{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T00:09:24Z","timestamp":1780618164508,"version":"3.54.1"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2020,10,30]],"date-time":"2020-10-30T00:00:00Z","timestamp":1604016000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,10,30]],"date-time":"2020-10-30T00:00:00Z","timestamp":1604016000000},"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":["Vis Comput"],"published-print":{"date-parts":[[2021,7]]},"DOI":"10.1007\/s00371-020-01934-1","type":"journal-article","created":{"date-parts":[[2020,10,30]],"date-time":"2020-10-30T19:02:26Z","timestamp":1604084546000},"page":"1731-1741","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["RGB-D-based gaze point estimation via multi-column CNNs and facial landmarks global optimization"],"prefix":"10.1007","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4496-1861","authenticated-orcid":false,"given":"Ziheng","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongze","family":"Lian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shenghua","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,10,30]]},"reference":[{"key":"1934_CR1","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Malik, J.: Intrinsic scene properties from a single RGB-D image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 17\u201324 (2013)","DOI":"10.1109\/CVPR.2013.10"},{"key":"1934_CR2","doi-asserted-by":"crossref","unstructured":"Cire\u015fan, D., Meier, U., Schmidhuber, J.: Multi-column Deep Neural Networks for Image Classification (2012). arXiv:1202.2745","DOI":"10.1109\/CVPR.2012.6248110"},{"key":"1934_CR3","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. In: Advances in Neural Information Processing Systems, pp. 2366\u20132374 (2014)"},{"issue":"2","key":"1934_CR4","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1007\/s11263-015-0863-4","volume":"118","author":"KA Funes-Mora","year":"2016","unstructured":"Funes-Mora, K.A., Odobez, J.M.: Gaze estimation in the 3d space using RGB-D sensors. Int. J. Comput. Vision 118(2), 194\u2013216 (2016)","journal-title":"Int. J. Comput. Vision"},{"key":"1934_CR5","unstructured":"Ghiass, R.S., Arandjelovic, O.: Highly accurate gaze estimation using a consumer RGB-D sensor. In: Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, pp. 3368\u20133374. AAAI Press (2016)"},{"issue":"3","key":"1934_CR6","doi-asserted-by":"publisher","first-page":"478","DOI":"10.1109\/TPAMI.2009.30","volume":"32","author":"DW Hansen","year":"2010","unstructured":"Hansen, D.W., Ji, Q.: In the eye of the beholder: a survey of models for eyes and gaze. IEEE Trans. Pattern Anal. Mach. Intell. 32(3), 478\u2013500 (2010)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1934_CR7","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":"1934_CR8","doi-asserted-by":"crossref","unstructured":"He, Q., Hong, X., Chai, X., Holappa, J., Zhao, G., Chen, X., Pietik\u00e4inen, M.: Omeg: oulu multi-pose eye gaze dataset. In: Scandinavian Conference on Image Analysis, pp. 418\u2013427. Springer (2015)","DOI":"10.1007\/978-3-319-19665-7_35"},{"key":"1934_CR9","unstructured":"Huang, Q., Veeraraghavan, A., Sabharwal, A.: Tabletgaze: Unconstrained Appearance-based Gaze Estimation in Mobile Tablets (2015). arXiv:1508.01244"},{"key":"1934_CR10","doi-asserted-by":"publisher","first-page":"16495","DOI":"10.1109\/ACCESS.2017.2735633","volume":"5","author":"A Kar","year":"2017","unstructured":"Kar, A., Corcoran, P.: A review and analysis of eye-gaze estimation systems, algorithms and performance evaluation methods in consumer platforms. IEEE Access 5, 16495\u201316519 (2017)","journal-title":"IEEE Access"},{"key":"1934_CR11","doi-asserted-by":"crossref","unstructured":"Krafka, K., Khosla, A., Kellnhofer, P., Kannan, H., Bhandarkar, S., Matusik, W., Torralba, A.: Eye tracking for everyone. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2176\u20132184 (2016)","DOI":"10.1109\/CVPR.2016.239"},{"key":"1934_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":"1934_CR13","unstructured":"Kuno, Y., Yagi, T., Uchikawa, Y.: Development of a fish-eye VR system with human visual functioning and biological signals. In: 1996 IEEE\/SICE\/RSJ International Conference on Multisensor Fusion and Integration for Intelligent Systems (Cat. No. 96TH8242), pp. 389\u2013394. IEEE (1996)"},{"key":"1934_CR14","unstructured":"Kuno, Y., Yagi, T., Uchikawa, Y.: Development of eye-gaze input interface. In: Proceedings of 7th International Conference on Human Computer Interaction. Volumen 1, vol.\u00a044 (1997)"},{"key":"1934_CR15","unstructured":"Liu, G., Yu, Y., Funes-Mora, K.A., Odobez, J.M.: A differential approach for gaze estimation with calibration. In: 29th British Machine Vision Conference 2018 (2018)"},{"key":"1934_CR16","unstructured":"Liu, G., Yu, Y., Mora, K.A.F., Odobez, J.M.: A differential approach for gaze estimation (2019). arXiv:1904.09459"},{"key":"1934_CR17","doi-asserted-by":"crossref","unstructured":"Majaranta, P., Bulling, A.: Eye tracking and eye-based human\u2013computer interaction. In: Advances in Physiological Computing, pp. 39\u201365. Springer (2014)","DOI":"10.1007\/978-1-4471-6392-3_3"},{"key":"1934_CR18","unstructured":"Masko, D.: Calibration in eye tracking using transfer learning. Master thesis, KTH, School of Computer Science and Communication (CSC) (2017)"},{"key":"1934_CR19","doi-asserted-by":"publisher","unstructured":"McMurrough, C.D., Metsis, V., Rich, J., Makedon, F.: An eye tracking dataset for point of gaze detection. In: Proceedings of the Symposium on Eye Tracking Research and Applications, ETRA\u201912, pp. 305\u2013308. ACM, New York, NY, USA (2012). https:\/\/doi.org\/10.1145\/2168556.2168622","DOI":"10.1145\/2168556.2168622"},{"key":"1934_CR20","unstructured":"Mora, K.A.F., Monay, F., Odobez, J.M.: Eyediap: a database for the development and evaluation of gaze estimation algorithms from RGB and RGB-D cameras. In: Proceedings of the Symposium on Eye Tracking Research and Applications, pp. 255\u2013258. ACM (2014)"},{"key":"1934_CR21","unstructured":"Mora, K.A.F., Odobez, J.M.: Gaze estimation from multimodal kinect data. In: 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, pp. 25\u201330. IEEE (2012)"},{"issue":"1","key":"1934_CR22","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1016\/j.cviu.2004.07.010","volume":"98","author":"CH Morimoto","year":"2005","unstructured":"Morimoto, C.H., Mimica, M.R.: Eye gaze tracking techniques for interactive applications. Comput. Vis. Image Underst. 98(1), 4\u201324 (2005)","journal-title":"Comput. Vis. Image Underst."},{"key":"1934_CR23","doi-asserted-by":"crossref","unstructured":"Ranjan, R., De\u00a0Mello, S., Kautz, J.: Light-weight head pose invariant gaze tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 2156\u20132164 (2018)","DOI":"10.1109\/CVPRW.2018.00290"},{"issue":"3","key":"1934_CR24","doi-asserted-by":"publisher","first-page":"372","DOI":"10.1037\/0033-2909.124.3.372","volume":"124","author":"K Rayner","year":"1998","unstructured":"Rayner, K.: Eye movements in reading and information processing: 20 years of research. Psychol. Bull. 124(3), 372 (1998)","journal-title":"Psychol. Bull."},{"key":"1934_CR25","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"1934_CR26","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.imavis.2016.01.002","volume":"47","author":"C Sagonas","year":"2016","unstructured":"Sagonas, C., Antonakos, E., Tzimiropoulos, G., Zafeiriou, S., Pantic, M.: 300 faces in-the-wild challenge: database and results. Image Vis. Comput. 47, 3\u201318 (2016)","journal-title":"Image Vis. Comput."},{"issue":"12","key":"1934_CR27","doi-asserted-by":"publisher","first-page":"4280","DOI":"10.3390\/s18124280","volume":"18","author":"R Shoja Ghiass","year":"2018","unstructured":"Shoja Ghiass, R., Arandjelov\u0107, O., Laurendeau, D.: Highly accurate and fully automatic 3d head pose estimation and eye gaze estimation using rgb-d sensors and 3d morphable models. Sensors 18(12), 4280 (2018)","journal-title":"Sensors"},{"key":"1934_CR28","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 (2014)"},{"key":"1934_CR29","doi-asserted-by":"publisher","unstructured":"Stellato, B., Banjac, G., Goulart, P., Bemporad, A., Boyd, S.: OSQP: an operator splitting solver for quadratic programs. Math. Program. Comput. 12, 637\u2013672 (2020). https:\/\/doi.org\/10.1007\/s12532-020-00179-2","DOI":"10.1007\/s12532-020-00179-2"},{"issue":"02","key":"1934_CR30","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1142\/S0218213097000116","volume":"6","author":"R Stiefelhagen","year":"1997","unstructured":"Stiefelhagen, R., Yang, J., Waibel, A.: A model-based gaze tracking system. Int. J. Artif. Intell. Tools 6(02), 193\u2013209 (1997)","journal-title":"Int. J. Artif. Intell. Tools"},{"key":"1934_CR31","doi-asserted-by":"crossref","unstructured":"Sugano, Y., Matsushita, Y., Sato, Y.: Learning-by-synthesis for appearance-based 3d gaze estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1821\u20131828 (2014)","DOI":"10.1109\/CVPR.2014.235"},{"key":"1934_CR32","doi-asserted-by":"crossref","unstructured":"Suwajanakorn, S., Hernandez, C., Seitz, S.M.: Depth from focus with your mobile phone. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3497\u20133506 (2015)","DOI":"10.1109\/CVPR.2015.7298972"},{"key":"1934_CR33","doi-asserted-by":"crossref","unstructured":"Wang, K., Zhao, R., Su, H., Ji, Q.: Generalizing eye tracking with Bayesian adversarial learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11907\u201311916 (2019)","DOI":"10.1109\/CVPR.2019.01218"},{"issue":"6","key":"1934_CR34","doi-asserted-by":"publisher","first-page":"1287","DOI":"10.3390\/s19061287","volume":"19","author":"Y Wang","year":"2019","unstructured":"Wang, Y., Yuan, G., Mi, Z., Peng, J., Ding, X., Liang, Z., Fu, X.: Continuous driver\u2019s gaze zone estimation using RGB-D camera. Sensors 19(6), 1287 (2019)","journal-title":"Sensors"},{"key":"1934_CR35","doi-asserted-by":"crossref","unstructured":"Xie, J., Girshick, R., Farhadi, A.: Deep3d: Fully automatic 2d-to-3d video conversion with deep convolutional neural networks. In: European Conference on Computer Vision, pp. 842\u2013857. Springer (2016)","DOI":"10.1007\/978-3-319-46493-0_51"},{"key":"1934_CR36","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"},{"issue":"8","key":"1934_CR37","doi-asserted-by":"publisher","first-page":"690","DOI":"10.1109\/34.784284","volume":"21","author":"R Zhang","year":"1999","unstructured":"Zhang, R., Tsai, P.S., Cryer, J.E., Shah, M.: Shape-from-shading: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 21(8), 690\u2013706 (1999)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1934_CR38","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":"1934_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, X., Sugano, Y., Fritz, M., Bulling, A.: It\u2019s written all over your face: full-face appearance-based gaze estimation. In: CVPRW (2017)","DOI":"10.1109\/CVPRW.2017.284"},{"key":"1934_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Funkhouser, T.: Deep depth completion of a single RGB-D image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 175\u2013185 (2018)","DOI":"10.1109\/CVPR.2018.00026"},{"key":"1934_CR41","doi-asserted-by":"crossref","unstructured":"Zhu, W., Deng, H.: Monocular free-head 3d gaze tracking with deep learning and geometry constraints. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3143\u20133152 (2017)","DOI":"10.1109\/ICCV.2017.341"},{"key":"1934_CR42","unstructured":"Zhu, Z., Ji, Q., Bennett, K.P.: Nonlinear eye gaze mapping function estimation via support vector regression. In: 18th International Conference on Pattern Recognition, 2006. ICPR 2006, vol.\u00a01, pp. 1132\u20131135. IEEE (2006)"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-020-01934-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-020-01934-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-020-01934-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,6,25]],"date-time":"2021-06-25T13:20:16Z","timestamp":1624627216000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-020-01934-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,30]]},"references-count":42,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2021,7]]}},"alternative-id":["1934"],"URL":"https:\/\/doi.org\/10.1007\/s00371-020-01934-1","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,10,30]]},"assertion":[{"value":"30 October 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The author declares that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Ziheng Zhang declares that all procedures performed in studies involving human participants were in accordance with the ethical standards of the ShanghaiTech Ethics Committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards, and that no study with animals was performed by any of the authors. Ziheng Zhang declares that informed consent was obtained from all individual participants included in the study.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}]}}