{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:22:47Z","timestamp":1778084567998,"version":"3.51.4"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198359","type":"print"},{"value":"9783031198366","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-19836-6_8","type":"book-chapter","created":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T09:04:58Z","timestamp":1666343098000},"page":"126-143","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":32,"title":["End-to-End Active Speaker Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7546-3531","authenticated-orcid":false,"given":"Juan Le\u00f3n","family":"Alc\u00e1zar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Moritz","family":"Cordes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4993-5416","authenticated-orcid":false,"given":"Chen","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5534-587X","authenticated-orcid":false,"given":"Bernard","family":"Ghanem","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,22]]},"reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Alc\u00e1zar, J.L., et al.: Active speakers in context. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12465\u201312474 (2020)","DOI":"10.1109\/CVPR42600.2020.01248"},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Cai, J., Jiang, N., Han, X., Jia, K., Lu, J.: JOLO-GCN: mining joint-centered light-weight information for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2735\u20132744 (2021)","DOI":"10.1109\/WACV48630.2021.00278"},{"key":"8_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"439","DOI":"10.1007\/978-3-030-86362-3_36","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2021","author":"H Carneiro","year":"2021","unstructured":"Carneiro, H., Weber, C., Wermter, S.: FaVoA: face-voice association favours ambiguous speaker detection. In: Farka\u0161, I., Masulli, P., Otte, S., Wermter, S. (eds.) ICANN 2021. LNCS, vol. 12891, pp. 439\u2013450. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86362-3_36"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Chakravarty, P., Mirzaei, S., Tuytelaars, T., Van hamme, H.: Who\u2019s speaking? Audio-supervised classification of active speakers in video. In: Proceedings of the 2015 ACM on International Conference on Multimodal Interaction, pp. 87\u201390 (2015)","DOI":"10.1145\/2818346.2820780"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Chakravarty, P., Zegers, J., Tuytelaars, T., Van hamme, H.: Active speaker detection with audio-visual co-training. In: Proceedings of the 18th ACM International Conference on Multimodal Interaction, pp. 312\u2013316 (2016)","DOI":"10.1145\/2993148.2993172"},{"issue":"6","key":"8_CR6","doi-asserted-by":"publisher","first-page":"1965","DOI":"10.1109\/TSP.2006.874403","volume":"54","author":"JH Chang","year":"2006","unstructured":"Chang, J.H., Kim, N.S., Mitra, S.K.: Voice activity detection based on multiple statistical models. IEEE Trans. Signal Process. 54(6), 1965\u20131976 (2006)","journal-title":"IEEE Trans. Signal Process."},{"key":"8_CR7","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: Encoder-decoder approaches. arXiv preprint arXiv:1409.1259 (2014)","DOI":"10.3115\/v1\/W14-4012"},{"key":"8_CR9","unstructured":"Chung, J.S.: Naver at ActivityNet challenge 2019-task B active speaker detection (AVA). arXiv preprint arXiv:1906.10555 (2019)"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Nagrani, A., Zisserman, A.: VoxCeleb2: deep speaker recognition. arXiv preprint arXiv:1806.05622 (2018)","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"8_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1007\/978-3-319-54427-4_19","volume-title":"Computer Vision \u2013 ACCV 2016 Workshops","author":"JS Chung","year":"2017","unstructured":"Chung, J.S., Zisserman, A.: Out of time: automated lip sync in the wild. In: Chen, C.-S., Lu, J., Ma, K.-K. (eds.) ACCV 2016. LNCS, vol. 10117, pp. 251\u2013263. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-54427-4_19"},{"key":"8_CR12","unstructured":"Cutler, R., Davis, L.: Look who\u2019s talking: speaker detection using video and audio correlation. In: International Conference on Multimedia and Expo (2000)"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Ding, S., Wang, Q., Chang, S.y., Wan, L., Moreno, I.L.: Personal VAD: speaker-conditioned voice activity detection. arXiv preprint arXiv:1908.04284 (2019)","DOI":"10.21437\/Odyssey.2020-62"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Duhme, M., Memmesheimer, R., Paulus, D.: Fusion-GCN: multimodal action recognition using graph convolutional networks. arXiv preprint arXiv:2109.12946 (2021)","DOI":"10.1007\/978-3-030-92659-5_17"},{"issue":"5","key":"8_CR15","doi-asserted-by":"publisher","first-page":"545","DOI":"10.1016\/j.imavis.2008.04.018","volume":"27","author":"M Everingham","year":"2009","unstructured":"Everingham, M., Sivic, J., Zisserman, A.: Taking the bite out of automated naming of characters in TV video. Image Vis. Comput. 27(5), 545\u2013559 (2009)","journal-title":"Image Vis. Comput."},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Malik, J., Johnson, J.: Mesh R-CNN. arXiv preprint arXiv:1906.02739 (2019)","DOI":"10.1109\/ICCV.2019.00988"},{"key":"8_CR17","unstructured":"Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: CVPR (2006)"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., Satoh, Y.: Can spatiotemporal 3D CNNs retrace the history of 2D CNNs and ImageNet? In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 6546\u20136555 (2018)","DOI":"10.1109\/CVPR.2018.00685"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"8_CR20","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":"8_CR21","doi-asserted-by":"crossref","unstructured":"Jain, A., Zamir, A.R., Savarese, S., Saxena, A.: Structural-RNN: deep learning on spatio-temporal graphs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5308\u20135317 (2016)","DOI":"10.1109\/CVPR.2016.573"},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Johnson, J., Gupta, A., Fei-Fei, L.: Image generation from scene graphs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1219\u20131228 (2018)","DOI":"10.1109\/CVPR.2018.00133"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Kampffmeyer, M., Chen, Y., Liang, X., Wang, H., Zhang, Y., Xing, E.P.: Rethinking knowledge graph propagation for zero-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11487\u201311496 (2019)","DOI":"10.1109\/CVPR.2019.01175"},{"key":"8_CR24","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)"},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"K\u00f6p\u00fckl\u00fc, O., Taseska, M., Rigoll, G.: How to design a three-stage architecture for audio-visual active speaker detection in the wild. arXiv preprint arXiv:2106.03932 (2021)","DOI":"10.1109\/ICCV48922.2021.00123"},{"key":"8_CR26","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, vol. 25, pp. 1097\u20131105 (2012)"},{"key":"8_CR27","unstructured":"LeCun, Y., et al.: Handwritten digit recognition with a back-propagation network. In: Advances in Neural Information Processing Systems 2 (1989)"},{"key":"8_CR28","doi-asserted-by":"crossref","unstructured":"Le\u00f3n-Alc\u00e1zar, J., Heilbron, F.C., Thabet, A., Ghanem, B.: MAAS: multi-modal assignation for active speaker detection. arXiv preprint arXiv:2101.03682 (2021)","DOI":"10.1109\/ICCV48922.2021.00033"},{"key":"8_CR29","doi-asserted-by":"crossref","unstructured":"Li, G., Qian, G., Delgadillo, I.C., M\u00fcller, M., Thabet, A., Ghanem, B.: SGAS: sequential greedy architecture search (2019)","DOI":"10.1109\/CVPR42600.2020.00169"},{"key":"8_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1007\/978-3-030-01246-5_21","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Li","year":"2018","unstructured":"Li, Y., Ouyang, W., Zhou, B., Shi, J., Zhang, C., Wang, X.: Factorizable net: an efficient subgraph-based framework for scene graph generation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 346\u2013363. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_21"},{"key":"8_CR31","doi-asserted-by":"crossref","unstructured":"Nagrani, A., Chung, J.S., Zisserman, A.: VoxCeleb: a large-scale speaker identification dataset. arXiv preprint arXiv:1706.08612 (2017)","DOI":"10.21437\/Interspeech.2017-950"},{"key":"8_CR32","unstructured":"Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., Ng, A.Y.: Multimodal deep learning. In: ICML (2011)"},{"key":"8_CR33","doi-asserted-by":"crossref","unstructured":"Nie, W., Ren, M., Nie, J., Zhao, S.: C-GCN: correlation based graph convolutional network for audio-video emotion recognition. IEEE Trans. Multimedia 23, 3793\u20133804 (2020)","DOI":"10.1109\/TMM.2020.3032037"},{"key":"8_CR34","doi-asserted-by":"crossref","unstructured":"Ren, M., Huang, X., Li, W., Song, D., Nie, W.: LR-GCN: latent relation-aware graph convolutional network for conversational emotion recognition. IEEE Trans. Multimedia (2021)","DOI":"10.1109\/TMM.2021.3117062"},{"key":"8_CR35","doi-asserted-by":"crossref","unstructured":"Roth, J., et al.: AVA active speaker: an audio-visual dataset for active speaker detection. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4492\u20134496. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053900"},{"issue":"6088","key":"8_CR36","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/323533a0","volume":"323","author":"DE Rumelhart","year":"1986","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323(6088), 533\u2013536 (1986)","journal-title":"Nature"},{"key":"8_CR37","doi-asserted-by":"crossref","unstructured":"Saenko, K., Livescu, K., Siracusa, M., Wilson, K., Glass, J., Darrell, T.: Visual speech recognition with loosely synchronized feature streams. In: ICCV (2005)","DOI":"10.1109\/ICCV.2005.251"},{"issue":"4","key":"8_CR38","doi-asserted-by":"publisher","first-page":"478","DOI":"10.1109\/89.848229","volume":"8","author":"SG Tanyer","year":"2000","unstructured":"Tanyer, S.G., Ozer, H.: Voice activity detection in nonstationary noise. IEEE Trans. Speech Audio Process. 8(4), 478\u2013482 (2000)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"8_CR39","doi-asserted-by":"crossref","unstructured":"Tao, F., Busso, C.: Bimodal recurrent neural network for audiovisual voice activity detection. In: INTERSPEECH, pp. 1938\u20131942 (2017)","DOI":"10.21437\/Interspeech.2017-1573"},{"key":"8_CR40","doi-asserted-by":"crossref","unstructured":"Tao, R., Pan, Z., Das, R.K., Qian, X., Shou, M.Z., Li, H.: Is someone speaking? Exploring long-term temporal features for audio-visual active speaker detection. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 3927\u20133935 (2021)","DOI":"10.1145\/3474085.3475587"},{"key":"8_CR41","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"issue":"3","key":"8_CR42","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1109\/29.21701","volume":"37","author":"A Waibel","year":"1989","unstructured":"Waibel, A., Hanazawa, T., Hinton, G., Shikano, K., Lang, K.J.: Phoneme recognition using time-delay neural networks. IEEE Trans. Acoust. Speech Signal Process. 37(3), 328\u2013339 (1989)","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"8_CR43","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"8_CR44","doi-asserted-by":"crossref","unstructured":"Wang, X., Ye, Y., Gupta, A.: Zero-shot recognition via semantic embeddings and knowledge graphs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6857\u20136866 (2018)","DOI":"10.1109\/CVPR.2018.00717"},{"key":"8_CR45","unstructured":"Wu, F., Souza, A., Zhang, T., Fifty, C., Yu, T., Weinberger, K.: Simplifying graph convolutional networks. In: International Conference on Machine Learning, pp. 6861\u20136871. PMLR (2019)"},{"key":"8_CR46","doi-asserted-by":"crossref","unstructured":"Xie, Z., Chen, J., Peng, B.: Point clouds learning with attention-based graph convolution networks. arXiv preprint arXiv:1905.13445 (2019)","DOI":"10.1016\/j.neucom.2020.03.086"},{"key":"8_CR47","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhao, C., Rojas, D.S., Thabet, A., Ghanem, B.: G-TAD: sub-graph localization for temporal action detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10156\u201310165 (2020)","DOI":"10.1109\/CVPR42600.2020.01017"},{"key":"8_CR48","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"8_CR49","unstructured":"Zhang, Y.H., Xiao, J., Yang, S., Shan, S.: Multi-task learning for audio-visual active speaker detection (2019)"},{"key":"8_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: UniCon: unified context network for robust active speaker detection. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 3964\u20133972 (2021)","DOI":"10.1145\/3474085.3475275"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19836-6_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,24]],"date-time":"2022-10-24T23:06:28Z","timestamp":1666652788000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19836-6_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198359","9783031198366"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19836-6_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"22 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}