{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T14:05:11Z","timestamp":1756994711930,"version":"3.40.3"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030585648"},{"type":"electronic","value":"9783030585655"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58565-5_25","type":"book-chapter","created":{"date-parts":[[2020,11,11]],"date-time":"2020-11-11T12:03:19Z","timestamp":1605096199000},"page":"413-429","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Learning to Predict Salient Faces: A Novel Visual-Audio Saliency Model"],"prefix":"10.1007","author":[{"given":"Yufan","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minglang","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mai","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bing","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiming","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ali","family":"Borji","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,11,12]]},"reference":[{"issue":"7","key":"25_CR1","doi-asserted-by":"publisher","first-page":"1688","DOI":"10.1109\/TMM.2017.2777665","volume":"20","author":"C Bak","year":"2017","unstructured":"Bak, C., Kocak, A., Erdem, E., Erdem, A.: Spatio-temporal saliency networks for dynamic saliency prediction. IEEE Trans. Multimedia 20(7), 1688\u20131698 (2017)","journal-title":"IEEE Trans. Multimedia"},{"key":"25_CR2","unstructured":"Borji, A.: Saliency prediction in the deep learning era: an empirical investigation. arXiv preprint arXiv:1810.03716 (2018)"},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Bylinskii, Z., Judd, T., Oliva, A., Torralba, A., Durand, F.: What do different evaluation metrics tell us about saliency models? IEEE Trans. Pattern Anal. Mach. Intell. (2018)","DOI":"10.1109\/TPAMI.2018.2815601"},{"issue":"10","key":"25_CR4","doi-asserted-by":"publisher","first-page":"5142","DOI":"10.1109\/TIP.2018.2851672","volume":"27","author":"M Cornia","year":"2018","unstructured":"Cornia, M., Baraldi, L., Serra, G., Cucchiara, R.: Predicting human eye fixations via an LSTM-based saliency attentive model. IEEE Trans. Image Process. 27(10), 5142\u20135154 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Coutrot, A., Guyader, N.: Toward the introduction of auditory information in dynamic visual attention models. In: International Workshop on Image Analysis for Multimedia Interactive Services, pp. 1\u20134. IEEE (2013)","DOI":"10.1109\/WIAMIS.2013.6616164"},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Coutrot, A., Guyader, N.: An audiovisual attention model for natural conversation scenes. In: IEEE International Conference on Image Processing, pp. 1100\u20131104. IEEE (2014)","DOI":"10.1109\/ICIP.2014.7025219"},{"issue":"8","key":"25_CR7","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1167\/14.8.5","volume":"14","author":"A Coutrot","year":"2014","unstructured":"Coutrot, A., Guyader, N.: How saliency, faces, and sound influence gaze in dynamic social scenes. J. Vis. 14(8), 5 (2014)","journal-title":"J. Vis."},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Coutrot, A., Guyader, N.: An efficient audiovisual saliency model to predict eye positions when looking at conversations. In: European Signal Processing Conference, pp. 1531\u20131535. IEEE (2015)","DOI":"10.1109\/EUSIPCO.2015.7362640"},{"issue":"4","key":"25_CR9","doi-asserted-by":"crossref","first-page":"2","DOI":"10.16910\/jemr.5.4.2","volume":"5","author":"A Coutrot","year":"2012","unstructured":"Coutrot, A., Guyader, N., Ionescu, G., Caplier, A.: Influence of soundtrack on eye movements during video exploration. J. Eye Mov. Res. 5(4), 2 (2012)","journal-title":"J. Eye Mov. Res."},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., et al.: FlowNet: learning optical flow with convolutional networks. In: IEEE International Conference on Computer Vision, pp. 2758\u20132766 (2015)","DOI":"10.1109\/ICCV.2015.316"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Hershey, S., et al.: 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":"25_CR12","doi-asserted-by":"crossref","unstructured":"Hossein Khatoonabadi, S., Vasconcelos, N., Bajic, I.V., Shan, Y.: How many bits does it take for a stimulus to be salient? In: IEEE Conference on Computer Vision and Pattern (2015)","DOI":"10.1109\/CVPR.2015.7299189"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Huang, X., Shen, C., Boix, X., Zhao, Q.: SALICON: reducing the semantic gap in saliency prediction by adapting deep neural networks. In: IEEE International Conference on Computer Vision (2015)","DOI":"10.1109\/ICCV.2015.38"},{"key":"25_CR14","doi-asserted-by":"publisher","first-page":"1254","DOI":"10.1109\/34.730558","volume":"11","author":"L Itti","year":"1998","unstructured":"Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. Pattern Anal. Mach. Intell. 11, 1254\u20131259 (1998)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1007\/978-3-030-01264-9_37","volume-title":"Computer Vision \u2013 ECCV 2018","author":"L Jiang","year":"2018","unstructured":"Jiang, L., Xu, M., Liu, T., Qiao, M., Wang, Z.: DeepVS: a deep learning based video saliency prediction approach. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11218, pp. 625\u2013642. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_37"},{"issue":"21","key":"25_CR16","doi-asserted-by":"publisher","first-page":"1943","DOI":"10.1016\/j.cub.2005.09.040","volume":"15","author":"C Kayser","year":"2005","unstructured":"Kayser, C., Petkov, C.I., Lippert, M., Logothetis, N.K.: Mechanisms for allocating auditory attention: an auditory saliency map. Curr. Biol. 15(21), 1943\u20131947 (2005)","journal-title":"Curr. Biol."},{"key":"25_CR17","doi-asserted-by":"crossref","unstructured":"Li, C., Xu, M., Du, X., Wang, Z.: Bridge the gap between VQA and human behavior on omnidirectional video: a large-scale dataset and a deep learning model. In: ACM International Conference on Multimedia, pp. 932\u2013940 (2018)","DOI":"10.1145\/3240508.3240581"},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Y., Zhang, S., Xu, M., He, X.: Predicting salient face in multiple-face videos. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4420\u20134428 (2017)","DOI":"10.1109\/CVPR.2017.343"},{"key":"25_CR19","doi-asserted-by":"crossref","unstructured":"Marighetto, P., et al.: Audio-visual attention: eye-tracking dataset and analysis toolbox. In: IEEE International Conference on Image Processing, pp. 1802\u20131806. IEEE (2017)","DOI":"10.1109\/ICIP.2017.8296592"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Min, K., Corso, J.J.: TASED-Net: temporally-aggregating spatial encoder-decoder network for video saliency detection (2019)","DOI":"10.1109\/ICCV.2019.00248"},{"key":"25_CR21","unstructured":"Pan, J., Ferrer, C.C., McGuinness, K., O\u2019Connor, N.E., Torres, J., Sayrol, E., Giro-iNieto, X.: Salgan: Visual saliency prediction with generative adversarial networks. arXiv preprint arXiv:1701.01081 (2017)"},{"key":"25_CR22","doi-asserted-by":"crossref","unstructured":"Ren, S., Cao, X., Wei, Y., Sun, J.: Face alignment at 3000 fps via regressing local binary features. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1685\u20131692 (2014)","DOI":"10.1109\/CVPR.2014.218"},{"key":"25_CR23","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"25_CR24","unstructured":"SR-Research: Eyelink 1000 plus. https:\/\/www.sr-research.com\/products\/eyelink-1000-plus\/"},{"key":"25_CR25","unstructured":"Tavakoli, H.R., Borji, A., Rahtu, E., Kannala, J.: DAVE: a deep audio-visual embedding for dynamic saliency prediction. arXiv preprint arXiv:1905.10693 (2019)"},{"key":"25_CR26","doi-asserted-by":"crossref","unstructured":"Tsiami, A., Katsamanis, A., Maragos, P., Vatakis, A.: Towards a behaviorally-validated computational audiovisual saliency model. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 2847\u20132851. IEEE (2016)","DOI":"10.1109\/ICASSP.2016.7472197"},{"issue":"5","key":"25_CR27","doi-asserted-by":"publisher","first-page":"2368","DOI":"10.1109\/TIP.2017.2787612","volume":"27","author":"W Wang","year":"2017","unstructured":"Wang, W., Shen, J.: Deep visual attention prediction. IEEE Trans. Image Process. 27(5), 2368\u20132378 (2017)","journal-title":"IEEE Trans. Image Process."},{"key":"25_CR28","doi-asserted-by":"crossref","unstructured":"Wang, W., Shen, J., Guo, F., Cheng, M.M., Borji, A.: Revisiting video saliency: a large-scale benchmark and a new model. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4894\u20134903 (2018)","DOI":"10.1109\/CVPR.2018.00514"},{"key":"25_CR29","unstructured":"Xingjian, S., Chen, Z., Wang, H., Yeung, D.Y., Wong, W.K., Woo, W.C.: Convolutional LSTM network: a machine learning approach for precipitation nowcasting. In: Advances in Neural Information Processing Systems, pp. 802\u2013810 (2015)"},{"issue":"9","key":"25_CR30","doi-asserted-by":"publisher","first-page":"4529","DOI":"10.1109\/TIP.2018.2837106","volume":"27","author":"M Xu","year":"2018","unstructured":"Xu, M., Liu, Y., Hu, R., He, F.: Find who to look at: turning from action to saliency. IEEE Trans. Image Process. 27(9), 4529\u20134544 (2018)","journal-title":"IEEE Trans. Image Process."},{"issue":"11","key":"25_CR31","doi-asserted-by":"publisher","first-page":"2693","DOI":"10.1109\/TPAMI.2018.2858783","volume":"41","author":"M Xu","year":"2019","unstructured":"Xu, M., Song, Y., Wang, J., Qiao, M., Huo, L., Wang, Z.: Predicting head movement in panoramic video: a deep reinforcement learning approach. IEEE Trans. Pattern Anal. Mach. Intell. 41(11), 2693\u20132708 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Zanca, D., Melacci, S., Gori, M.: Gravitational laws of focus of attention. IEEE (2019)","DOI":"10.1109\/TPAMI.2019.2920636"},{"key":"25_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, J., Sclaroff, S.: Exploiting surroundedness for saliency detection: a boolean map approach. IEEE Trans. Pattern Anal. Mach. Intell., 889\u2013902 (2016)","DOI":"10.1109\/TPAMI.2015.2473844"},{"issue":"10","key":"25_CR34","doi-asserted-by":"publisher","first-page":"1499","DOI":"10.1109\/LSP.2016.2603342","volume":"23","author":"K Zhang","year":"2016","unstructured":"Zhang, K., Zhang, Z., Li, Z., Qiao, Y.: Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Process. Lett. 23(10), 1499\u20131503 (2016)","journal-title":"IEEE Signal Process. Lett."},{"key":"25_CR35","unstructured":"Zoom: Zoom announces lineup of global technology and thought leaders for zoomtopia 2018. https:\/\/blog.zoom.us\/wordpress\/2018\/07\/11\/zoom-announces-lineup-of-global-technology-and-thought-leaders-for-zoomtopia-2018\/"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58565-5_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,11]],"date-time":"2024-11-11T00:08:46Z","timestamp":1731283726000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58565-5_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585648","9783030585655"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58565-5_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"12 November 2020","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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","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":"7","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)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}