{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T05:19:56Z","timestamp":1742966396068,"version":"3.40.3"},"publisher-location":"Cham","reference-count":111,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030948924"},{"type":"electronic","value":"9783030948931"}],"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\/978-3-030-94893-1_21","type":"book-chapter","created":{"date-parts":[[2022,1,22]],"date-time":"2022-01-22T13:02:27Z","timestamp":1642856547000},"page":"453-476","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["On the\u00a0Use of\u00a03D CNNs for\u00a0Video Saliency Modeling"],"prefix":"10.1007","author":[{"given":"Yasser Abdelaziz","family":"Dahou Djilali","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohamed","family":"Sayah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin","family":"McGuinness","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Noel E.","family":"O\u2019Connor","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,1,22]]},"reference":[{"key":"21_CR1","doi-asserted-by":"crossref","unstructured":"Adel Bargal, S., Zunino, A., Kim, D., Zhang, J., Murino, V., Sclaroff, S.: Excitation backprop for RNNs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1440\u20131449 (2018)","DOI":"10.1109\/CVPR.2018.00156"},{"key":"21_CR2","unstructured":"Amudha, J., Radha, D., Naresh, P.: Video shot detection using saliency measure. Int. J. Comput. Appl. 975, 8887 (2012). Citeseer"},{"key":"21_CR3","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1016\/j.visres.2012.04.005","volume":"74","author":"S Arun","year":"2012","unstructured":"Arun, S.: Turning visual search time on its head. Vis. Res. 74, 86\u201392 (2012)","journal-title":"Vis. Res."},{"issue":"7","key":"21_CR4","doi-asserted-by":"crossref","first-page":"1688","DOI":"10.1109\/TMM.2017.2777665","volume":"20","author":"C Bak","year":"2018","unstructured":"Bak, C., Kocak, A., Erdem, E., Erdem, A.: Spatio-temporal saliency networks for dynamic saliency prediction. IEEE Trans. Multimed. 20(7), 1688\u20131698 (2018)","journal-title":"IEEE Trans. Multimed."},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Boccignone, G.: Nonparametric Bayesian attentive video analysis. In: 2008 19th International Conference on Pattern Recognition, pp. 1\u20134. IEEE (2008)","DOI":"10.1109\/ICPR.2008.4760948"},{"issue":"1\u20132","key":"21_CR6","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1016\/j.physa.2003.09.011","volume":"331","author":"G Boccignone","year":"2004","unstructured":"Boccignone, G., Ferraro, M.: Modelling gaze shift as a constrained random walk. Phys. A 331(1\u20132), 207\u2013218 (2004)","journal-title":"Phys. A"},{"key":"21_CR7","unstructured":"Borji, A.: Saliency prediction in the deep learning era: an empirical investigation. arXiv preprint arXiv:1810.03716 (2018)"},{"issue":"1","key":"21_CR8","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1109\/TPAMI.2012.89","volume":"35","author":"A Borji","year":"2013","unstructured":"Borji, A., Itti, L.: State-of-the-art in visual attention modeling. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 185\u2013207 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR9","unstructured":"Borji, A., Itti, L.: CAT 2000: a large scale fixation dataset for boosting saliency research. arXiv preprint arXiv:1505.03581 (2015)"},{"key":"21_CR10","unstructured":"Bruce, N., Tsotsos, J.: Saliency based on information maximization. In: Advances in Neural Information Processing Systems, pp. 155\u2013162 (2006)"},{"key":"21_CR11","unstructured":"Bylinskii, Z., et al.: MIT saliency benchmark (2015)"},{"issue":"3","key":"21_CR12","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1109\/TPAMI.2018.2815601","volume":"41","author":"Z Bylinskii","year":"2018","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. 41(3), 740\u2013757 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Chao, F.Y., Zhang, L., Hamidouche, W., Deforges, O.: Salgan360: visual saliency prediction on 360 degree images with generative adversarial networks. In: 2018 IEEE International Conference on Multimedia & Expo Workshops (ICMEW), pp. 01\u201304. IEEE (2018)","DOI":"10.1109\/ICMEW.2018.8551543"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Cheng, H.T., Chao, C.H., Dong, J.D., Wen, H.K., Liu, T.L., Sun, M.: Cube padding for weakly-supervised saliency prediction in 360 videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1420\u20131429 (2018)","DOI":"10.1109\/CVPR.2018.00154"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Cornia, M., Baraldi, L., Serra, G., Cucchiara, R.: A deep multi-level network for saliency prediction. In: 2016 23rd International Conference on Pattern Recognition (ICPR), pp. 3488\u20133493. IEEE (2016)","DOI":"10.1109\/ICPR.2016.7900174"},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Dahou Djilali, Y.A., Sayah, M., McGuinness, K., O\u2019Connor, N.E.: 3DSAL: An efficient 3D-CNN architecture for video saliency prediction. In: Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, pp. 27\u201336. INSTICC, SciTePress (2020). https:\/\/doi.org\/10.5220\/0008875600270036","DOI":"10.5220\/0008875600270036"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"David, E.J., Guti\u00e9rrez, J., Coutrot, A., Da Silva, M.P., Callet, P.L.: A dataset of head and eye movements for 360 videos. In: Proceedings of the 9th ACM Multimedia Systems Conference, pp. 432\u2013437 (2018)","DOI":"10.1145\/3204949.3208139"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Droste, R., Jiao, J., Noble, J.A.: Unified image and video saliency modeling. arXiv preprint arXiv:2003.05477 (2020)","DOI":"10.1007\/978-3-030-58558-7_25"},{"issue":"6\u20137","key":"21_CR20","doi-asserted-by":"crossref","first-page":"945","DOI":"10.1080\/13506280902834720","volume":"17","author":"KA Ehinger","year":"2009","unstructured":"Ehinger, K.A., Hidalgo-Sotelo, B., Torralba, A., Oliva, A.: Modelling search for people in 900 scenes: a combined source model of eye guidance. Vis. Cogn. 17(6\u20137), 945\u2013978 (2009)","journal-title":"Vis. Cogn."},{"issue":"5","key":"21_CR21","doi-asserted-by":"crossref","first-page":"1054","DOI":"10.1109\/TRO.2008.2004977","volume":"24","author":"S Frintrop","year":"2008","unstructured":"Frintrop, S., Jensfelt, P.: Attentional landmarks and active gaze control for visual SLAM. IEEE Trans. Rob. 24(5), 1054\u20131065 (2008)","journal-title":"IEEE Trans. Rob."},{"key":"21_CR22","unstructured":"Gao, D., Vasconcelos, N.: Discriminant saliency for visual recognition from cluttered scenes. In: Advances in Neural Information Processing Systems, pp. 481\u2013488 (2005)"},{"key":"21_CR23","unstructured":"Gao, J., Huang, Y., Yu, H.H.: Method and system for video summarization, 31 May 2016. US Patent 9,355,635"},{"key":"21_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1007\/978-3-642-04697-1_32","volume-title":"Advanced Concepts for Intelligent Vision Systems","author":"A Garcia-Diaz","year":"2009","unstructured":"Garcia-Diaz, A., Fdez-Vidal, X.R., Pardo, X.M., Dosil, R.: Decorrelation and distinctiveness provide with human-like saliency. In: Blanc-Talon, J., Philips, W., Popescu, D., Scheunders, P. (eds.) ACIVS 2009. LNCS, vol. 5807, pp. 343\u2013354. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-04697-1_32"},{"issue":"1","key":"21_CR25","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/j.imavis.2011.11.007","volume":"30","author":"A Garcia-Diaz","year":"2012","unstructured":"Garcia-Diaz, A., Fdez-Vidal, X.R., Pardo, X.M., Dosil, R.: Saliency from hierarchical adaptation through decorrelation and variance normalization. Image Vis. Comput. 30(1), 51\u201364 (2012)","journal-title":"Image Vis. Comput."},{"issue":"10","key":"21_CR26","doi-asserted-by":"crossref","first-page":"1915","DOI":"10.1109\/TPAMI.2011.272","volume":"34","author":"S Goferman","year":"2012","unstructured":"Goferman, S., Zelnik-Manor, L., Tal, A.: Context-aware saliency detection. IEEE Trans. Pattern Anal. Mach. Intell. 34(10), 1915\u20131926 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR27","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672\u20132680 (2014)"},{"key":"21_CR28","unstructured":"Guo, C., Ma, Q., Zhang, L.: Spatio-temporal saliency detection using phase spectrum of quaternion fourier transform. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20138. IEEE (2008)"},{"issue":"1","key":"21_CR29","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 Trans. Image Process. 19(1), 185\u2013198 (2009)","journal-title":"IEEE Trans. Image Process."},{"issue":"8","key":"21_CR30","doi-asserted-by":"crossref","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":"21_CR31","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5501\u20135510 (2015)","DOI":"10.1109\/CVPR.2015.7299189"},{"key":"21_CR32","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: Proceedings of the IEEE International Conference on Computer Vision, pp. 262\u2013270 (2015)","DOI":"10.1109\/ICCV.2015.38"},{"issue":"10","key":"21_CR33","doi-asserted-by":"crossref","first-page":"1304","DOI":"10.1109\/TIP.2004.834657","volume":"13","author":"L Itti","year":"2004","unstructured":"Itti, L.: Automatic foveation for video compression using a neurobiological model of visual attention. IEEE Trans. Image Process. 13(10), 1304\u20131318 (2004)","journal-title":"IEEE Trans. Image Process."},{"issue":"10","key":"21_CR34","doi-asserted-by":"crossref","first-page":"1295","DOI":"10.1016\/j.visres.2008.09.007","volume":"49","author":"L Itti","year":"2009","unstructured":"Itti, L., Baldi, P.: Bayesian surprise attracts human attention. Vision. Res. 49(10), 1295\u20131306 (2009)","journal-title":"Vision. Res."},{"issue":"10\u201312","key":"21_CR35","doi-asserted-by":"crossref","first-page":"1489","DOI":"10.1016\/S0042-6989(99)00163-7","volume":"40","author":"L Itti","year":"2000","unstructured":"Itti, L., Koch, C.: A saliency-based search mechanism for overt and covert shifts of visual attention. Vis. Res. 40(10\u201312), 1489\u20131506 (2000)","journal-title":"Vis. Res."},{"key":"21_CR36","doi-asserted-by":"crossref","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."},{"issue":"11","key":"21_CR37","doi-asserted-by":"crossref","first-page":"2924","DOI":"10.1109\/TIP.2010.2050928","volume":"19","author":"N Jacobson","year":"2010","unstructured":"Jacobson, N., Lee, Y.L., Mahadevan, V., Vasconcelos, N., Nguyen, T.Q.: A novel approach to FRUC using discriminant saliency and frame segmentation. IEEE Trans. Image Process. 19(11), 2924\u20132934 (2010)","journal-title":"IEEE Trans. Image Process."},{"key":"21_CR38","unstructured":"James, W.: The Principles of Psychology, vol. 1. Cosimo, Inc. (1950)"},{"issue":"1","key":"21_CR39","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2013","unstructured":"Ji, S., Xu, W., Yang, M., Yu, K.: 3D convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 221\u2013231 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR40","doi-asserted-by":"crossref","first-page":"103887","DOI":"10.1016\/j.imavis.2020.103887","volume":"95","author":"S Jia","year":"2020","unstructured":"Jia, S., Bruce, N.D.: EML-NET: an expandable multi-layer network for saliency prediction. Image Vis. Comput. 95, 103887 (2020)","journal-title":"Image Vis. Comput."},{"key":"21_CR41","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: Proceedings of the European Conference on Computer Vision (ECCV), pp. 602\u2013617 (2018)","DOI":"10.1007\/978-3-030-01264-9_37"},{"key":"21_CR42","unstructured":"Jiang, L., Xu, M., Wang, Z.: Predicting video saliency with object-to-motion CNN and two-layer convolutional LSTM. arXiv preprint arXiv:1709.06316 (2017)"},{"key":"21_CR43","doi-asserted-by":"crossref","unstructured":"Jiang, M., Huang, S., Duan, J., Zhao, Q.: SALICON: saliency in context. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015","DOI":"10.1109\/CVPR.2015.7298710"},{"key":"21_CR44","unstructured":"Judd, T., Durand, F., Torralba, A.: A benchmark of computational models of saliency to predict human fixations. MIT Technical report (2012)"},{"key":"21_CR45","unstructured":"Judd, T., Durand, F., Torralba, A.: A benchmark of computational models of saliency to predict human fixations (2012)"},{"key":"21_CR46","doi-asserted-by":"crossref","unstructured":"Judd, T., Ehinger, K., Durand, F., Torralba, A.: Learning to predict where humans look. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 2106\u20132113. IEEE (2009)","DOI":"10.1109\/ICCV.2009.5459462"},{"issue":"5","key":"21_CR47","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1167\/9.5.7","volume":"9","author":"W Kienzle","year":"2009","unstructured":"Kienzle, W., Franz, M.O., Sch\u00f6lkopf, B., Wichmann, F.A.: Center-surround patterns emerge as optimal predictors for human saccade targets. J. Vis. 9(5), 7 (2009)","journal-title":"J. Vis."},{"key":"21_CR48","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"21_CR49","series-title":"Synthese Library (Studies in Epistemology, Logic, Methodology, and Philosophy of Science)","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1007\/978-94-009-3833-5_5","volume-title":"Matters of intelligence","author":"C Koch","year":"1987","unstructured":"Koch, C., Ullman, S.: Shifts in selective visual attention: towards the underlying neural circuitry. In: Vaina, L.M. (ed.) Matters of intelligence. Synthese Library (Studies in Epistemology, Logic, Methodology, and Philosophy of Science), vol. 188, pp. 115\u2013141. Springer, Dordrecht (1987). https:\/\/doi.org\/10.1007\/978-94-009-3833-5_5"},{"key":"21_CR50","doi-asserted-by":"crossref","unstructured":"Kootstra, G., Nederveen, A., De Boer, B.: Paying attention to symmetry. In: British Machine Vision Conference (BMVC2008), pp. 1115\u20131125. The British Machine Vision Association and Society for Pattern Recognition (2008)","DOI":"10.5244\/C.22.111"},{"key":"21_CR51","unstructured":"Kotseruba, I., Wloka, C., Rasouli, A., Tsotsos, J.K.: Do saliency models detect odd-one-out targets? New datasets and evaluations. arXiv preprint arXiv:2005.06583 (2020)"},{"issue":"9","key":"21_CR52","doi-asserted-by":"crossref","first-page":"4446","DOI":"10.1109\/TIP.2017.2710620","volume":"26","author":"SS Kruthiventi","year":"2017","unstructured":"Kruthiventi, S.S., Ayush, K., Babu, R.V.: DeepFix: a fully convolutional neural network for predicting human eye fixations. IEEE Trans. Image Process. 26(9), 4446\u20134456 (2017)","journal-title":"IEEE Trans. Image Process."},{"key":"21_CR53","unstructured":"K\u00fcmmerer, M., Theis, L., Bethge, M.: Deep gaze i: Boosting saliency prediction with feature maps trained on ImageNet. arXiv preprint arXiv:1411.1045 (2014)"},{"key":"21_CR54","doi-asserted-by":"crossref","first-page":"1113","DOI":"10.1109\/TIP.2019.2936112","volume":"29","author":"Q Lai","year":"2019","unstructured":"Lai, Q., Wang, W., Sun, H., Shen, J.: Video saliency prediction using spatiotemporal residual attentive networks. IEEE Trans. Image Process. 29, 1113\u20131126 (2019)","journal-title":"IEEE Trans. Image Process."},{"issue":"19","key":"21_CR55","doi-asserted-by":"crossref","first-page":"2483","DOI":"10.1016\/j.visres.2007.06.015","volume":"47","author":"O Le Meur","year":"2007","unstructured":"Le Meur, O., Le Callet, P., Barba, D.: Predicting visual fixations on video based on low-level visual features. Vis. Res. 47(19), 2483\u20132498 (2007)","journal-title":"Vis. Res."},{"issue":"5","key":"21_CR56","doi-asserted-by":"crossref","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 Trans. Pattern Anal. Mach. Intell. 28(5), 802\u2013817 (2006)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"5","key":"21_CR57","doi-asserted-by":"crossref","first-page":"893","DOI":"10.1109\/TPAMI.2016.2567391","volume":"39","author":"V Leboran","year":"2017","unstructured":"Leboran, V., Garcia-Diaz, A., Fdez-Vidal, X.R., Pardo, X.M.: Dynamic whitening saliency. IEEE Trans. Pattern Anal. Mach. Intell. 39(5), 893\u2013907 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"8","key":"21_CR58","doi-asserted-by":"crossref","first-page":"3919","DOI":"10.1109\/TIP.2016.2579306","volume":"25","author":"X Li","year":"2016","unstructured":"Li, X., et al.: DeepSaliency: multi-task deep neural network model for salient object detection. IEEE Trans. Image Process. 25(8), 3919\u20133930 (2016)","journal-title":"IEEE Trans. Image Process."},{"key":"21_CR59","unstructured":"Linardos, P., Mohedano, E., Nieto, J.J., O\u2019Connor, N.E., Giro-i Nieto, X., McGuinness, K.: Simple vs complex temporal recurrences for video saliency prediction. arXiv preprint arXiv:1907.01869 (2019)"},{"issue":"7","key":"21_CR60","doi-asserted-by":"crossref","first-page":"3264","DOI":"10.1109\/TIP.2018.2817047","volume":"27","author":"N Liu","year":"2018","unstructured":"Liu, N., Han, J.: A deep spatial contextual long-term recurrent convolutional network for saliency detection. IEEE Trans. Image Process. 27(7), 3264\u20133274 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"21_CR61","unstructured":"Liu, N., Han, J., Zhang, D., Wen, S., Liu, T.: Predicting eye fixations using convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 362\u2013370 (2015)"},{"issue":"5","key":"21_CR62","doi-asserted-by":"crossref","first-page":"907","DOI":"10.1109\/TMM.2005.854410","volume":"7","author":"YF Ma","year":"2005","unstructured":"Ma, Y.F., Hua, X.S., Lu, L., Zhang, H.J.: A generic framework of user attention model and its application in video summarization. IEEE Trans. Multimed. 7(5), 907\u2013919 (2005)","journal-title":"IEEE Trans. Multimed."},{"key":"21_CR63","doi-asserted-by":"crossref","unstructured":"Mahadevan, V., Vasconcelos, N.: Saliency-based discriminant tracking. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1007\u20131013. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206573"},{"key":"21_CR64","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4939-3435-5","volume-title":"From Human Attention to Computational Attention","author":"M Mancas","year":"2016","unstructured":"Mancas, M., Ferrera, V.P., Riche, N., Taylor, J.G.: From Human Attention to Computational Attention, vol. 2. Springer, Heidelberg (2016). https:\/\/doi.org\/10.1007\/978-1-4939-3435-5"},{"key":"21_CR65","doi-asserted-by":"crossref","unstructured":"Marat, S., Guironnet, M., Pellerin, D.: Video summarization using a visual attention model. In: 2007 15th European Signal Processing Conference, pp. 1784\u20131788. IEEE (2007)","DOI":"10.1155\/2007\/60245"},{"issue":"3","key":"21_CR66","doi-asserted-by":"crossref","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":"21_CR67","doi-asserted-by":"crossref","first-page":"1408","DOI":"10.1109\/TPAMI.2014.2366154","volume":"37","author":"S Mathe","year":"2014","unstructured":"Mathe, S., Sminchisescu, C.: Actions in the eye: dynamic gaze datasets and learnt saliency models for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(7), 1408\u20131424 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"7","key":"21_CR68","doi-asserted-by":"crossref","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 Trans. Pattern Anal. Mach. Intell. 37(7), 1408\u20131424 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR69","unstructured":"Milanese, R.: Detecting salient regions in an image: from biological evidence to computer implementation. Ph. D Theses, the University of Geneva (1993)"},{"key":"21_CR70","doi-asserted-by":"crossref","unstructured":"Min, K., Corso, J.J.: TASED-net: temporally-aggregating spatial encoder-decoder network for video saliency detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2394\u20132403 (2019)","DOI":"10.1109\/ICCV.2019.00248"},{"issue":"1","key":"21_CR71","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1007\/s12559-010-9074-z","volume":"3","author":"PK Mital","year":"2011","unstructured":"Mital, P.K., Smith, T.J., Hill, R.L., Henderson, J.M.: Clustering of gaze during dynamic scene viewing is predicted by motion. Cogn. Comput. 3(1), 5\u201324 (2011)","journal-title":"Cogn. Comput."},{"key":"21_CR72","doi-asserted-by":"crossref","unstructured":"Murray, N., Vanrell, M., Otazu, X., Parraga, C.A.: Saliency estimation using a non-parametric low-level vision model. In: CVPR 2011, pp. 433\u2013440. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995506"},{"key":"21_CR73","doi-asserted-by":"crossref","unstructured":"Navalpakkam, V., Itti, L.: An integrated model of top-down and bottom-up attention for optimizing detection speed. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2006), vol. 2, pp. 2049\u20132056. IEEE (2006)","DOI":"10.1109\/CVPR.2006.54"},{"key":"21_CR74","unstructured":"Nwankpa, C., Ijomah, W., Gachagan, A., Marshall, S.: Activation functions: comparison of trends in practice and research for deep learning. CoRR abs\/1811.03378 (2018). http:\/\/arxiv.org\/abs\/1811.03378"},{"key":"21_CR75","doi-asserted-by":"crossref","unstructured":"Oliva, A., Torralba, A., Castelhano, M.S., Henderson, J.M.: Top-down control of visual attention in object detection. In: Proceedings 2003 International Conference on Image Processing (Cat. No. 03CH37429), vol. 1, p. I-253. IEEE (2003)","DOI":"10.1109\/ICIP.2003.1246946"},{"issue":"3","key":"21_CR76","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1016\/S1077-2014(03)00036-6","volume":"9","author":"N Ouerhani","year":"2003","unstructured":"Ouerhani, N., H\u00fcgli, H.: Real-time visual attention on a massively parallel SIMD architecture. Real-Time Imaging 9(3), 189\u2013196 (2003)","journal-title":"Real-Time Imaging"},{"key":"21_CR77","unstructured":"Pan, J., et al.: SalGAN: visual saliency prediction with generative adversarial networks. arXiv preprint arXiv:1701.01081 (2017)"},{"key":"21_CR78","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 598\u2013606 (2016)","DOI":"10.1109\/CVPR.2016.71"},{"key":"21_CR79","unstructured":"Panagiotis, L., Eva, M., Monica, C., Cathal, G., Xavier, G.i.N.: Temporal saliency adaptation in egocentric videos (2018)"},{"key":"21_CR80","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Pont-Tuset, J., McWilliams, B., Van Gool, L., Gross, M., Sorkine-Hornung, A.: A benchmark dataset and evaluation methodology for video object segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 724\u2013732 (2016)","DOI":"10.1109\/CVPR.2016.85"},{"key":"21_CR81","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1007\/3-540-49430-8_3","volume-title":"Neural Networks: Tricks of the Trade","author":"L Prechelt","year":"1998","unstructured":"Prechelt, L.: Early stopping - but when? In: Orr, G.B., M\u00fcller, K.-R. (eds.) Neural Networks: Tricks of the Trade. LNCS, vol. 1524, pp. 55\u201369. Springer, Heidelberg (1998). https:\/\/doi.org\/10.1007\/3-540-49430-8_3"},{"issue":"9","key":"21_CR82","doi-asserted-by":"crossref","first-page":"970","DOI":"10.1109\/34.877520","volume":"22","author":"CM Privitera","year":"2000","unstructured":"Privitera, C.M., Stark, L.W.: Algorithms for defining visual regions-of-interest: comparison with eye fixations. IEEE Trans. Pattern Anal. Mach. Intell. 22(9), 970\u2013982 (2000)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR83","doi-asserted-by":"crossref","unstructured":"Rai, Y., Le Callet, P., Guillotel, P.: Which saliency weighting for omni directional image quality assessment? In: 2017 Ninth International Conference on Quality of Multimedia Experience (QoMEX), pp. 1\u20136. IEEE (2017)","DOI":"10.1109\/QoMEX.2017.7965659"},{"issue":"5","key":"21_CR84","doi-asserted-by":"crossref","first-page":"769","DOI":"10.1109\/TCSVT.2013.2280096","volume":"24","author":"Z Ren","year":"2013","unstructured":"Ren, Z., Gao, S., Chia, L.T., Tsang, I.W.H.: Region-based saliency detection and its application in object recognition. IEEE Trans. Circ. Syst. Video Technol. 24(5), 769\u2013779 (2013)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"issue":"1","key":"21_CR85","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1007\/BF00130489","volume":"7","author":"RD Rimey","year":"1991","unstructured":"Rimey, R.D., Brown, C.M.: Controlling eye movements with hidden Markov models. Int. J. Comput. Vis. 7(1), 47\u201365 (1991)","journal-title":"Int. J. Comput. Vis."},{"issue":"19","key":"21_CR86","doi-asserted-by":"crossref","first-page":"3157","DOI":"10.1016\/S0042-6989(99)00077-2","volume":"39","author":"R Rosenholtz","year":"1999","unstructured":"Rosenholtz, R.: A simple saliency model predicts a number of motion popout phenomena. Vis. Res. 39(19), 3157\u20133163 (1999)","journal-title":"Vis. Res."},{"key":"21_CR87","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1147\u20131154 (2013)","DOI":"10.1109\/CVPR.2013.152"},{"issue":"4","key":"21_CR88","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1016\/S1389-0417(00)00015-2","volume":"1","author":"DD Salvucci","year":"2001","unstructured":"Salvucci, D.D.: An integrated model of eye movements and visual encoding. Cogn. Syst. Res. 1(4), 201\u2013220 (2001)","journal-title":"Cogn. Syst. Res."},{"issue":"8","key":"21_CR89","doi-asserted-by":"crossref","first-page":"1024","DOI":"10.1364\/JOSA.57.001024","volume":"57","author":"M Saslow","year":"1967","unstructured":"Saslow, M.: Effects of components of displacement-step stimuli upon latency for saccadic eye movement. Josa 57(8), 1024\u20131029 (1967)","journal-title":"Josa"},{"issue":"12","key":"21_CR90","doi-asserted-by":"crossref","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 (2009)","journal-title":"J. Vis."},{"key":"21_CR91","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"21_CR92","unstructured":"Sohlberg, M.M., Mateer, C.A.: Introduction to Cognitive Rehabilitation: Theory and Practice. Guilford Press (1989)"},{"key":"21_CR93","unstructured":"Sprague, N., Ballard, D.: Eye movements for reward maximization. In: Advances in Neural Information Processing Systems, pp. 1467\u20131474 (2004)"},{"key":"21_CR94","doi-asserted-by":"crossref","unstructured":"Suzuki, T., Yamanaka, T.: Saliency map estimation for omni-directional image considering prior distributions. In: 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 2079\u20132084. IEEE (2018)","DOI":"10.1109\/SMC.2018.00358"},{"issue":"7","key":"21_CR95","doi-asserted-by":"crossref","first-page":"1407","DOI":"10.1364\/JOSAA.20.001407","volume":"20","author":"A Torralba","year":"2003","unstructured":"Torralba, A.: Modeling global scene factors in attention. JOSA A 20(7), 1407\u20131418 (2003)","journal-title":"JOSA A"},{"key":"21_CR96","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 the IEEE International Conference on Computer Vision, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"issue":"1","key":"21_CR97","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1016\/0010-0285(80)90005-5","volume":"12","author":"AM Treisman","year":"1980","unstructured":"Treisman, A.M., Gelade, G.: A feature-integration theory of attention. Cogn. Psychol. 12(1), 97\u2013136 (1980)","journal-title":"Cogn. Psychol."},{"issue":"1\u20132","key":"21_CR98","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1016\/0004-3702(95)00025-9","volume":"78","author":"JK Tsotsos","year":"1995","unstructured":"Tsotsos, J.K., Culhane, S.M., Wai, W.Y.K., Lai, Y., Davis, N., Nuflo, F.: Modeling visual attention via selective tuning. Artif. Intell. 78(1\u20132), 507\u2013545 (1995)","journal-title":"Artif. Intell."},{"key":"21_CR99","doi-asserted-by":"crossref","unstructured":"Vig, E., Dorr, M., Cox, D.: Large-scale optimization of hierarchical features for saliency prediction in natural images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2798\u20132805 (2014)","DOI":"10.1109\/CVPR.2014.358"},{"key":"21_CR100","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4894\u20134903 (2018)","DOI":"10.1109\/CVPR.2018.00514"},{"key":"21_CR101","unstructured":"Wang, W., Shen, J., Xie, J., Cheng, M.M., Ling, H., Borji, A.: Revisiting video saliency prediction in the deep learning era. IEEE Trans. Pattern Anal. Mach. Intell. (2019)"},{"issue":"1","key":"21_CR102","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1109\/TPAMI.2017.2662005","volume":"40","author":"W Wang","year":"2017","unstructured":"Wang, W., Shen, J., Yang, R., Porikli, F.: Saliency-aware video object segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 40(1), 20\u201333 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"21_CR103","doi-asserted-by":"crossref","first-page":"202","DOI":"10.3758\/BF03200774","volume":"1","author":"JM Wolfe","year":"1994","unstructured":"Wolfe, J.M.: Guided search 2.0 a revised model of visual search. Psychon. Bull. Rev. 1(2), 202\u2013238 (1994)","journal-title":"Psychon. Bull. Rev."},{"key":"21_CR104","doi-asserted-by":"crossref","unstructured":"Wu, X., Yuen, P.C., Liu, C., Huang, J.: Shot boundary detection: an information saliency approach. In: 2008 Congress on Image and Signal Processing, vol. 2, pp. 808\u2013812. IEEE (2008)","DOI":"10.1109\/CISP.2008.122"},{"issue":"1","key":"21_CR105","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1109\/JSTSP.2020.2966864","volume":"14","author":"M Xu","year":"2020","unstructured":"Xu, M., Li, C., Zhang, S., Le Callet, P.: State-of-the-art in 360 video\/image processing: perception, assessment and compression. IEEE J. Sel. Top. Signal Process. 14(1), 5\u201326 (2020)","journal-title":"IEEE J. Sel. Top. Signal Process."},{"issue":"11","key":"21_CR106","doi-asserted-by":"crossref","first-page":"2693","DOI":"10.1109\/TPAMI.2018.2858783","volume":"41","author":"M Xu","year":"2018","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 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR107","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: Gaze prediction in dynamic 360 immersive videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5333\u20135342 (2018)","DOI":"10.1109\/CVPR.2018.00559"},{"key":"21_CR108","doi-asserted-by":"crossref","unstructured":"Zhang, J., Sclaroff, S.: Saliency detection: a boolean map approach. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 153\u2013160 (2013)","DOI":"10.1109\/ICCV.2013.26"},{"issue":"12","key":"21_CR109","doi-asserted-by":"crossref","first-page":"3544","DOI":"10.1109\/TCSVT.2018.2883305","volume":"29","author":"K Zhang","year":"2018","unstructured":"Zhang, K., Chen, Z.: Video saliency prediction based on spatial-temporal two-stream network. IEEE Trans. Circ. Syst. Video Technol. 29(12), 3544\u20133557 (2018)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"issue":"7","key":"21_CR110","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1167\/8.7.32","volume":"8","author":"L Zhang","year":"2008","unstructured":"Zhang, L., Tong, M.H., Marks, T.K., Shan, H., Cottrell, G.W.: SUN: a Bayesian framework for saliency using natural statistics. J. Vis. 8(7), 32 (2008)","journal-title":"J. Vis."},{"key":"21_CR111","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Xu, Y., Yu, J., Gao, S.: Saliency detection in 360 videos. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 488\u2013503 (2018)","DOI":"10.1007\/978-3-030-01234-2_30"}],"container-title":["Communications in Computer and Information Science","Computer Vision, Imaging and Computer Graphics Theory and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-94893-1_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T19:03:04Z","timestamp":1726513384000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-94893-1_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783030948924","9783030948931"],"references-count":111,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-94893-1_21","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"22 January 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"VISIGRAPP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Joint Conference on Computer Vision, Imaging and Computer Graphics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Valletta","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malta","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":"27 February 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 February 2020","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":"visigrapp2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.visigrapp.org\/?y=2020","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":"PRIMORIS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"455","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":"25","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":"5% - 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":"4","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}