVPR46437.2021.00138"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Wu, Y., Zhu, L., Yan, Y., Yang, Y.: Dual attention matching for audio-visual event localization. In: ICCV, pp. 6292\u20136300 (2019)","DOI":"10.1109\/ICCV.2019.00639"},{"key":"3_CR29","doi-asserted-by":"crossref","unstructured":"Xia, Y., Zhao, Z.: Cross-modal background suppression for audio-visual event localization. In: CVPR, pp. 19989\u201319998 (2022)","DOI":"10.1109\/CVPR52688.2022.01936"},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Yu, J., Cheng, Y., Zhao, R.W., Feng, R., Zhang, Y.: MM-Pyramid: multimodal pyramid attentional network for audio-visual event localization and video parsing. In: ACM MM, pp. 6241\u20136249 (2022)","DOI":"10.1145\/3503161.3547869"},{"key":"3_CR31","unstructured":"Lai, Y.-H., Chen, Y.-C., Wang, F.: Modality-independent teachers meet weakly-supervised audio-visual event parser. In: NeurIPS, pp. 1\u201319 (2023)"},{"key":"3_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, J., Li, W.: Multi-modal and multi-scale temporal fusion architecture search for audio-visual video parsing. In: ACM MM, pp. 3328\u20133336 (2023)","DOI":"10.1145\/3581783.3611947"},{"key":"3_CR33","doi-asserted-by":"crossref","unstructured":"Zhou, J., Guo, D., Wang, M.: Contrastive positive sample propagation along the audio-visual event line. TPAMI 7239\u20137257 (2023)","DOI":"10.1109\/TPAMI.2022.3223688"},{"key":"3_CR34","unstructured":"Zhou, J., Guo, D., Zhong, Y., Wang, M.: Improving audio-visual video parsing with pseudo visual labels. arXiv preprint arXiv:2303.02344 (2023)"},{"key":"3_CR35","doi-asserted-by":"crossref","unstructured":"Zhou, J., Guo, D., Zhong, Y., Wang, M.: Advancing weakly-supervised audio-visual video parsing via segment-wise pseudo labeling. IJCV 1\u201322 (2024)","DOI":"10.1007\/s11263-024-02142-3"},{"key":"3_CR36","unstructured":"Zhou, J., et\u00a0al.: Audio-visual segmentation with semantics. arXiv preprint arXiv:2301.13190 (2023)"},{"key":"3_CR37","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1007\/978-3-031-19836-6_22","volume-title":"ECCV 2022","author":"J Zhou","year":"2022","unstructured":"Zhou, J., et al.: Audio\u2013visual segmentation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13697, pp. 386\u2013403. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19836-6_22"},{"key":"3_CR38","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, pp. 8436\u20138444 (2021)","DOI":"10.1109\/CVPR46437.2021.00833"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72684-2_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T19:03:14Z","timestamp":1730574194000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72684-2_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9783031726835","9783031726842"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72684-2_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}