{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T14:51:53Z","timestamp":1784904713825,"version":"3.55.0"},"publisher-location":"Cham","reference-count":61,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012151","type":"print"},{"value":"9783030012168","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-01216-8_16","type":"book-chapter","created":{"date-parts":[[2018,10,8]],"date-time":"2018-10-08T15:10:26Z","timestamp":1539011426000},"page":"252-268","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":377,"title":["Audio-Visual Event Localization in Unconstrained Videos"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1423-4513","authenticated-orcid":false,"given":"Yapeng","family":"Tian","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4509-0535","authenticated-orcid":false,"given":"Jing","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8304-6973","authenticated-orcid":false,"given":"Bochen","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8334-9974","authenticated-orcid":false,"given":"Zhiyao","family":"Duan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2183-822X","authenticated-orcid":false,"given":"Chenliang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,10,9]]},"reference":[{"key":"16_CR1","unstructured":"Andrew, G., Arora, R., Bilmes, J., Livescu, K.: Deep canonical correlation analysis. In: Proceedings of ICML, pp. 1247\u20131255. PMLR (2013)"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Zisserman, A.: Look, listen and learn. In: Proceedings of ICCV. IEEE (2017)","DOI":"10.1109\/ICCV.2017.73"},{"key":"16_CR3","volume-title":"Computer Vision \u2013 ECCV 2018","author":"R Arandjelovi\u0107","year":"2018","unstructured":"Arandjelovi\u0107, R., Zisserman, A.: Objects that sound. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. Springer, Heidelberg (2018)"},{"key":"16_CR4","unstructured":"Arevalo, J., Solorio, T., Montes-y G\u00f3mez, M., Gonz\u00e1lez, F.A.: Gated multimodal units for information fusion. In: Proceedings of ICLR Workshop (2017)"},{"key":"16_CR5","unstructured":"Assael, Y.M., Shillingford, B., Whiteson, S., de Freitas, N.: LipNet: sentence-level lipreading. CoRR abs\/1611.01599 (2016)"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Aytar, Y., Vondrick, C., Torralba, A.: SoundNet: learning sound representations from unlabeled video. In: Proceedings of NIPS. Curran Associates, Inc. (2016)","DOI":"10.1109\/CVPR.2016.18"},{"key":"16_CR7","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: Proceedings of ICLR (2015)"},{"key":"16_CR8","unstructured":"Baltru\u0161aitis, T., Ahuja, C., Morency, L.P.: Multimodal machine learning: a survey and taxonomy. IEEE TPAMI (2018)"},{"issue":"4","key":"16_CR9","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":"16_CR10","doi-asserted-by":"crossref","unstructured":"Cakir, E., Heittola, T., Huttunen, H., Virtanen, T.: Polyphonic sound event detection using multi label deep neural networks. In: Proceedings of IJCNN. IEEE (2015)","DOI":"10.1109\/IJCNN.2015.7280624"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Chen, L., Srivastava, S., Duan, Z., Xu, C.: Deep cross-modal audio-visual generation. In: Proceedings of ACMMM Workshop. ACM (2017)","DOI":"10.1145\/3126686.3126723"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Senior, A., Vinyals, O., Zisserman, A.: Lip reading sentences in the wild. In: Proceedings of CVPR. IEEE (2017)","DOI":"10.1109\/CVPR.2017.367"},{"key":"16_CR13","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":"16_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1007\/978-3-319-46487-9_47","volume-title":"Computer Vision \u2013 ECCV 2016","author":"V Escorcia","year":"2016","unstructured":"Escorcia, V., Caba Heilbron, F., Niebles, J.C., Ghanem, B.: DAPs: deep action proposals for action understanding. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 768\u2013784. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_47"},{"key":"16_CR15","unstructured":"Fisher III., J.W., Darrell, T., Freeman, W.T., Viola, P.A.: Learning joint statistical models for audio-visual fusion and segregation. In: Proceedings of NIPS. Curran Associates, Inc. (2001)"},{"key":"16_CR16","volume-title":"Computer Vision \u2013 ECCV 2018","author":"R Gao","year":"2018","unstructured":"Gao, R., Feris, R., Grauman, K.: Learning to separate object sounds by watching unlabeled video. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. Springer, Heidelberg (2018)"},{"issue":"1","key":"16_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1207\/s15326969eco0501_1","volume":"5","author":"WW Gaver","year":"1993","unstructured":"Gaver, W.W.: What in the world do we hear?: An ecological approach to auditory event perception. Ecol. Psychol. 5(1), 1\u201329 (1993)","journal-title":"Ecol. Psychol."},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Gemmeke, J.F., et al.: Audio set: an ontology and human-labeled dataset for audio events. In: Proceedings of ICASSP. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952261"},{"issue":"Jul","key":"16_CR19","first-page":"2211","volume":"12","author":"M G\u00f6nen","year":"2011","unstructured":"G\u00f6nen, M., Alpayd\u0131n, E.: Multiple kernel learning algorithms. JMLR 12(Jul), 2211\u20132268 (2011)","journal-title":"JMLR"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Gurban, M., Thiran, J.P., Drugman, T., Dutoit, T.: Dynamic modality weighting for multi-stream HMMs in audio-visual speech recognition. In: Proceedings of ICMI. ACM (2008)","DOI":"10.1145\/1452392.1452442"},{"key":"16_CR21","unstructured":"Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: Proceedings of CVPR. IEEE (2006)"},{"key":"16_CR22","unstructured":"Harwath, D., Torralba, A., Glass, J.: Unsupervised learning of spoken language with visual context. In: Proceedings of NIPS. Curran Associates, Inc. (2016)"},{"issue":"1","key":"16_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1687-4722-2013-1","volume":"2013","author":"T Heittola","year":"2013","unstructured":"Heittola, T., Mesaros, A., Eronen, A., Virtanen, T.: Context-dependent sound event detection. EURASIP J. Audio Speech Music Process. 2013(1), 1 (2013)","journal-title":"EURASIP J. Audio Speech Music Process."},{"key":"16_CR24","unstructured":"Hershey, J.R., Movellan, J.R.: Audio vision: Using audio-visual synchrony to locate sounds. In: Proceedings of NIPS. Curran Associates, Inc. (2000)"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Hershey, S., et al.: CNN architectures for large-scale audio classification. In: Proceedings of ICASSP. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952132"},{"issue":"8","key":"16_CR26","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Hu, D., Li, X., et al.: Temporal multimodal learning in audiovisual speech recognition. In: Proceedings of CVPR. IEEE (2016)","DOI":"10.1109\/CVPR.2016.389"},{"key":"16_CR28","doi-asserted-by":"crossref","unstructured":"Kiela, D., Grave, E., Joulin, A., Mikolov, T.: Efficient large-scale multi-modal classification. In: Proceedings of AAAI. AAAI Press (2018)","DOI":"10.1609\/aaai.v32i1.11945"},{"key":"16_CR29","unstructured":"Kim, J.H., et al.: Multimodal residual learning for visual QA. In: Proceedings of NIPS. Curran Associates, Inc. (2016)"},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Lea, C., et al.: Temporal convolutional networks for action segmentation and detection. In: Proceedings of CVPR. IEEE (2017)","DOI":"10.1109\/CVPR.2017.113"},{"issue":"11","key":"16_CR31","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"16_CR32","unstructured":"Li, B., Xu, C., Duan, Z.: Audio-visual source association for string ensembles through multi-modal vibrato analysis. In: Proceedings of SMC (2017)"},{"key":"16_CR33","unstructured":"Lin, M., Chen, Q., Yan, S.: Network in network. arXiv preprint arXiv:1312.4400 (2013)"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Lu, J., Xiong, C., Parikh, D., Socher, R.: Knowing when to look: adaptive attention via a visual sentinel for image captioning. In: Proceedings of CVPR. IEEE (2017)","DOI":"10.1109\/CVPR.2017.345"},{"key":"16_CR35","unstructured":"Maron, O., Lozano-P\u00e9rez, T.: A framework for multiple-instance learning. In: Proceedings of NIPS. Curran Associates, Inc. (1998)"},{"key":"16_CR36","doi-asserted-by":"crossref","unstructured":"Mesaros, A., Heittola, T., Virtanen, T.: TUT database for acoustic scene classification and sound event detection. In: Proceedings of EUSIPCO. IEEE (2016)","DOI":"10.1109\/EUSIPCO.2016.7760424"},{"key":"16_CR37","doi-asserted-by":"crossref","unstructured":"Mroueh, Y., Marcheret, E., Goel, V.: Deep multimodal learning for audio-visual speech recognition. In: Proceedings of ICASSP. IEEE (2015)","DOI":"10.1109\/ICASSP.2015.7178347"},{"key":"16_CR38","unstructured":"Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., Ng, A.Y.: Multimodal deep learning. In: Proceedings of ICML. PMLR (2011)"},{"key":"16_CR39","doi-asserted-by":"crossref","unstructured":"Oneata, D., Verbeek, J., Schmid, C.: Action and event recognition with fisher vectors on a compact feature set. In: Proceedings of ICCV. IEEE (2013)","DOI":"10.1109\/ICCV.2013.228"},{"key":"16_CR40","volume-title":"Computer Vision \u2013 ECCV 2018","author":"A Owens","year":"2018","unstructured":"Owens, A., Efros, A.A.: Audio-visual scene analysis with self-supervised multisensory features. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. Springer, Heidelberg (2018)"},{"key":"16_CR41","doi-asserted-by":"crossref","unstructured":"Owens, A., Isola, P., McDermott, J., Torralba, A., Adelson, E.H., Freeman, W.T.: Visually indicated sounds. In: Proceedings of CVPR. IEEE (2016)","DOI":"10.1109\/CVPR.2016.264"},{"key":"16_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1007\/978-3-319-46448-0_48","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Owens","year":"2016","unstructured":"Owens, A., Wu, J., McDermott, J.H., Freeman, W.T., Torralba, A.: Ambient sound provides supervision for visual learning. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 801\u2013816. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_48"},{"key":"16_CR43","doi-asserted-by":"crossref","unstructured":"Parascandolo, G., Huttunen, H., Virtanen, T.: Recurrent neural networks for polyphonic sound event detection in real life recordings. In: Proceedings of ICASSP. IEEE (2016)","DOI":"10.1109\/ICASSP.2016.7472917"},{"key":"16_CR44","doi-asserted-by":"crossref","unstructured":"Poria, S., Cambria, E., Gelbukh, A.: Deep convolutional neural network textual features and multiple kernel learning for utterance-level multimodal sentiment analysis. In: Proceedings of EMNLP. Association for Computational Linguistics (2015)","DOI":"10.18653\/v1\/D15-1303"},{"issue":"3","key":"16_CR45","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. IJCV 115(3), 211\u2013252 (2015)","journal-title":"IJCV"},{"issue":"11","key":"16_CR46","first-page":"2673","volume":"45","author":"M Schuster","year":"1997","unstructured":"Schuster, M., Paliwal, K.K.: Bidirectional recurrent neural networks. IEEE TSP 45(11), 2673\u20132681 (1997)","journal-title":"IEEE TSP"},{"key":"16_CR47","doi-asserted-by":"crossref","unstructured":"Senocak, A., Oh, T.H., Kim, J., Yang, M.H., Kweon, I.S.: Learning to localize sound source in visual scenes. In: Proceedings of CVPR. IEEE (2018)","DOI":"10.1109\/CVPR.2018.00458"},{"key":"16_CR48","doi-asserted-by":"crossref","unstructured":"Shou, Z., Wang, D., Chang, S.F.: Temporal action localization in untrimmed videos via multi-stage CNNs. In: Proceedings of CVPR. IEEE (2016)","DOI":"10.1109\/CVPR.2016.119"},{"key":"16_CR49","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Proceedings of ICLR (2015)"},{"key":"16_CR50","unstructured":"Srivastava, N., Salakhutdinov, R.: Learning representations for multimodal data with deep belief nets. In: Proceedings of ICML Workshop. PMLR (2012)"},{"key":"16_CR51","unstructured":"Srivastava, N., Salakhutdinov, R.R.: Multimodal learning with deep Boltzmann machines. In: Proceedings of NIPS. Curran Associates, Inc. (2012)"},{"key":"16_CR52","doi-asserted-by":"crossref","unstructured":"Sur\u00eds, D., Duarte, A., Salvador, A., Torres, J., Gir\u00f3-i Nieto, X.: Cross-modal embeddings for video and audio retrieval. arXiv preprint arXiv:1801.02200 (2018)","DOI":"10.1007\/978-3-030-11018-5_62"},{"key":"16_CR53","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: Proceedings of CVPR. IEEE (2016)","DOI":"10.1109\/CVPR.2016.501"},{"key":"16_CR54","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: Proceedings of ICCV. IEEE (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"16_CR55","doi-asserted-by":"crossref","unstructured":"Wu, J., Yu, Y., Huang, C., Yu, K.: Deep multiple instance learning for image classification and auto-annotation. In: Proceedings of CVPR. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7298968"},{"key":"16_CR56","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: Proceedings of CVPR. IEEE (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"16_CR57","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: Proceedings of ICLR (2015)"},{"key":"16_CR58","doi-asserted-by":"crossref","unstructured":"Yang, X., Ramesh, P., Chitta, R., Madhvanath, S., Bernal, E.A., Luo, J.: Deep multimodal representation learning from temporal data. In: Proceedings of CVPR. IEEE (2017)","DOI":"10.1109\/CVPR.2017.538"},{"key":"16_CR59","volume-title":"Computer Vision \u2013 ECCV 2018","author":"H Zhao","year":"2018","unstructured":"Zhao, H., Gan, C., Rouditchenko, A., Vondrick, C., McDermott, J., Torralba, A.: The sound of pixels. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. Springer, Heidelberg (2018)"},{"key":"16_CR60","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Xiong, Y., Wang, L., Wu, Z., Tang, X., Lin, D.: Temporal action detection with structured segment networks. In: Proceedings of ICCV. IEEE (2017)","DOI":"10.1109\/ICCV.2017.317"},{"key":"16_CR61","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Wang, Z., Fang, C., Bui, T., Berg, T.L.: Visual to sound: generating natural sound for videos in the wild. In: CVPR. IEEE (2018)","DOI":"10.1109\/CVPR.2018.00374"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01216-8_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,5]],"date-time":"2023-09-05T19:25:31Z","timestamp":1693941931000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01216-8_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012151","9783030012168"],"references-count":61,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01216-8_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"9 October 2018","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":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}