{"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":1777568529120,"version":"3.51.4"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732461","type":"print"},{"value":"9783031732478","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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\/978-3-031-73247-8_1","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T12:02:20Z","timestamp":1730376140000},"page":"1-17","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["CoLeaF: A Contrastive-Collaborative Learning Framework for\u00a0Weakly Supervised Audio-Visual Video Parsing"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9134-0427","authenticated-orcid":false,"given":"Faegheh","family":"Sardari","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1779-2775","authenticated-orcid":false,"given":"Armin","family":"Mustafa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7933-5935","authenticated-orcid":false,"given":"Philip J. B.","family":"Jackson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4223-238X","authenticated-orcid":false,"given":"Adrian","family":"Hilton","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo Vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"1_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":"1_CR3","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18827\u201318836 (2023)","DOI":"10.1109\/CVPR52729.2023.01805"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Geng, T., Wang, T., Duan, J., Cong, R., Zheng, F.: Dense-localizing audio-visual events in untrimmed videos: a large-scale benchmark and baseline. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22942\u201322951 (2023)","DOI":"10.1109\/CVPR52729.2023.02197"},{"key":"1_CR5","unstructured":"Gutmann, M., Hyv\u00e4rinen, A.: Noise-contrastive estimation: a new estimation principle for unnormalized statistical models. In: Proceedings of the 13th International Conference on Artificial Intelligence and Statistics, pp. 297\u2013304. JMLR Workshop and Conference Proceedings (2010)"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1_CR7","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. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Jiang, X., et al.: DHHN: dual hierarchical hybrid network for weakly-supervised audio-visual video parsing. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 719\u2013727 (2022)","DOI":"10.1145\/3503161.3548309"},{"key":"1_CR9","unstructured":"Lai, Y.H., Chen, Y.C., Wang, Y.C.F.: Modality-independent teachers meet weakly-supervised audio-visual event parser. In: Advances in Neural Information Processing systems (2023)"},{"key":"1_CR10","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19108\u201319118 (2022)","DOI":"10.1109\/CVPR52688.2022.01852"},{"key":"1_CR11","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. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683226"},{"key":"1_CR12","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: Advance in Neural Information Processing System, vol. 34, pp. 11449\u201311461 (2021)"},{"key":"1_CR13","unstructured":"Mo, S., Tian, Y.: Multi-modal grouping network for weakly-supervised audio-visual video parsing. In: Advance in Neural Information Processing System, vol. 35, pp. 34722\u201334733 (2022)"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Nadeem, A., Hilton, A., Dawes, R., Thomas, G., Mustafa, A.: CAD\u2013contextual multi-modal alignment for dynamic AVQA. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (2023)","DOI":"10.1109\/WACV57701.2024.00709"},{"key":"1_CR15","unstructured":"Radford, A., et\u00a0al.: Quantify classificationl models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763 (2021)"},{"key":"1_CR16","unstructured":"Sensoy, M., Kaplan, L., Kandemir, M.: Evidential deep learning to quantify classification uncertainty. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"1_CR17","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":"1_CR18","doi-asserted-by":"crossref","unstructured":"Tian, Y., Shi, J., Li, B., Duan, Z., Xu, C.: Audio-visual event localization in unconstrained videos. In: European Conference on Computer Vision, pp. 247\u2013263 (2018)","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"1_CR19","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"1_CR20","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Wu, Y., Yang, Y.: Exploring heterogeneous clues for weakly-supervised audio-visual video parsing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1326\u20131335 (2021)","DOI":"10.1109\/CVPR46437.2021.00138"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Wu, Y., Chen, K., Zhang, T., Hui, Y., Berg-Kirkpatrick, T., Dubnov, S.: Large-scale contrastive language-audio pretraining with feature fusion and keyword-to-caption augmentation. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp.\u00a01\u20135 (2023)","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Xia, Y., Zhao, Z.: Cross-modal background suppression for audio-visual event localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19989\u201319998 (2022)","DOI":"10.1109\/CVPR52688.2022.01936"},{"key":"1_CR24","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: Proceedings of the 30th ACM International Conference on Multimedia, pp. 6241\u20136249 (2022)","DOI":"10.1145\/3503161.3547869"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Yun, H., Yu, Y., Yang, W., Lee, K., Kim, G.: Pano-AVQA: grounded audio-visual question answering on 360deg videos. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2031\u20132041 (2021)","DOI":"10.1109\/ICCV48922.2021.00204"},{"key":"1_CR26","unstructured":"Zhou, J., Guo, D., Zhong, Y., Wang, M.: Improving audio-visual video parsing with pseudo visual labels. arXiv preprint arXiv:2303.02344 (2023)"}],"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\/978-3-031-73247-8_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T12:04:59Z","timestamp":1730376299000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73247-8_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9783031732461","9783031732478"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73247-8_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 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"}}]}}