{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T19:33:44Z","timestamp":1785699224331,"version":"3.56.0"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030208929","type":"print"},{"value":"9783030208936","type":"electronic"}],"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\/978-3-030-20893-6_3","type":"book-chapter","created":{"date-parts":[[2019,5,28]],"date-time":"2019-05-28T03:25:52Z","timestamp":1559013952000},"page":"35-50","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":73,"title":["Believe It or Not, We Know What You Are Looking At!"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4947-0316","authenticated-orcid":false,"given":"Dongze","family":"Lian","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6559-9830","authenticated-orcid":false,"given":"Zehao","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1626-2040","authenticated-orcid":false,"given":"Shenghua","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,5,29]]},"reference":[{"key":"3_CR1","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, CVPR 2009, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"2","key":"3_CR2","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The Pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88(2), 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vis."},{"key":"3_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1007\/978-3-642-33718-5_23","volume-title":"Computer Vision \u2013 ECCV 2012","author":"A Fathi","year":"2012","unstructured":"Fathi, A., Li, Y., Rehg, J.M.: Learning to recognize daily actions using gaze. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7572, pp. 314\u2013327. Springer, Heidelberg (2012). \n                      https:\/\/doi.org\/10.1007\/978-3-642-33718-5_23"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Fragkiadaki, K., Levine, S., Felsen, P., Malik, J.: Recurrent network models for human dynamics. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 4346\u20134354. IEEE (2015)","DOI":"10.1109\/ICCV.2015.494"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Hennessey, C., Noureddin, B., Lawrence, P.: A single camera eye-gaze tracking system with free head motion. In: Proceedings of the 2006 Symposium on Eye Tracking Research & Applications, pp. 87\u201394. ACM (2006)","DOI":"10.1145\/1117309.1117349"},{"issue":"3","key":"3_CR7","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1038\/35058500","volume":"2","author":"L Itti","year":"2001","unstructured":"Itti, L., Koch, C.: Computational modelling of visual attention. Nat. Rev. Neurosci. 2(3), 194 (2001)","journal-title":"Nat. Rev. Neurosci."},{"issue":"11","key":"3_CR8","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":"3_CR9","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":"3_CR10","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint \n                      arXiv:1412.6980\n                      \n                     (2014)"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Krafka, K., et al.: Eye tracking for everyone. arXiv preprint \n                      arXiv:1606.05814\n                      \n                     (2016)","DOI":"10.1109\/CVPR.2016.239"},{"key":"3_CR12","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"3_CR13","unstructured":"K\u00fcmmerer, M., Theis, L., Bethge, M.: Deep gaze I: boosting saliency prediction with feature maps trained on imagenet. arXiv preprint \n                      arXiv:1411.1045\n                      \n                     (2014)"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Leifman, G., Rudoy, D., Swedish, T., Bayro-Corrochano, E., Raskar, R.: Learning gaze transitions from depth to improve video saliency estimation. In: Proceedings of IEEE International Conference on Computer Vision, vol. 3 (2017)","DOI":"10.1109\/ICCV.2017.188"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR, vol. 1, p. 4 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"3_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). \n                      https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"issue":"3","key":"3_CR17","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/s11263-013-0655-7","volume":"106","author":"MJ Mar\u00edn-Jim\u00e9nez","year":"2014","unstructured":"Mar\u00edn-Jim\u00e9nez, M.J., Zisserman, A., Eichner, M., Ferrari, V.: Detecting people looking at each other in videos. Int. J. Comput. Vis. 106(3), 282\u2013296 (2014)","journal-title":"Int. J. Comput. Vis."},{"issue":"11","key":"3_CR18","doi-asserted-by":"publisher","first-page":"2094","DOI":"10.1109\/TMM.2015.2482819","volume":"17","author":"SS Mukherjee","year":"2015","unstructured":"Mukherjee, S.S., Robertson, N.M.: Deep head pose: gaze-direction estimation in multimodal video. IEEE Trans. Multimed. 17(11), 2094\u20132107 (2015)","journal-title":"IEEE Trans. Multimed."},{"key":"3_CR19","unstructured":"Pan, J., et al.: SaLGAN: visual saliency prediction with generative adversarial networks. arXiv preprint \n                      arXiv:1701.01081\n                      \n                     (2017)"},{"key":"3_CR20","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1016\/j.visres.2014.10.027","volume":"116","author":"D Parks","year":"2015","unstructured":"Parks, D., Borji, A., Itti, L.: Augmented saliency model using automatic 3d head pose detection and learned gaze following in natural scenes. Vis. Res. 116, 113\u2013126 (2015)","journal-title":"Vis. Res."},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Pfister, T., Charles, J., Zisserman, A.: Flowing convnets for human pose estimation in videos. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1913\u20131921 (2015)","DOI":"10.1109\/ICCV.2015.222"},{"key":"3_CR22","unstructured":"Recasens\n                      \n                        \n                      \n                      $$^*$$\n                    , A., Khosla\n                      \n                        \n                      \n                      $$^*$$\n                    , A., Vondrick, C., Torralba, A.: Where are they looking? In: Advances in Neural Information Processing Systems (NIPS) (2015). \n                      \n                        \n                      \n                      $$^*$$\n                     indicates equal contribution"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Recasens, A., Vondrick, C., Khosla, A., Torralba, A.: Following gaze in video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1435\u20131443 (2017)","DOI":"10.1109\/ICCV.2017.160"},{"issue":"3","key":"3_CR24","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"3_CR25","unstructured":"Tompson, J.J., Jain, A., LeCun, Y., Bregler, C.: Joint training of a convolutional network and a graphical model for human pose estimation. In: Advances in Neural Information Processing Systems, pp. 1799\u20131807 (2014)"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Xiao, J., Hays, J., Ehinger, K.A., Oliva, A., Torralba, A.: Sun database: large-scale scene recognition from abbey to zoo. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3485\u20133492. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Xiong, X., Liu, Z., Cai, Q., Zhang, Z.: Eye gaze tracking using an RGBD camera: a comparison with a RGB solution. In: Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing: Adjunct Publication, pp. 1113\u20131121. ACM (2014)","DOI":"10.1145\/2638728.2641694"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Yao, B., Jiang, X., Khosla, A., Lin, A.L., Guibas, L., Fei-Fei, L.: Human action recognition by learning bases of action attributes and parts. In: 2011 IEEE International Conference on Computer Vision (ICCV), pp. 1331\u20131338. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126386"},{"key":"3_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, X., Sugano, Y., Fritz, M., Bulling, A.: Appearance-based gaze estimation in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4511\u20134520 (2015)","DOI":"10.1109\/CVPR.2015.7299081"},{"key":"3_CR30","unstructured":"Zhou, B., Lapedriza, A., Xiao, J., Torralba, A., Oliva, A.: Learning deep features for scene recognition using places database. In: Advances in Neural Information Processing Systems, pp. 487\u2013495 (2014)"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Zhu, W., Deng, H.: Monocular free-head 3D gaze tracking with deep learning and geometry constraints. In: The IEEE International Conference on Computer Vision (ICCV), October 2017","DOI":"10.1109\/ICCV.2017.341"},{"key":"3_CR32","unstructured":"Zhu, X., Ramanan, D.: Face detection, pose estimation, and landmark localization in the wild. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2879\u20132886. IEEE (2012)"},{"key":"3_CR33","unstructured":"Zhu, Z., Ji, Q.: Eye gaze tracking under natural head movements. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. 1, pp. 918\u2013923. IEEE (2005)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2018"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-20893-6_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,28]],"date-time":"2019-05-28T03:28:35Z","timestamp":1559014115000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-20893-6_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030208929","9783030208936"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-20893-6_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"29 May 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Perth, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2018.net\/","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"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"979","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"274","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"28% - 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"}},{"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"}},{"value":"2.7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}