{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T05:31:48Z","timestamp":1773725508891,"version":"3.50.1"},"reference-count":87,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,8,28]],"date-time":"2020-08-28T00:00:00Z","timestamp":1598572800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,8,28]],"date-time":"2020-08-28T00:00:00Z","timestamp":1598572800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["61573037"],"award-info":[{"award-number":["61573037"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["61922009"],"award-info":[{"award-number":["61922009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["61876013"],"award-info":[{"award-number":["61876013"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2021,1]]},"DOI":"10.1007\/s11263-020-01371-6","type":"journal-article","created":{"date-parts":[[2020,8,28]],"date-time":"2020-08-28T04:25:17Z","timestamp":1598588717000},"page":"203-224","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["DeepVS2.0: A Saliency-Structured Deep Learning Method for Predicting Dynamic Visual Attention"],"prefix":"10.1007","volume":"129","author":[{"given":"Lai","family":"Jiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0277-3301","authenticated-orcid":false,"given":"Mai","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zulin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leonid","family":"Sigal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,8,28]]},"reference":[{"key":"1371_CR1","doi-asserted-by":"crossref","unstructured":"Alers, H., Redi J. A., & Heynderickx, I. (2012). Examining the effect of task on viewing behavior in videos using saliency maps. In IS&T\/SPIE Electronic Imaging, International Society for Optics and Photonics (pp. 82910X\u201382910X).","DOI":"10.1117\/12.907373"},{"key":"1371_CR2","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. (2017). Spatio-temporal saliency networks for dynamic saliency prediction. IEEE Transactions on Multimedia, 20, 1688\u20131698.","journal-title":"IEEE Transactions on Multimedia"},{"key":"1371_CR3","unstructured":"Bazzani, L., Larochelle, H., & Torresani, L. (2017). Recurrent mixture density network for spatiotemporal visual attention."},{"issue":"1","key":"1371_CR4","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1109\/TPAMI.2012.89","volume":"35","author":"A Borji","year":"2013","unstructured":"Borji, A., & Itti, L. (2013). State-of-the-art in visual attention modeling. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(1), 185\u2013207.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1371_CR5","doi-asserted-by":"crossref","unstructured":"Boulos, F., Chen, W., Parrein, B., & Le\u00a0Callet, P. (2009). Region-of-interest intra prediction for h. 264\/AVC error resilience. In ICIP, IEEE (pp. 3109\u20133112).","DOI":"10.1109\/ICIP.2009.5414458"},{"issue":"3","key":"1371_CR6","doi-asserted-by":"publisher","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. (2018). What do different evaluation metrics tell us about saliency models? IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(3), 740\u2013757.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"26","key":"1371_CR7","doi-asserted-by":"publisher","first-page":"4333","DOI":"10.1016\/j.visres.2006.08.019","volume":"46","author":"R Carmi","year":"2006","unstructured":"Carmi, R., & Itti, L. (2006). Visual causes versus correlates of attentional selection in dynamic scenes. Vision Research, 46(26), 4333\u20134345.","journal-title":"Vision Research"},{"key":"1371_CR8","doi-asserted-by":"crossref","unstructured":"Chaabouni, S., Benois-Pineau, J., & Amar, C.B. (2016) Transfer learning with deep networks for saliency prediction in natural video. In: ICIP, IEEE, pp 1604\u20131608.","DOI":"10.1109\/ICIP.2016.7532629"},{"issue":"3","key":"1371_CR9","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1109\/TPAMI.2014.2345401","volume":"37","author":"MM Cheng","year":"2015","unstructured":"Cheng, M. M., Mitra, N. J., Huang, X., Torr, P. H., & Hu, S. M. (2015). Global contrast based salient region detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(3), 569\u2013582.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1371_CR10","doi-asserted-by":"crossref","unstructured":"Cornia, M., Baraldi, L., Serra, G., & Cucchiara, R. (2018). SAM: Pushing the limits of saliency prediction models. In Proceedings of the IEEE\/CVF international conference on computer vision and pattern recognition workshops.","DOI":"10.1109\/CVPRW.2018.00250"},{"key":"1371_CR11","doi-asserted-by":"crossref","unstructured":"Coutrot, A., & Guyader, N. (2013). Toward the introduction of auditory information in dynamic visual attention models. In 2013 14th international workshop on image analysis for multimedia interactive services (WIAMIS), IEEE (pp 1\u20134).","DOI":"10.1109\/WIAMIS.2013.6616164"},{"key":"1371_CR12","doi-asserted-by":"crossref","unstructured":"Coutrot, A., & Guyader, N. (2015). An efficient audiovisual saliency model to predict eye positions when looking at conversations. In 23rd European signal processing conference (EUSIPCO), IEEE (pp. 1531\u20131535).","DOI":"10.1109\/EUSIPCO.2015.7362640"},{"issue":"10","key":"1371_CR13","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1167\/10.10.28","volume":"10","author":"M Dorr","year":"2010","unstructured":"Dorr, M., Martinetz, T., Gegenfurtner, K. R., & Barth, E. (2010). Variability of eye movements when viewing dynamic natural scenes. Journal of vision, 10(10), 28\u201328.","journal-title":"Journal of vision"},{"key":"1371_CR14","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., Fischer, P., Ilg, E., Hausser, P., Hazirbas, C., Golkov, V., van der Smagt, P., Cremers, D., & Brox, T. (2015). Flownet: Learning optical flow with convolutional networks. In ICCV (pp. 2758\u20132766).","DOI":"10.1109\/ICCV.2015.316"},{"key":"1371_CR15","unstructured":"Du, Y., Wang, W., & Wang, L. (2015). Hierarchical recurrent neural network for skeleton based action recognition. In CVPR (pp. 1110\u20131118)."},{"issue":"1","key":"1371_CR16","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1109\/TCSVT.2013.2273613","volume":"24","author":"Y Fang","year":"2014","unstructured":"Fang, Y., Lin, W., Chen, Z., Tsai, C. M., & Lin, C. W. (2014a). A video saliency detection model in compressed domain. IEEE Transactions on Circuits and Systems for Video Technology, 24(1), 27\u201338.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"9","key":"1371_CR17","doi-asserted-by":"publisher","first-page":"3910","DOI":"10.1109\/TIP.2014.2336549","volume":"23","author":"Y Fang","year":"2014","unstructured":"Fang, Y., Wang, Z., Lin, W., & Fang, Z. (2014b). Video saliency incorporating spatiotemporal cues and uncertainty weighting. IEEE Transactions on Image Processing, 23(9), 3910\u20133921.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1371_CR18","doi-asserted-by":"crossref","unstructured":"Fu, J., Liu, J., Tian, H., Li, Y., Bao, Y., Fang, Z., & Lu, H. (2019). Dual attention network for scene segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3146\u20133154).","DOI":"10.1109\/CVPR.2019.00326"},{"key":"1371_CR19","unstructured":"Gal, Y., & Ghahramani, Z. (2016). A theoretically grounded application of dropout in recurrent neural networks. In: NIPS (pp. 1019\u20131027)."},{"key":"1371_CR20","doi-asserted-by":"crossref","unstructured":"Gitman, Y., Erofeev, M., Vatolin, D., & Andrey, B. (2014). Semiautomatic visual-attention modeling and its application to video compression. In ICIP, IEEE (pp. 1105\u20131109).","DOI":"10.1109\/ICIP.2014.7025220"},{"key":"1371_CR21","unstructured":"Glorot, X., & Bengio, Y. (2010). Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the thirteenth international conference on artificial intelligence and statistics (pp. 249\u2013256)."},{"issue":"10","key":"1371_CR22","doi-asserted-by":"publisher","first-page":"1915","DOI":"10.1109\/TPAMI.2011.272","volume":"34","author":"S Goferman","year":"2012","unstructured":"Goferman, S., Zelnik-Manor, L., & Tal, A. (2012). Context-aware saliency detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(10), 1915\u20131926.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"1","key":"1371_CR23","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1109\/TIP.2009.2030969","volume":"19","author":"C Guo","year":"2010","unstructured":"Guo, C., & Zhang, L. (2010). A novel multiresolution spatiotemporal saliency detection model and its applications in image and video compression. IEEE Transactions on Image Processing, 19(1), 185\u2013198.","journal-title":"IEEE Transactions on Image Processing"},{"issue":"2","key":"1371_CR24","doi-asserted-by":"publisher","first-page":"898","DOI":"10.1109\/TIP.2011.2165292","volume":"21","author":"H Hadizadeh","year":"2012","unstructured":"Hadizadeh, H., Enriquez, M. J., & Bajic, I. V. (2012). Eye-tracking database for a set of standard video sequences. IEEE Transactions on Image Processing, 21(2), 898\u2013903.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1371_CR25","unstructured":"Harel, J., Koch, C., & Perona, P. (2006). Graph-based visual saliency. In NIPS (pp. 545\u2013552)."},{"key":"1371_CR26","volume-title":"Eye tracking: A comprehensive guide to methods and measures","author":"K Holmqvist","year":"2011","unstructured":"Holmqvist, K., Nystr\u00f6m, M., Andersson, R., Dewhurst, R., Jarodzka, H., & Van de Weijer, J. (2011). Eye tracking: A comprehensive guide to methods and measures. Oxford: OUP."},{"key":"1371_CR27","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., & Sun, G. (2018). Squeeze-and-excitation networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7132\u20137141).","DOI":"10.1109\/CVPR.2018.00745"},{"key":"1371_CR28","doi-asserted-by":"crossref","unstructured":"Huang, X., Shen, C., Boix, X., & Zhao, Q. (2015). Salicon: Reducing the semantic gap in saliency prediction by adapting deep neural networks. In ICCV (pp. 262\u2013270).","DOI":"10.1109\/ICCV.2015.38"},{"issue":"8","key":"1371_CR29","doi-asserted-by":"publisher","first-page":"1336","DOI":"10.1109\/TCSVT.2014.2308652","volume":"24","author":"CR Huang","year":"2014","unstructured":"Huang, C. R., Chang, Y. J., Yang, Z. X., & Lin, Y. Y. (2014). Video saliency map detection by dominant camera motion removal. IEEE Transactions on Circuits and Systems for Video Technology, 24(8), 1336\u20131349.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"1371_CR30","doi-asserted-by":"crossref","unstructured":"Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., & Brox, T. (2017). Flownet 2.0: Evolution of optical flow estimation with deep networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2462\u20132470).","DOI":"10.1109\/CVPR.2017.179"},{"issue":"10","key":"1371_CR31","doi-asserted-by":"publisher","first-page":"1304","DOI":"10.1109\/TIP.2004.834657","volume":"13","author":"L Itti","year":"2004","unstructured":"Itti, L. (2004). Automatic foveation for video compression using a neurobiological model of visual attention. IEEE Transactions on Image Processing, 13(10), 1304\u20131318.","journal-title":"IEEE Transactions on Image Processing"},{"issue":"10","key":"1371_CR32","doi-asserted-by":"publisher","first-page":"1295","DOI":"10.1016\/j.visres.2008.09.007","volume":"49","author":"L Itti","year":"2009","unstructured":"Itti, L., & Baldi, P. (2009). Bayesian surprise attracts human attention. Vision Research, 49(10), 1295\u20131306.","journal-title":"Vision Research"},{"key":"1371_CR33","first-page":"64","volume":"64","author":"L Itti","year":"2004","unstructured":"Itti, L., Dhavale, N., & Pighin, F. (2004). Realistic avatar eye and head animation using a neurobiological model of visual attention. Optical Science and Technology, 64, 64\u201378.","journal-title":"Optical Science and Technology"},{"issue":"11","key":"1371_CR34","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. (1998). A model of saliency-based visual attention for rapid scene analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(11), 1254\u20131259.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1371_CR35","doi-asserted-by":"crossref","unstructured":"Jiang, L., Xu, M., Liu, T., Qiao, M. & Wang, Z. (2018). Deepvs: A deep learning based video saliency prediction approach. In ECCV, Berlin: Springer.","DOI":"10.1007\/978-3-030-01264-9_37"},{"key":"1371_CR36","doi-asserted-by":"crossref","unstructured":"Jiang, L., Xu, M., Ye, Z., & Wang, Z. (2015). Image saliency detection with sparse representation of learnt texture atoms. In Proceedings of the IEEE international conference on computer vision workshops (pp. 54\u201362).","DOI":"10.1109\/ICCVW.2015.119"},{"key":"1371_CR37","doi-asserted-by":"crossref","unstructured":"Judd, T., Ehinger, K., Durand, F., & Torralba, A. (2009). Learning to predict where humans look. In ICCV (pp. 2106\u20132113).","DOI":"10.1109\/ICCV.2009.5459462"},{"key":"1371_CR38","doi-asserted-by":"crossref","unstructured":"Khatoonabadi, S. H., Vasconcelos, N., Bajic, I. V., & Shan, Y. (2015). How many bits does it take for a stimulus to be salient? In CVPR (pp. 5501\u20135510).","DOI":"10.1109\/CVPR.2015.7299189"},{"issue":"5","key":"1371_CR39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3131275","volume":"24","author":"NW Kim","year":"2017","unstructured":"Kim, N. W., Bylinskii, Z., Borkin, M. A., Gajos, K. Z., Oliva, A., Durand, F., et al. (2017). Bubbleview: an interface for crowdsourcing image importance maps and tracking visual attention. ACM Transactions on Computer-Human Interaction (TOCHI), 24(5), 1\u201340.","journal-title":"ACM Transactions on Computer-Human Interaction (TOCHI)"},{"key":"1371_CR40","unstructured":"Kingma, D., & Ba, J. (2015). Adam: A method for stochastic optimization."},{"key":"1371_CR41","doi-asserted-by":"publisher","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. (2017). Deepfix: A fully convolutional neural network for predicting human eye fixations. IEEE Transactions on Image Processing., 26, 4446\u20134456.","journal-title":"IEEE Transactions on Image Processing."},{"key":"1371_CR42","unstructured":"K\u00fcmmerer, M., Theis, L., & Bethge, M. (2014) Deep gaze i: Boosting saliency prediction with feature maps trained on imagenet. arXiv preprint arXiv:1411.1045."},{"key":"1371_CR43","unstructured":"Le, T. N., & Sugimoto, A. (2017). Video salient object detection using spatiotemporal deep features. arXiv preprint arXiv:1708.01447."},{"issue":"5","key":"1371_CR44","doi-asserted-by":"publisher","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. (2017). Dynamic whitening saliency. IEEE PAMI, 39(5), 893\u2013907.","journal-title":"IEEE PAMI"},{"key":"1371_CR45","doi-asserted-by":"crossref","unstructured":"Lee, S. H., Kim, J. H., Choi, K. P., Sim, J. Y., & Kim, C. S. (2014). Video saliency detection based on spatiotemporal feature learning. In ICIP (pp 1120\u20131124).","DOI":"10.1109\/ICIP.2014.7025223"},{"issue":"1","key":"1371_CR46","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.imavis.2010.07.001","volume":"29","author":"Z Li","year":"2011","unstructured":"Li, Z., Qin, S., & Itti, L. (2011). Visual attention guided bit allocation in video compression. Image and Vision Computing, 29(1), 1\u201314.","journal-title":"Image and Vision Computing"},{"issue":"2","key":"1371_CR47","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1007\/s11263-010-0354-6","volume":"90","author":"J Li","year":"2010","unstructured":"Li, J., Tian, Y., Huang, T., & Gao, W. (2010). Probabilistic multi-task learning for visual saliency estimation in video. International Journal of Computer Vision, 90(2), 150\u2013165.","journal-title":"International Journal of Computer Vision"},{"key":"1371_CR48","doi-asserted-by":"crossref","unstructured":"Liu, Y., Zhang, S., Xu, M., & He, X. (2017). Predicting salient face in multiple-face videos. In: CVPR.","DOI":"10.1109\/CVPR.2017.343"},{"issue":"2","key":"1371_CR49","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1109\/TPAMI.2010.70","volume":"33","author":"T Liu","year":"2011","unstructured":"Liu, T., Yuan, Z., Sun, J., Wang, J., Zheng, N., Tang, X., et al. (2011). Learning to detect a salient object. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(2), 353\u2013367.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"1","key":"1371_CR50","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1109\/TIP.2017.2762594","volume":"27","author":"J Li","year":"2018","unstructured":"Li, J., Xia, C., & Chen, X. (2018). A benchmark dataset and saliency-guided stacked autoencoders for video-based salient object detection. IEEE Transactions on Image Processing, 27(1), 349\u2013364.","journal-title":"IEEE Transactions on Image Processing"},{"issue":"8","key":"1371_CR51","doi-asserted-by":"publisher","first-page":"3919","DOI":"10.1109\/TIP.2016.2579306","volume":"25","author":"X Li","year":"2016","unstructured":"Li, X., Zhao, L., Wei, L., Yang, M. H., Wu, F., Zhuang, Y., et al. (2016). Deepsaliency: Multi-task deep neural network model for salient object detection. IEEE Transactions on Image Processing, 25(8), 3919\u20133930.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1371_CR52","volume-title":"Foundations of statistical natural language processing","author":"CD Manning","year":"1999","unstructured":"Manning, C. D., & Sch\u00fctze, H. (1999). Foundations of statistical natural language processing. Cambridge: MIT Press."},{"key":"1371_CR53","unstructured":"Marat, S., Guironnet, M., & Pellerin, D. (2007). Video summarization using a visual attention model. In Signal processing conference, IEEE (pp. 1784\u20131788)."},{"key":"1371_CR54","doi-asserted-by":"crossref","unstructured":"Marszalek, M., Laptev, I., & Schmid, C. (2009). Actions in context. In CVPR, IEEE (pp. 2929\u20132936).","DOI":"10.1109\/CVPRW.2009.5206557"},{"issue":"7","key":"1371_CR55","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. (2015). Actions in the eye: Dynamic gaze datasets and learnt saliency models for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(7), 1408\u20131424.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"12","key":"1371_CR56","doi-asserted-by":"publisher","first-page":"899","DOI":"10.1037\/h0037368","volume":"81","author":"E Matin","year":"1974","unstructured":"Matin, E. (1974). Saccadic suppression: A review and an analysis. Psychological Bulletin, 81(12), 899\u2013917.","journal-title":"Psychological Bulletin"},{"key":"1371_CR57","doi-asserted-by":"crossref","unstructured":"Mauthner, T., Possegger, H., Waltner, G., & Bischof, H. (2015). Encoding based saliency detection for videos and images. In: CVPR (pp. 2494\u20132502).","DOI":"10.1109\/CVPR.2015.7298864"},{"issue":"1","key":"1371_CR58","doi-asserted-by":"publisher","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. (2011). Clustering of gaze during dynamic scene viewing is predicted by motion. Cognitive Computation, 3(1), 5\u201324.","journal-title":"Cognitive Computation"},{"key":"1371_CR59","doi-asserted-by":"crossref","unstructured":"Nguyen, T.V., Xu, M., Gao, G., Kankanhalli, M., Tian, Q., & Yan, S. (2013). Static saliency vs. dynamic saliency: A comparative study. In: ACMM, ACM (pp. 987\u2013996).","DOI":"10.1145\/2502081.2502128"},{"key":"1371_CR60","volume-title":"The Tobii i-vt fixation filter","author":"A Olsen","year":"2012","unstructured":"Olsen, A. (2012). The Tobii i-vt fixation filter. Danderyd: Tobii Technology."},{"key":"1371_CR61","doi-asserted-by":"crossref","unstructured":"Palazzi, A., Solera, F., Calderara, S., Alletto, S., & Cucchiara, R. (2017). Learning where to attend like a human driver. Intelligent Vehicles Symposium (IV) (pp. 920\u2013925). IEEE: IEEE.","DOI":"10.1109\/IVS.2017.7995833"},{"key":"1371_CR62","unstructured":"Pan, J., Canton, C., McGuinness, K., O\u2019Connor, N.E., Torres, J., Sayrol, E., & Xa, G. N. (2017). Salgan: Visual saliency prediction with generative adversarial networks. In CVPR Workshop."},{"key":"1371_CR63","doi-asserted-by":"crossref","unstructured":"Pan, J., Sayrol, E., Giro-i Nieto, X., McGuinness, K., & O\u2019Connor, N. E. (2016). Shallow and deep convolutional networks for saliency prediction. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp 598\u2013606).","DOI":"10.1109\/CVPR.2016.71"},{"key":"1371_CR64","doi-asserted-by":"crossref","unstructured":"Peters, R.J., & Itti, L. (2007). Beyond bottom-up: Incorporating task-dependent influences into a computational model of spatial attention. In: CVPR, IEEE (pp. 1\u20138).","DOI":"10.1109\/CVPR.2007.383337"},{"issue":"4","key":"1371_CR65","doi-asserted-by":"publisher","first-page":"564","DOI":"10.1109\/TIP.2008.917218","volume":"17","author":"U Rajashekar","year":"2008","unstructured":"Rajashekar, U., van der Linde, I., Bovik, A. C., & Cormack, L. K. (2008). Gaffe: A gaze-attentive fixation finding engine. IEEE Transactions on Image Processing, 17(4), 564\u2013573.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1371_CR66","doi-asserted-by":"crossref","unstructured":"Redmon, J., & Farhadi, A. (2017). Yolo9000: Better, faster, stronger. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7263\u20137271).","DOI":"10.1109\/CVPR.2017.690"},{"key":"1371_CR67","unstructured":"Redmon, J., & Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767."},{"key":"1371_CR68","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. In: CVPR (pp. 779\u2013788).","DOI":"10.1109\/CVPR.2016.91"},{"issue":"8","key":"1371_CR69","doi-asserted-by":"publisher","first-page":"3120","DOI":"10.1109\/TIP.2013.2259837","volume":"22","author":"Z Ren","year":"2013","unstructured":"Ren, Z., Gao, S., Chia, L. T., & Rajan, D. (2013). Regularized feature reconstruction for spatio-temporal saliency detection. IEEE Transactions on Image Processing, 22(8), 3120\u20133132.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1371_CR70","doi-asserted-by":"crossref","unstructured":"Riche, N., Mancas, M., Culibrk, D., Crnojevic, V., Gosselin, B., & Dutoit, T. (2012). Dynamic saliency models and human attention: A comparative study on videos. In ACCV (pp. 586\u2013598), Berlin: Springer.","DOI":"10.1007\/978-3-642-37431-9_45"},{"key":"1371_CR71","volume-title":"Spatio-temporal maximum average correlation height templates in action recognition and video summarization","author":"M Rodriguez","year":"2010","unstructured":"Rodriguez, M. (2010). Spatio-temporal maximum average correlation height templates in action recognition and video summarization. Princeton: Citeseer."},{"key":"1371_CR72","doi-asserted-by":"crossref","unstructured":"Rudoy, D., Goldman, D. B., Shechtman, E., & Zelnik-Manor, L. (2013) Learning video saliency from human gaze using candidate selection. In CVPR (pp. 1147\u20131154).","DOI":"10.1109\/CVPR.2013.152"},{"key":"1371_CR73","unstructured":"Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556."},{"key":"1371_CR74","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015). Going deeper with convolutions. In CVPR (pp. 1\u20139).","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"1371_CR75","unstructured":"Tobii I TECHNOLOGY (2017). Tobii tx300 eye tracker. Retrieved July, 2018, from http:\/\/www.tobiipro.com\/product-listing\/tobii-pro-tx300\/."},{"key":"1371_CR76","doi-asserted-by":"crossref","unstructured":"Wang, W., Shen, J, Guo, F., Cheng, M. M., & Borji, A. (2018). Revisiting video saliency: A large-scale benchmark and a new model. In CVPR.","DOI":"10.1109\/CVPR.2018.00514"},{"key":"1371_CR77","doi-asserted-by":"crossref","unstructured":"Wang, L., Wang, L., Lu, H., Zhang, P., & Ruan, X. (2016a) Saliency detection with recurrent fully convolutional networks. In: ECCV (pp. 825\u2013841). Berlin: Springer.","DOI":"10.1007\/978-3-319-46493-0_50"},{"key":"1371_CR78","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhang, Q., & Li, B. (2016b). Efficient unsupervised abnormal crowd activity detection based on a spatiotemporal saliency detector. In WACV, IEEE (pp. 1\u20139).","DOI":"10.1109\/WACV.2016.7477684"},{"issue":"5","key":"1371_CR79","doi-asserted-by":"publisher","first-page":"2368","DOI":"10.1109\/TIP.2017.2787612","volume":"27","author":"W Wang","year":"2018","unstructured":"Wang, W., & Shen, J. (2018). Deep visual attention prediction. IEEE Transactions on Image Processing, 27(5), 2368\u20132378.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1371_CR80","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1109\/TIP.2017.2754941","volume":"27","author":"W Wang","year":"2017","unstructured":"Wang, W., Shen, J., & Shao, L. (2017). Video salient object detection via fully convolutional networks. IEEE Transactions on Image Processing., 27, 38\u201349.","journal-title":"IEEE Transactions on Image Processing."},{"key":"1371_CR81","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., & Kweon, I.S. (2018). Cbam: Convolutional block attention module. In Proceedings of the European conference on computer vision (ECCV) (pp. 3\u201319).","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"1371_CR82","unstructured":"Xingjian, S., Chen, Z., Wang, H., Yeung, D.Y., Wong, W.K., & Woo, W.c. (2015). Convolutional lstm network: A machine learning approach for precipitation nowcasting. In NIPS (pp. 802\u2013810)."},{"issue":"1","key":"1371_CR83","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1109\/TIP.2016.2628583","volume":"26","author":"M Xu","year":"2017","unstructured":"Xu, M., Jiang, L., Sun, X., Ye, Z., & Wang, Z. (2017). Learning to detect video saliency with hevc features. IEEE Transactions on Image Processing, 26(1), 369\u2013385.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1371_CR84","unstructured":"Zhang, L., Tong, M. H., & Cottrell, G. W. (2009). Sunday: Saliency using natural statistics for dynamic analysis of scenes. In Annual cognitive science conference (pp. 2944\u20132949)."},{"issue":"5","key":"1371_CR85","doi-asserted-by":"publisher","first-page":"889","DOI":"10.1109\/TPAMI.2015.2473844","volume":"38","author":"J Zhang","year":"2016","unstructured":"Zhang, J., & Sclaroff, S. (2016). Exploiting surroundedness for saliency detection: A boolean map approach. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(5), 889\u2013902.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1371_CR86","doi-asserted-by":"crossref","unstructured":"Zhong, S. H., Liu, Y., Ren, F., Zhang, J., & Ren, T. (2013). Video saliency detection via dynamic consistent spatio-temporal attention modelling. In AAAI.","DOI":"10.1609\/aaai.v27i1.8642"},{"key":"1371_CR87","doi-asserted-by":"crossref","unstructured":"Zhou, F., Kang, S. B., & Cohen, M. F. (2014). Time-mapping using space-time saliency. In CVPR (pp. 3358\u20133365).","DOI":"10.1109\/CVPR.2014.429"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01371-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-020-01371-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01371-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T15:29:22Z","timestamp":1668094162000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-020-01371-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,28]]},"references-count":87,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["1371"],"URL":"https:\/\/doi.org\/10.1007\/s11263-020-01371-6","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,8,28]]},"assertion":[{"value":"30 July 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 August 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 August 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}