{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T15:24:36Z","timestamp":1785857076632,"version":"3.56.0"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585570","type":"print"},{"value":"9783030585587","type":"electronic"}],"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\/978-3-030-58558-7_25","type":"book-chapter","created":{"date-parts":[[2020,10,28]],"date-time":"2020-10-28T09:03:08Z","timestamp":1603875788000},"page":"419-435","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":157,"title":["Unified Image and Video Saliency Modeling"],"prefix":"10.1007","author":[{"given":"Richard","family":"Droste","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianbo","family":"Jiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J. Alison","family":"Noble","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,10,29]]},"reference":[{"issue":"7","key":"25_CR1","first-page":"1688","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 TMM 20(7), 1688\u20131698 (2017)","journal-title":"IEEE TMM"},{"key":"25_CR2","unstructured":"Borji, A.: Saliency prediction in the deep learning era: an empirical investigation. arXiv:1810.03716 (2018)"},{"issue":"1","key":"25_CR3","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1109\/TPAMI.2012.89","volume":"35","author":"A Borji","year":"2012","unstructured":"Borji, A., Itti, L.: State-of-the-art in visual attention modeling. IEEE TPAMI 35(1), 185\u2013207 (2012)","journal-title":"IEEE TPAMI"},{"key":"25_CR4","unstructured":"Bousmalis, K., Trigeorgis, G., Silberman, N., Krishnan, D., Erhan, D.: Domain separation networks. In: NeurIPS (2016)"},{"issue":"3","key":"25_CR5","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1109\/TPAMI.2018.2815601","volume":"41","author":"Z Bylinskii","year":"2019","unstructured":"Bylinskii, Z., Judd, T., Oliva, A., Torralba, A., Durand, F.: What do different evaluation metrics tell us about saliency models? IEEE TPAMI 41(3), 740\u2013757 (2019)","journal-title":"IEEE TPAMI"},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Chang, W.G., You, T., Seo, S., Kwak, S., Han, B.: Domain-specific batch normalization for unsupervised domain adaptation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00753"},{"issue":"10","key":"25_CR7","first-page":"5142","volume":"27","author":"M Cornia","year":"2016","unstructured":"Cornia, M., Baraldi, L., Serra, G., Cucchiara, R.: Predicting human eye fixations via an LSTM-based saliency attentive model. IEEE TIP 27(10), 5142\u20135154 (2016)","journal-title":"IEEE TIP"},{"issue":"9","key":"25_CR8","first-page":"3910","volume":"23","author":"Y Fang","year":"2014","unstructured":"Fang, Y., Wang, Z., Lin, W., Fang, Z.: Video saliency incorporating spatiotemporal cues and uncertainty weighting. IEEE TIP 23(9), 3910\u20133921 (2014)","journal-title":"IEEE TIP"},{"key":"25_CR9","unstructured":"Gal, Y., Ghahramani, Z.: A Theoretically grounded application of dropout in recurrent neural networks. In: NeurIPS (2016)"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Gorji, S., Clark, J.J.: Going from image to video saliency: augmenting image salience with dynamic attentional push. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00783"},{"key":"25_CR11","unstructured":"Guo, C., Ma, Q., Zhang, L.: Spatio-temporal saliency detection using phase spectrum of quaternion fourier transform. In: CVPR (2008)"},{"issue":"1","key":"25_CR12","first-page":"185","volume":"19","author":"C Guo","year":"2009","unstructured":"Guo, C., Zhang, L.: A novel multiresolution spatiotemporal saliency detection model and its applications in image and video compression. IEEE TIP 19(1), 185\u2013198 (2009)","journal-title":"IEEE TIP"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Harel, J., Koch, C., Perona, P.: Graph-based visual saliency. In: NeurIPS (2007)","DOI":"10.7551\/mitpress\/7503.003.0073"},{"key":"25_CR14","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: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299189"},{"key":"25_CR15","unstructured":"Hou, X., Zhang, L.: Dynamic visual attention: searching for coding length increments. In: NeurIPS (2009)"},{"key":"25_CR16","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: ICCV (2015)","DOI":"10.1109\/ICCV.2015.38"},{"issue":"11","key":"25_CR17","doi-asserted-by":"publisher","first-page":"1254","DOI":"10.1109\/34.730558","volume":"20","author":"L Itti","year":"1998","unstructured":"Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. IEEE TPAMI 20(11), 1254\u20131259 (1998)","journal-title":"IEEE TPAMI"},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Jetley, S., Murray, N., Vig, E.: End-to-end saliency mapping via probability distribution prediction. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.620"},{"key":"25_CR19","doi-asserted-by":"crossref","unstructured":"Jiang, L., Xu, M., Liu, T., Qiao, M., Wang, Z.: DeepVS: a deep learning based video saliency prediction approach. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01264-9_37"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Jiang, M., Huang, S., Duan, J., Zhao, Q.: SALICON: saliency in context. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298710"},{"key":"25_CR21","unstructured":"Judd, T., Durand, F., Torralba, A.: A Benchmark of computational models of saliency to predict human fixations. In: MIT-CSAIL-TR-2012, vol. 1, pp. 1\u20137 (2012)"},{"key":"25_CR22","doi-asserted-by":"crossref","unstructured":"Judd, T., Ehinger, K., Durand, F., Torralba, A.: Learning to predict where humans look. In: ICCV (2009)","DOI":"10.1109\/ICCV.2009.5459462"},{"issue":"9","key":"25_CR23","first-page":"4446","volume":"26","author":"SSS Kruthiventi","year":"2015","unstructured":"Kruthiventi, S.S.S., Ayush, K., Babu, R.V.: DeepFix: a fully convolutional neural network for predicting human eye fixations. IEEE TIP 26(9), 4446\u20134456 (2015)","journal-title":"IEEE TIP"},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"K\u00fcmmerer, M., Wallis, T.S.A., Bethge, M.: DeepGaze II: reading fixations from deep features trained on object recognition. arXiv:1610.01563 (2016)","DOI":"10.1167\/17.10.1147"},{"key":"25_CR25","first-page":"1113","volume":"26","author":"Q Lai","year":"2019","unstructured":"Lai, Q., Wang, W., Sun, H., Shen, J.: Video saliency prediction using spatiotemporal residual attentive networks. IEEE TIP 26, 1113\u20131126 (2019)","journal-title":"IEEE TIP"},{"issue":"5","key":"25_CR26","doi-asserted-by":"publisher","first-page":"802","DOI":"10.1109\/TPAMI.2006.86","volume":"28","author":"O Le Meur","year":"2006","unstructured":"Le Meur, O., Le Callet, P., Barba, D., Thoreau, D.: A coherent computational approach to model bottom-up visual attention. IEEE TPAMI 28(5), 802\u2013817 (2006)","journal-title":"IEEE TPAMI"},{"issue":"5","key":"25_CR27","doi-asserted-by":"publisher","first-page":"893","DOI":"10.1109\/TPAMI.2016.2567391","volume":"39","author":"V Leboran","year":"2016","unstructured":"Leboran, V., Garcia-Diaz, A., Fdez-Vidal, X.R., Pardo, X.M.: Dynamic whitening saliency. IEEE TPAMI 39(5), 893\u2013907 (2016)","journal-title":"IEEE TPAMI"},{"key":"25_CR28","unstructured":"Li, Y., Wang, N., Shi, J., Liu, J., Hou, X.: Revisiting batch normalization for practical domain adaptation. In: ICLR (2016)"},{"key":"25_CR29","unstructured":"Linardos, P., Mohedano, E., Nieto, J.J., McGuinness, K., Giro-i Nieto, X., O\u2019Connor, N.E.: Simple vs complex temporal recurrences for video saliency prediction. In: BMVC (2019)"},{"key":"25_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"816","DOI":"10.1007\/978-3-319-46487-9_50","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Liu","year":"2016","unstructured":"Liu, J., Shahroudy, A., Xu, D., Wang, G.: Spatio-temporal LSTM with trust gates for 3D human action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 816\u2013833. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_50"},{"issue":"Nov","key":"25_CR31","first-page":"2579","volume":"9","author":"LVD Maaten","year":"2008","unstructured":"Maaten, L.V.D., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(Nov), 2579\u20132605 (2008)","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"25_CR32","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1109\/TPAMI.2009.112","volume":"32","author":"V Mahadevan","year":"2009","unstructured":"Mahadevan, V., Vasconcelos, N.: Spatiotemporal saliency in dynamic scenes. IEEE TPAMI 32(1), 171\u2013177 (2009)","journal-title":"IEEE TPAMI"},{"issue":"3","key":"25_CR33","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1007\/s11263-009-0215-3","volume":"82","author":"S Marat","year":"2009","unstructured":"Marat, S., Phuoc, T.H., Granjon, L., Guyader, N., Pellerin, D., Gu\u00e9rin-Dugu\u00e9, A.: Modelling spatio-temporal saliency to predict gaze direction for short videos. Int. J. Comput. Vis. 82(3), 231 (2009)","journal-title":"Int. J. Comput. Vis."},{"issue":"7","key":"25_CR34","doi-asserted-by":"publisher","first-page":"1408","DOI":"10.1109\/TPAMI.2014.2366154","volume":"37","author":"S Mathe","year":"2015","unstructured":"Mathe, S., Sminchisescu, C.: Actions in the eye: dynamic gaze datasets and learnt saliency models for visual recognition. IEEE TPAMI 37(7), 1408\u20131424 (2015)","journal-title":"IEEE TPAMI"},{"key":"25_CR35","doi-asserted-by":"crossref","unstructured":"Min, K., Corso, J.J.: TASED-net: temporally-aggregating spatial encoder-decoder network for video saliency detection. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00248"},{"key":"25_CR36","unstructured":"Pan, J., et al.: SaLGAN: visual saliency prediction with generative adversarial networks. arXiv:1701.01081 (2017)"},{"key":"25_CR37","doi-asserted-by":"crossref","unstructured":"Pan, J., Sayrol, E., Giro-i Nieto, X., McGuinness, K., O\u2019Connor, N.E.: Shallow and deep convolutional networks for saliency prediction. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.71"},{"issue":"4","key":"25_CR38","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1109\/TPAMI.2018.2814042","volume":"41","author":"A Rozantsev","year":"2019","unstructured":"Rozantsev, A., Salzmann, M., Fua, P.: Beyond sharing weights for deep domain adaptation. IEEE TPAMI 41(4), 801\u2013814 (2019)","journal-title":"IEEE TPAMI"},{"key":"25_CR39","doi-asserted-by":"crossref","unstructured":"Rudoy, D., Goldman, D.B., Shechtman, E., Zelnik-Manor, L.: Learning video saliency from human gaze using candidate selection. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.152"},{"key":"25_CR40","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: inverted residuals and linear bottlenecks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"issue":"12","key":"25_CR41","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1167\/9.12.15","volume":"9","author":"HJ Seo","year":"2009","unstructured":"Seo, H.J., Milanfar, P.: Static and space-time visual saliency detection by self-resemblance. J. Vis. 9(12), 15\u201315 (2009)","journal-title":"J. Vis."},{"issue":"1","key":"25_CR42","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1016\/S0004-3702(02)00399-5","volume":"146","author":"Y Sun","year":"2003","unstructured":"Sun, Y., Fisher, R.: Object-based visual attention for computer vision. Artif. Intell. 146(1), 77\u2013123 (2003)","journal-title":"Artif. Intell."},{"key":"25_CR43","doi-asserted-by":"crossref","unstructured":"Tsai, J.C., Chien, J.T.: Adversarial domain separation and adaptation. In: 2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP), pp. 1\u20136 (2017)","DOI":"10.1109\/MLSP.2017.8168121"},{"key":"25_CR44","doi-asserted-by":"crossref","unstructured":"Valipour, S., Siam, M., Jagersand, M., Ray, N.: Recurrent fully convolutional networks for video segmentation. In: IEEE WACV, pp. 29\u201336 (2017)","DOI":"10.1109\/WACV.2017.11"},{"key":"25_CR45","doi-asserted-by":"crossref","unstructured":"Vig, E., Dorr, M., Cox, D.: Large-scale optimization of hierarchical features for saliency prediction in natural images. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.358"},{"issue":"5","key":"25_CR46","first-page":"2368","volume":"27","author":"W Wang","year":"2017","unstructured":"Wang, W., Shen, J.: Deep visual attention prediction. IEEE TIP 27(5), 2368\u20132378 (2017)","journal-title":"IEEE TIP"},{"key":"25_CR47","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: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00514"},{"key":"25_CR48","unstructured":"Wang, W., Shen, J., Xie, J., Cheng, M.M., Ling, H., Borji, A.: Revisiting video saliency prediction in the deep learning era. IEEE TPAMI (2019, early access)"},{"key":"25_CR49","doi-asserted-by":"crossref","unstructured":"Xiao, T., Li, H., Ouyang, W., Wang, X.: Learning deep feature representations with domain guided dropout for person re-identification. arXiv:1604.07528 (2016)","DOI":"10.1109\/CVPR.2016.140"},{"key":"25_CR50","doi-asserted-by":"crossref","unstructured":"Yang, S., Lin, G., Jiang, Q., Lin, W.: A dilated inception network for visual saliency prediction. IEEE TMM 22(8), 2163\u20132176 (2020)","DOI":"10.1109\/TMM.2019.2947352"},{"key":"25_CR51","doi-asserted-by":"crossref","unstructured":"Zheng, Q., Jiao, J., Cao, Y., Lau, R.W.: Task-driven webpage saliency. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01264-9_18"},{"key":"25_CR52","doi-asserted-by":"crossref","unstructured":"Zhong, S.H., Liu, Y., Ren, F., Zhang, J., Ren, T.: Video saliency detection via dynamic consistent spatio-temporal attention modelling. In: AAAI (2013)","DOI":"10.1609\/aaai.v27i1.8642"}],"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\/978-3-030-58558-7_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T08:53:20Z","timestamp":1730105600000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58558-7_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585570","9783030585587"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58558-7_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"29 October 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)"}}]}}