{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:03:27Z","timestamp":1776888207056,"version":"3.51.2"},"publisher-location":"Singapore","reference-count":45,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819658145","type":"print"},{"value":"9789819658152","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-981-96-5815-2_7","type":"book-chapter","created":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T18:43:38Z","timestamp":1745606618000},"page":"107-124","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Reinforced Label Denoising for\u00a0Weakly-Supervised Audio-Visual Video Parsing"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1005-8965","authenticated-orcid":false,"given":"Yongbiao","family":"Gao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2167-3719","authenticated-orcid":false,"given":"Xiangcheng","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3550-8026","authenticated-orcid":false,"given":"Guohua","family":"Lv","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2343-3688","authenticated-orcid":false,"given":"Deng","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1401-9859","authenticated-orcid":false,"given":"Sijiu","family":"Niu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,26]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Zisserman, A.: Look, listen and learn. In: IEEE International Conference on Computer Vision, pp. 609\u2013617 (2017)","DOI":"10.1109\/ICCV.2017.73"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Aytar, Y., Vondrick, C., Torralba, A.: SoundNet: learning sound representations from unlabeled video. In: Neural Information Processing Systems, pp. 892\u2013900 (2016)","DOI":"10.1109\/CVPR.2016.18"},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Bayoudh, K., Knani, R., Hamdaoui, F., Mtibaa, A.: A survey on deep multimodal learning for computer vision: advances, trends, applications, and datasets. Vis. Comput., 1\u201332 (2021)","DOI":"10.1007\/s00371-021-02166-7"},{"issue":"4","key":"7_CR4","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1016\/j.conb.2006.06.008","volume":"16","author":"DA Bulkin","year":"2006","unstructured":"Bulkin, D.A., Groh, J.M.: Seeing sounds: visual and auditory interactions in the brain. Curr. Opin. Neurobiol. 16(4), 415\u2013419 (2006)","journal-title":"Curr. Opin. Neurobiol."},{"key":"7_CR5","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: IEEE International Conference on Acoustics, Speech and Signal Processing, pp.\u00a01\u20135 (2023)","DOI":"10.1109\/ICASSP49357.2023.10097072"},{"key":"7_CR6","doi-asserted-by":"crossref","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: European Conference on Computer Vision, pp. 431\u2013448. Springer (2022)","DOI":"10.1007\/978-3-031-19830-4_25"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Wang, R., Pan, Z., Feng, R., Zhang, Y.: Look, listen, and attend: co-attention network for self-supervised audio-visual representation learning. In: ACM International Conference on Multimedia, pp. 3884\u20133892 (2020)","DOI":"10.1145\/3394171.3413869"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Ephrat, A., et al.: Looking to listen at the cocktail party: a speaker-independent audio-visual model for speech separation. arXiv preprint arXiv:1804.03619 (2018)","DOI":"10.1145\/3197517.3201357"},{"key":"7_CR9","unstructured":"Fan, Y., Wu, Y., Lin, Y., Du, B.: Revisit weakly-supervised audio-visual video parsing from the language perspective. In: Neural Information Processing Systems (2023)"},{"key":"7_CR10","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: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18827\u201318836 (2023)","DOI":"10.1109\/CVPR52729.2023.01805"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Gao, R., Grauman, K.: Visualvoice: audio-visual speech separation with cross-modal consistency. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15490\u201315500 (2021)","DOI":"10.1109\/CVPR46437.2021.01524"},{"key":"7_CR12","unstructured":"Gao, Y., Wang, K., Geng, X.: Sequential label enhancement. IEEE Trans. Neural Netw. Learn. Syst., 1\u201312 (2022)"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Hershey, S., et\u00a0al.: CNN architectures for large-scale audio classification. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 131\u2013135 (2017)","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Hu, A., Cotter, F., Mohan, N., Gurau, C., Kendall, A.: Probabilistic future prediction for video scene understanding. In: European Conference on Computer Vision, pp. 767\u2013785 (2020)","DOI":"10.1007\/978-3-030-58517-4_45"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Hu, D., Nie, F., Li, X.: Deep multimodal clustering for unsupervised audiovisual learning. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9248\u20139257 (2019)","DOI":"10.1109\/CVPR.2019.00947"},{"issue":"11","key":"7_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1167\/19.11.1","volume":"19","author":"RA Jacobs","year":"2019","unstructured":"Jacobs, R.A., Xu, C.: Can multisensory training aid visual learning? A computational investigation. J. Vis. 19(11), 1\u20131 (2019)","journal-title":"J. Vis."},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Jiang, X., et al.: DHHN: dual hierarchical hybrid network for weakly-supervised audio-visual video parsing. In: ACM International Conference on Multimedia, pp. 719\u2013727 (2022)","DOI":"10.1145\/3503161.3548309"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Lee, S., et al.: ACAV100M: automatic curation of large-scale datasets for audio-visual video representation learning. In: IEEE\/CVF International Conference on Computer Vision, pp. 10274\u201310284 (2021)","DOI":"10.1109\/ICCV48922.2021.01011"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Lin, K., et al.: SwinBERT: end-to-end transformers with sparse attention for video captioning. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17949\u201317958 (2022)","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"7_CR21","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: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 2002\u20132006 (2019)","DOI":"10.1109\/ICASSP.2019.8683226"},{"key":"7_CR22","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: Neural Information Processing Systems, pp. 11449\u201311461 (2021)"},{"key":"7_CR23","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11704-018-8015-y","volume":"13","author":"M Ling","year":"2019","unstructured":"Ling, M., Geng, X.: Soft video parsing by label distribution learning. Front. Comp. Sci. 13, 302\u2013317 (2019)","journal-title":"Front. Comp. Sci."},{"key":"7_CR24","doi-asserted-by":"crossref","unstructured":"Miao, J., Wei, Y., Wu, Y., Liang, C., Li, G., Yang, Y.: VSPW: a large-scale dataset for video scene parsing in the wild. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4133\u20134143 (2021)","DOI":"10.1109\/CVPR46437.2021.00412"},{"key":"7_CR25","unstructured":"Mo, S., Tian, Y.: Multi-modal grouping network for weakly-supervised audio-visual video parsing. In: Neural Information Processing Systems, pp. 34722\u201334733 (2022)"},{"issue":"1","key":"7_CR26","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1111\/bjet.13280","volume":"54","author":"A Nguyen","year":"2023","unstructured":"Nguyen, A., J\u00e4rvel\u00e4, S., Ros\u00e9, C., J\u00e4rvenoja, H., Malmberg, J.: Examining socially shared regulation and shared physiological arousal events with multimodal learning analytics. Br. J. Edu. Technol. 54(1), 293\u2013312 (2023)","journal-title":"Br. J. Edu. Technol."},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Rachavarapu, K.K., et\u00a0al.: Boosting positive segments for weakly-supervised audio-visual video parsing. In: IEEE\/CVF International Conference on Computer Vision, pp. 10192\u201310202 (2023)","DOI":"10.1109\/ICCV51070.2023.00935"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Rahman, T., Xu, B., Sigal, L.: Watch, listen and tell: multi-modal weakly supervised dense event captioning. In: IEEE\/CVF International Conference on Computer Vision, pp. 8908\u20138917 (2019)","DOI":"10.1109\/ICCV.2019.00900"},{"issue":"6","key":"7_CR29","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1109\/MSP.2017.2738401","volume":"34","author":"D Ramachandram","year":"2017","unstructured":"Ramachandram, D., Taylor, G.W.: Deep multimodal learning: a survey on recent advances and trends. IEEE Signal Process. Mag. 34(6), 96\u2013108 (2017)","journal-title":"IEEE Signal Process. Mag."},{"issue":"5","key":"7_CR30","doi-asserted-by":"publisher","first-page":"1054","DOI":"10.1109\/TNN.1998.712192","volume":"9","author":"R Sutton","year":"1998","unstructured":"Sutton, R., Barto, A.: Reinforcement learning: an introduction. IEEE Trans. Neural Netw. 9(5), 1054\u20131054 (1998)","journal-title":"IEEE Trans. Neural Netw."},{"key":"7_CR31","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":"7_CR32","doi-asserted-by":"crossref","unstructured":"Tosi, F., Aleotti, F., Ramirez, P.Z., Poggi, M., Salti, S., Stefano, L.D., Mattoccia, S.: Distilled semantics for comprehensive scene understanding from videos. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4654\u20134665 (2020)","DOI":"10.1109\/CVPR42600.2020.00471"},{"key":"7_CR33","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: IEEE Conference on Computer Vision and Pattern Recognition, pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"issue":"7","key":"7_CR34","doi-asserted-by":"publisher","first-page":"1381","DOI":"10.1109\/TASL.2013.2250961","volume":"21","author":"Y Wang","year":"2013","unstructured":"Wang, Y., Wang, D.: Towards scaling up classification-based speech separation. IEEE Trans. Audio Speech Lang. Process. 21(7), 1381\u20131390 (2013)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"7_CR35","doi-asserted-by":"crossref","unstructured":"Wei, H., Feng, L., Chen, X., An, B.: Combating noisy labels by agreement: a joint training method with co-regularization. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13726\u201313735 (2020)","DOI":"10.1109\/CVPR42600.2020.01374"},{"key":"7_CR36","doi-asserted-by":"crossref","unstructured":"Williams, Ronald, J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 3-4(8), 229\u2013256 (1992)","DOI":"10.1007\/BF00992696"},{"key":"7_CR37","doi-asserted-by":"crossref","unstructured":"Wu, Y., Yang, Y.: Exploring heterogeneous clues for weakly-supervised audio-visual video parsing. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1326\u20131335 (2021)","DOI":"10.1109\/CVPR46437.2021.00138"},{"key":"7_CR38","doi-asserted-by":"publisher","first-page":"12113","DOI":"10.1109\/TPAMI.2023.3275156","volume":"45","author":"P Xu","year":"2023","unstructured":"Xu, P., Zhu, X., Clifton, D.A.: Multimodal learning with transformers: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 45, 12113\u201312132 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR39","doi-asserted-by":"crossref","unstructured":"Yang, A., et al.: Vid2Seq: large-scale pretraining of a visual language model for dense video captioning. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10714\u201310726 (2023)","DOI":"10.1109\/CVPR52729.2023.01032"},{"key":"7_CR40","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 International Conference on Multimedia, pp. 6241\u20136249 (2022)","DOI":"10.1145\/3503161.3547869"},{"key":"7_CR41","unstructured":"Yu, X., Han, B., Yao, J., Niu, G., Tsang, I., Sugiyama, M.: How does disagreement help generalization against label corruption? In: International Conference on Machine Learning, pp. 7164\u20137173 (2019)"},{"key":"7_CR42","unstructured":"Yung-Hsuan, L., Yen-Chun, C., Yu-Chiang, F.W.: Modality-independent teachers meet weakly-supervised audio-visual event parser. In: Neural Information Processing Systems, pp. 1\u201319 (2023)"},{"issue":"6","key":"7_CR43","doi-asserted-by":"publisher","first-page":"7239","DOI":"10.1109\/TPAMI.2022.3223688","volume":"45","author":"J Zhou","year":"2023","unstructured":"Zhou, J., Guo, D., Wang, M.: Contrastive positive sample propagation along the audio-visual event line. IEEE Trans. Pattern Anal. Mach. Intell. 45(6), 7239\u20137257 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR44","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":"7_CR45","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. Int. J. Comput. Vis. (2024). Early Access","DOI":"10.1007\/s11263-024-02142-3"}],"container-title":["Lecture Notes in Computer Science","Computational Visual Media"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-5815-2_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T18:44:04Z","timestamp":1745606644000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-5815-2_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819658145","9789819658152"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-5815-2_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"26 April 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CVM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Visual Media","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hong Kong SAR","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 April 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 April 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cvm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iccvm.org\/2025\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}