{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T15:32:17Z","timestamp":1760369537855,"version":"3.37.3"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030298876"},{"type":"electronic","value":"9783030298883"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-29888-3_25","type":"book-chapter","created":{"date-parts":[[2019,8,22]],"date-time":"2019-08-22T23:12:33Z","timestamp":1566515553000},"page":"311-323","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["How Well Current Saliency Prediction Models Perform on UAVs Videos?"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4210-9517","authenticated-orcid":false,"given":"Anne-Flore","family":"Perrin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8859-5453","authenticated-orcid":false,"given":"Lu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9883-0296","authenticated-orcid":false,"given":"Olivier","family":"Le Meur","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,8,22]]},"reference":[{"issue":"7","key":"25_CR1","doi-asserted-by":"publisher","first-page":"1688","DOI":"10.1109\/TMM.2017.2777665","volume":"20","author":"C Bak","year":"2018","unstructured":"Bak, C., Kocak, A., Erdem, E., Erdem, A.: Spatio-temporal saliency networks for dynamic saliency prediction. IEEE Trans. Multimedia 20(7), 1688\u20131698 (2018)","journal-title":"IEEE Trans. Multimedia"},{"key":"25_CR2","unstructured":"Bazzani, L., Larochelle, H., Torresani, L.: Recurrent mixture density network for spatiotemporal visual attention. arXiv preprint arXiv:1603.08199 (2016)"},{"key":"25_CR3","unstructured":"Borji, A.: Saliency prediction in the deep learning era: an empirical investigation. arXiv preprint arXiv:1810.03716 (2018)"},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Bruckert, A., Tavakoli, H.R., Liu, Z., Christie, M., Meur, O.L.: Deep saliency models: the quest for the loss function. arXiv preprint arXiv:1907.02336 (2019)","DOI":"10.1016\/j.neucom.2020.06.131"},{"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 Trans. Pattern Anal. Mach. Intell. 41(3), 740\u2013757 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR6","unstructured":"Bylinskii, Z., et al.: MIT saliency benchmark (2015)"},{"key":"25_CR7","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":"25_CR8","doi-asserted-by":"crossref","unstructured":"Jain, S.D., Xiong, B., Grauman, K.: FusionSeg: learning to combine motion and appearance for fully automatic segmentation of generic objects in videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3664\u20133673 (2017)","DOI":"10.1109\/CVPR.2017.228"},{"issue":"9","key":"25_CR9","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.: Video saliency incorporating spatiotemporal cues and uncertainty weighting. IEEE Trans. Image Process. 23(9), 3910\u20133921 (2014)","journal-title":"IEEE Trans. Image Process."},{"issue":"17","key":"25_CR10","doi-asserted-by":"publisher","first-page":"1777","DOI":"10.1016\/j.visres.2008.05.018","volume":"48","author":"T Foulsham","year":"2008","unstructured":"Foulsham, T., Kingstone, A., Underwood, G.: Turning the world around: patterns in saccade direction vary with picture orientation. Vis. Res. 48(17), 1777\u20131790 (2008)","journal-title":"Vis. Res."},{"issue":"1","key":"25_CR11","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.: A novel multiresolution spatiotemporal saliency detection model and its applications in image and video compression. IEEE Trans. Image Process. 19(1), 185\u2013198 (2010)","journal-title":"IEEE Trans. Image Process."},{"key":"25_CR12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00114-8_55","volume-title":"Systems Engineering in Context","author":"X Guo","year":"2019","unstructured":"Guo, X., Cui, L., Park, B., Ding, W., Lockhart, M., Kim, I.: How will humans cut through automated vehicle platoons in mixed traffic environments? A simulation study of drivers\u2019 gaze behaviors based on the dynamic areas-of-interest. In: Adams, S., Beling, P., Lambert, J., Scherer, W., Fleming, C. (eds.) Systems Engineering in Context. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-00114-8_55"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Harel, J., Koch, C., Perona, P.: Graph-based visual saliency. In: Advances in Neural Information Processing Systems, pp. 545\u2013552 (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: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015","DOI":"10.1109\/CVPR.2015.7299189"},{"issue":"1","key":"25_CR15","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1109\/TPAMI.2011.146","volume":"34","author":"X Hou","year":"2012","unstructured":"Hou, X., Harel, J., Koch, C.: Image signature: highlighting sparse salient regions. IEEE Trans. Pattern Anal. Mach. Intell. 34(1), 194\u2013201 (2012). https:\/\/doi.org\/10.1109\/TPAMI.2011.146","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR16","first-page":"77","volume":"6","author":"IP Howard","year":"2002","unstructured":"Howard, I.P., Rogers, B.: Depth perception. Stevens Handb. Exp. Psychol. 6, 77\u2013120 (2002)","journal-title":"Stevens Handb. Exp. Psychol."},{"key":"25_CR17","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":"11","key":"25_CR18","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 Trans. Pattern Anal. Mach. Intell. 20(11), 1254\u20131259 (1998)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR19","doi-asserted-by":"crossref","unstructured":"Jia, Y., et al.: Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM International Conference on Multimedia, MM 2014, pp. 675\u2013678. ACM (2014)","DOI":"10.1145\/2647868.2654889"},{"key":"25_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1007\/978-3-030-01264-9_37","volume-title":"Computer Vision \u2013 ECCV 2018","author":"L Jiang","year":"2018","unstructured":"Jiang, L., Xu, M., Liu, T., Qiao, M., Wang, Z.: DeepVS: a deep learning based video saliency prediction approach. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11218, pp. 625\u2013642. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_37"},{"key":"25_CR21","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"},{"key":"25_CR22","unstructured":"Kim, D.K., Chen, T.: Deep neural network for real-time autonomous indoor navigation. arXiv preprint arXiv:1511.04668 (2015)"},{"key":"25_CR23","doi-asserted-by":"publisher","unstructured":"Krassanakis, V., Filippakopoulou, V., Nakos, B.: EyeMMV toolbox: an eye movement post-analysis tool based on a two-step spatial dispersion threshold for fixation identification. J. Eye Mov. Res. 7(1) (2014). https:\/\/doi.org\/10.16910\/jemr.7.1.1","DOI":"10.16910\/jemr.7.1.1"},{"issue":"4","key":"25_CR24","doi-asserted-by":"publisher","first-page":"36","DOI":"10.3390\/drones2040036","volume":"2","author":"V Krassanakis","year":"2018","unstructured":"Krassanakis, V., Perreira Da Silva, M., Ricordel, V.: Monitoring human visual behavior during the observation of unmanned aerial vehicles (UAVs) videos. Drones 2(4), 36 (2018)","journal-title":"Drones"},{"key":"25_CR25","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 25, pp. 1097\u20131105. Curran Associates, Inc. (2012)"},{"key":"25_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"798","DOI":"10.1007\/978-3-030-01270-0_47","volume-title":"Computer Vision \u2013 ECCV 2018","author":"M K\u00fcmmerer","year":"2018","unstructured":"K\u00fcmmerer, M., Wallis, T.S.A., Bethge, M.: Saliency benchmarking made easy: separating models, maps and metrics. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11220, pp. 798\u2013814. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01270-0_47"},{"issue":"1","key":"25_CR27","doi-asserted-by":"publisher","first-page":"251","DOI":"10.3758\/s13428-012-0226-9","volume":"45","author":"O Meur Le","year":"2013","unstructured":"Le Meur, O., Baccino, T.: Methods for comparing scanpaths and saliency maps: strengths and weaknesses. Behav. Res. Method 45(1), 251\u2013266 (2013)","journal-title":"Behav. Res. Method"},{"issue":"19","key":"25_CR28","doi-asserted-by":"publisher","first-page":"2483","DOI":"10.1016\/j.visres.2007.06.015","volume":"47","author":"O Meur Le","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."},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"Li, G., Xie, Y., Wei, T., Wang, K., Lin, L.: Flow guided recurrent neural encoder for video salient object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3243\u20133252 (2018)","DOI":"10.1109\/CVPR.2018.00342"},{"key":"25_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1007\/978-3-319-46448-0_27","volume-title":"Computer Vision \u2013 ECCV 2016","author":"M Mueller","year":"2016","unstructured":"Mueller, M., Smith, N., Ghanem, B.: A benchmark and simulator for UAV tracking. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 445\u2013461. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_27"},{"key":"25_CR31","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, June 2011","DOI":"10.1109\/CVPR.2011.5995506"},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Ninassi, A., Le Meur, O., Le Callet, P., Barba, D.: Does where you gaze on an image affect your perception of quality? Applying visual attention to image quality metric. In: 2007 IEEE International Conference on Image Processing, vol. 2, p. II-169. IEEE (2007)","DOI":"10.1109\/ICIP.2007.4379119"},{"key":"25_CR33","unstructured":"Pan, J., et al.: SalGAN: visual saliency prediction with generative adversarial networks. arXiv preprint arXiv:1701.01081 (2017)"},{"key":"25_CR34","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"},{"issue":"6","key":"25_CR35","doi-asserted-by":"publisher","first-page":"642","DOI":"10.1016\/j.image.2013.03.009","volume":"28","author":"N Riche","year":"2013","unstructured":"Riche, N., Mancas, M., Duvinage, M., Mibulumukini, M., Gosselin, B., Dutoit, T.: RARE2012: a multi-scale rarity-based saliency detection with its comparative statistical analysis. Signal Process. Image Commun. 28(6), 642\u2013658 (2013)","journal-title":"Signal Process. Image Commun."},{"key":"25_CR36","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"},{"key":"25_CR37","unstructured":"Sokalski, J., Breckon, T.P., Cowling, I.: Automatic salient object detection in UAV imagery. In: Proceedings of the 25th International Unmanned Air Vehicle Systems, pp. 1\u201312 (2010)"},{"key":"25_CR38","unstructured":"Trinh, H., Li, J., Miyazawa, S., Moreno, J., Pankanti, S.: Efficient UAV video event summarization. In: Proceedings of the 21st International Conference on Pattern Recognition (ICPR 2012), pp. 2226\u20132229. IEEE (2012)"},{"issue":"7","key":"25_CR39","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1167\/9.7.4","volume":"9","author":"PH Tseng","year":"2009","unstructured":"Tseng, P.H., Carmi, R., Cameron, I.G., Munoz, D.P., Itti, L.: Quantifying center bias of observers in free viewing of dynamic natural scenes. J. Vis. 9(7), 4 (2009)","journal-title":"J. Vis."},{"key":"25_CR40","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":"25_CR41","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1016\/j.neucom.2018.01.076","volume":"287","author":"Z Wang","year":"2018","unstructured":"Wang, Z., Ren, J., Zhang, D., Sun, M., Jiang, J.: A deep-learning based feature hybrid framework for spatiotemporal saliency detection inside videos. Neurocomputing 287, 68\u201383 (2018)","journal-title":"Neurocomputing"},{"issue":"5","key":"25_CR42","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.: Exploiting surroundedness for saliency detection: a boolean map approach. IEEE Trans. Pattern Anal. Mach. Intell. 38(5), 889\u2013902 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"7","key":"25_CR43","doi-asserted-by":"publisher","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."},{"issue":"3","key":"25_CR44","doi-asserted-by":"publisher","first-page":"712","DOI":"10.3390\/s18030712","volume":"18","author":"Y Zhao","year":"2018","unstructured":"Zhao, Y., Ma, J., Li, X., Zhang, J.: Saliency detection and deep learning-based wildfire identification in UAV imagery. Sensors 18(3), 712 (2018)","journal-title":"Sensors"}],"container-title":["Lecture Notes in Computer Science","Computer Analysis of Images and Patterns"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-29888-3_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,19]],"date-time":"2023-09-19T10:59:31Z","timestamp":1695121171000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-29888-3_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030298876","9783030298883"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-29888-3_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"22 August 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CAIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computer Analysis of Images and Patterns","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Salerno","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"caip2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/caip2019.unisa.it\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"176","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":"106","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":"60% - 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":"2.68","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.40","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)"}}]}}