{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T14:05:42Z","timestamp":1771509942870,"version":"3.50.1"},"reference-count":48,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100007065","name":"Nvidia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007065","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000921","name":"European Cooperation in Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000921","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Vision and Image Understanding"],"published-print":{"date-parts":[[2021,4]]},"DOI":"10.1016\/j.cviu.2021.103171","type":"journal-article","created":{"date-parts":[[2021,2,6]],"date-time":"2021-02-06T23:45:15Z","timestamp":1612655115000},"page":"103171","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":16,"special_numbering":"C","title":["Facial landmarks localization using cascaded neural networks"],"prefix":"10.1016","volume":"205","author":[{"given":"Shahar","family":"Mahpod","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rig","family":"Das","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emanuele","family":"Maiorana","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yosi","family":"Keller","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patrizio","family":"Campisi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.cviu.2021.103171_b1","doi-asserted-by":"crossref","unstructured":"Belagiannis, V., Zisserman, A., 2017. Recurrent human pose estimation. In: 2017 12th IEEE International Conference on Automatic Face Gesture Recognition (FG 2017), pp. 468\u2013475, doi:10.1109\/FG.2017.64.","DOI":"10.1109\/FG.2017.64"},{"issue":"12","key":"10.1016\/j.cviu.2021.103171_b2","doi-asserted-by":"crossref","first-page":"2930","DOI":"10.1109\/TPAMI.2013.23","article-title":"Localizing parts of faces using a consensus of exemplars","volume":"35","author":"Belhumeur","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.cviu.2021.103171_b3","doi-asserted-by":"crossref","unstructured":"Burgos-Artizzu, X., Perona, P., Doll\u00e1r, P., 2013. Robust Face Landmark Estimation under Occlusion. In: 2013 IEEE International Conference on Computer Vision, pp. 1513\u20131520, doi:10.1109\/ICCV.2013.191.","DOI":"10.1109\/ICCV.2013.191"},{"key":"10.1016\/j.cviu.2021.103171_b4","doi-asserted-by":"crossref","unstructured":"Cao, X., Wei, Y., Wen, F., Sun, J., 2012. Face alignment by explicit shape regression. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2887\u20132894, doi:10.1109\/CVPR.2012.6248015.","DOI":"10.1109\/CVPR.2012.6248015"},{"key":"10.1016\/j.cviu.2021.103171_b5","series-title":"Computer Vision \u2013 ECCV 2014","first-page":"109","article-title":"Joint cascade face detection and alignment","author":"Chen","year":"2014"},{"issue":"7","key":"10.1016\/j.cviu.2021.103171_b6","doi-asserted-by":"crossref","first-page":"1654","DOI":"10.1109\/TPAMI.2019.2901875","article-title":"Adversarial learning of structure-aware fully convolutional networks for landmark localization","volume":"42","author":"Chen","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.cviu.2021.103171_b7","doi-asserted-by":"crossref","unstructured":"Chen, X., Zhou, E., Mo, Y., Liu, J., Cao, Z., 2017. Delving deep into coarse-to-fine framework for facial landmark localization. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 2088\u20132095, doi:10.1109\/CVPRW.2017.260.","DOI":"10.1109\/CVPRW.2017.260"},{"issue":"1","key":"10.1016\/j.cviu.2021.103171_b8","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1016\/j.acha.2006.04.006","article-title":"Diffusion maps","volume":"21","author":"Coifman","year":"2006","journal-title":"Appl. Comput. Harmon. Anal."},{"issue":"6","key":"10.1016\/j.cviu.2021.103171_b9","doi-asserted-by":"crossref","first-page":"681","DOI":"10.1109\/34.927467","article-title":"Active appearance models","volume":"23","author":"Cootes","year":"2001","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.cviu.2021.103171_b10","series-title":"BMVC92","first-page":"266","article-title":"Active shape models \u2014 \u2018Smart Snakes\u2019","author":"Cootes","year":"1992"},{"key":"10.1016\/j.cviu.2021.103171_b11","unstructured":"Cristinacce, D., Cootes, T., 2006. Feature detection and tracking with constrained local models. In: British Machine Vision Conference, pp. 929\u2013938."},{"key":"10.1016\/j.cviu.2021.103171_b12","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/j.imavis.2015.11.005","article-title":"M CSR: multi-view, multi-scale and multi-component cascade shape regression","volume":"47","author":"Deng","year":"2016","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.cviu.2021.103171_b13","doi-asserted-by":"crossref","unstructured":"Dong, X., Yan, Y., Ouyang, W., Yang, Y., 2018. Style aggregated network for facial landmark detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 379\u2013388.","DOI":"10.1109\/CVPR.2018.00047"},{"issue":"C","key":"10.1016\/j.cviu.2021.103171_b14","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1016\/j.imavis.2015.11.004","article-title":"Approaching human level facial landmark localization by deep learning","volume":"47","author":"Fan","year":"2016","journal-title":"Image Vis. Comput."},{"issue":"9","key":"10.1016\/j.cviu.2021.103171_b15","doi-asserted-by":"crossref","first-page":"2420","DOI":"10.1109\/TSP.2015.2411211","article-title":"Sensor network localization by augmented dual embedding","volume":"63","author":"Gepshtein","year":"2015","journal-title":"IEEE Trans. Signal Process."},{"key":"10.1016\/j.cviu.2021.103171_b16","series-title":"Occlusion coherence: Detecting and localizing occluded faces","author":"Ghiasi","year":"2015"},{"key":"10.1016\/j.cviu.2021.103171_b17","doi-asserted-by":"crossref","unstructured":"He, Z., Kan, M., Zhang, J., Chen, X., Shan, S., 2017. A fully end-to-end cascaded CNN for facial landmark detection. In: 2017 12th IEEE International Conference on Automatic Face Gesture Recognition (FG 2017), pp. 200\u2013207, doi:10.1109\/FG.2017.33.","DOI":"10.1109\/FG.2017.33"},{"key":"10.1016\/j.cviu.2021.103171_b18","doi-asserted-by":"crossref","unstructured":"He, Z., Zhang, J., Kan, M., Shan, S., Chen, X., 2017. Robust FEC-CNN: A high accuracy facial landmark detection system. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 2044\u20132050, doi:10.1109\/CVPRW.2017.255.","DOI":"10.1109\/CVPRW.2017.255"},{"key":"10.1016\/j.cviu.2021.103171_b19","doi-asserted-by":"crossref","unstructured":"Huang, Z., Zhao, X., Shan, S., Wang, R., Chen, X., 2013. Coupling alignments with recognition for still-to-video face recognition. In: 2013 IEEE International Conference on Computer Vision, pp. 3296\u20133303, doi:10.1109\/ICCV.2013.409.","DOI":"10.1109\/ICCV.2013.409"},{"issue":"6","key":"10.1016\/j.cviu.2021.103171_b20","doi-asserted-by":"crossref","first-page":"2642","DOI":"10.1109\/TSP.2011.2122261","article-title":"A diffusion approach to network localization","volume":"59","author":"Keller","year":"2011","journal-title":"IEEE Trans. Signal Process."},{"issue":"11","key":"10.1016\/j.cviu.2021.103171_b21","doi-asserted-by":"crossref","first-page":"1567","DOI":"10.1109\/LSP.2016.2608139","article-title":"Face alignment using K-cluster regression forests with weighted splitting","volume":"23","author":"Kowalski","year":"2016","journal-title":"IEEE Signal Process. Lett."},{"key":"10.1016\/j.cviu.2021.103171_b22","doi-asserted-by":"crossref","unstructured":"Kowalski, M., Naruniec, J., Trzcinski, T., 2017. Deep alignment network: A convolutional neural network for robust face alignment. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 2034\u20132043, doi:10.1109\/CVPRW.2017.254.","DOI":"10.1109\/CVPRW.2017.254"},{"key":"10.1016\/j.cviu.2021.103171_b23","series-title":"Computer Vision \u2013 ECCV 2008","first-page":"340","article-title":"Facetracer: A search engine for large collections of images with faces","author":"Kumar","year":"2008"},{"issue":"99","key":"10.1016\/j.cviu.2021.103171_b24","first-page":"1","article-title":"Deep recurrent regression for facial landmark detection","volume":"PP","author":"Lai","year":"2017","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.cviu.2021.103171_b25","series-title":"Computer Vision \u2013 ECCV 2012: 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part III","first-page":"679","article-title":"Interactive facial feature localization","author":"Le","year":"2012"},{"key":"10.1016\/j.cviu.2021.103171_b26","doi-asserted-by":"crossref","unstructured":"Lee, D., Park, H., Yoo, C.D., 2015. Face alignment using cascade Gaussian process regression trees. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4204\u20134212, doi:10.1109\/CVPR.2015.7299048.","DOI":"10.1109\/CVPR.2015.7299048"},{"issue":"2","key":"10.1016\/j.cviu.2021.103171_b27","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","article-title":"Distinctive image features from scale-invariant keypoints","volume":"60","author":"Lowe","year":"2004","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.cviu.2021.103171_b28","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/j.cviu.2017.12.003","article-title":"Kinship verification using multiview hybrid distance learning","volume":"167","author":"Mahpod","year":"2018","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.cviu.2021.103171_b29","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1016\/j.imavis.2015.09.003","article-title":"L2,1-based regression and prediction accumulation across views for robust facial landmark detection","volume":"47","author":"Martinez","year":"2016","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.cviu.2021.103171_b30","series-title":"Audio- and Video-Based Biometric Person Authentication: 4th International Conference, AVBPA 2003 Guildford, UK, June 9\u201311, 2003 Proceedings","first-page":"964","article-title":"Face verification competition on the XM2vts database","author":"Messer","year":"2003"},{"key":"10.1016\/j.cviu.2021.103171_b31","doi-asserted-by":"crossref","unstructured":"Pfister, T., Charles, J., Zisserman, A., 2015. Flowing convnets for human pose estimation in videos. In: International Conference on Computer Vision (ICCV).","DOI":"10.1109\/ICCV.2015.222"},{"key":"10.1016\/j.cviu.2021.103171_b32","doi-asserted-by":"crossref","unstructured":"Ren, S., Cao, X., Wei, Y., Sun, J., 2014. Face Alignment at 3000 FPS via regressing local binary features. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1685\u20131692, doi:10.1109\/CVPR.2014.218.","DOI":"10.1109\/CVPR.2014.218"},{"issue":"Supplement C","key":"10.1016\/j.cviu.2021.103171_b33","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.imavis.2016.01.002","article-title":"300 faces in-the-wild challenge: database and results","volume":"47","author":"Sagonas","year":"2016","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.cviu.2021.103171_b34","doi-asserted-by":"crossref","unstructured":"Shao, X., Xing, J., Lv, J., Xiao, C., Liu, P., Feng, Y., Cheng, C., 2017. Unconstrained face alignment without face detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 2069\u20132077, doi:10.1109\/CVPRW.2017.258.","DOI":"10.1109\/CVPRW.2017.258"},{"key":"10.1016\/j.cviu.2021.103171_b35","doi-asserted-by":"crossref","unstructured":"Trigeorgis, G., Snape, P., Nicolaou, M.A., Antonakos, E., Zafeiriou, S., 2016. Mnemonic descent method: A recurrent process applied for end-to-end face alignment. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4177\u20134187, doi:10.1109\/CVPR.2016.453.","DOI":"10.1109\/CVPR.2016.453"},{"key":"10.1016\/j.cviu.2021.103171_b36","series-title":"Computer Vision \u2013 ECCV 2016","first-page":"825","article-title":"Robust face alignment using a mixture of invariant experts","author":"Tuzel","year":"2016"},{"key":"10.1016\/j.cviu.2021.103171_b37","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1016\/j.imavis.2016.02.004","article-title":"Multi-view facial landmark detector learned by the structured output SVM","volume":"47","author":"U\u0159i\u010d\u00e1\u0159","year":"2016","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.cviu.2021.103171_b38","series-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","first-page":"6000","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.cviu.2021.103171_b39","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.imavis.2015.11.003","article-title":"Multi-view facial landmark detection by using a 3D shape model","volume":"47","author":"\u010cech","year":"2016","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.cviu.2021.103171_b40","doi-asserted-by":"crossref","unstructured":"Vedaldi, A., Lenc, K., 2015. MatConvNet \u2013 Convolutional Neural Networks for MATLAB. In: Proceeding of the ACM Int. Conf. on Multimedia.","DOI":"10.1145\/2733373.2807412"},{"key":"10.1016\/j.cviu.2021.103171_b41","doi-asserted-by":"crossref","unstructured":"Viola, P., Jones, M., 2001. Rapid object detection using a boosted cascade of simple features. In: Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, Vol. 1, pp. I\u2013511\u2013I\u2013518, doi:10.1109\/CVPR.2001.990517.","DOI":"10.1109\/CVPR.2001.990517"},{"key":"10.1016\/j.cviu.2021.103171_b42","series-title":"Computer Vision \u2013 ECCV 2016","first-page":"57","article-title":"Robust facial landmark detection via recurrent attentive-refinement networks","author":"Xiao","year":"2016"},{"key":"10.1016\/j.cviu.2021.103171_b43","doi-asserted-by":"crossref","unstructured":"Xiong, X., De la Torre, F., 2013. Supervised descent method and its applications to face alignment. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition, pp. 532\u2013539, doi:10.1109\/CVPR.2013.75.","DOI":"10.1109\/CVPR.2013.75"},{"key":"10.1016\/j.cviu.2021.103171_b44","series-title":"CVPR Workshops","first-page":"2051","article-title":"Convolutional experts constrained local model for facial landmark detection","author":"Zadeh","year":"2017"},{"key":"10.1016\/j.cviu.2021.103171_b45","doi-asserted-by":"crossref","unstructured":"Zafeiriou, S., Trigeorgis, G., Chrysos, G., Deng, J., Shen, J., 2017. The Menpo facial landmark localisation challenge: A step towards the solution. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 2116\u20132125, doi:10.1109\/CVPRW.2017.263.","DOI":"10.1109\/CVPRW.2017.263"},{"issue":"5","key":"10.1016\/j.cviu.2021.103171_b46","doi-asserted-by":"crossref","first-page":"918","DOI":"10.1109\/TPAMI.2015.2469286","article-title":"Learning deep representation for face alignment with auxiliary attributes","volume":"38","author":"Zhang","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.cviu.2021.103171_b47","doi-asserted-by":"crossref","unstructured":"Zhu, S., Li, C., Loy, C.C., Tang, X., 2015. Face alignment by coarse-to-fine shape searching. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4998\u20135006, doi:10.1109\/CVPR.2015.7299134.","DOI":"10.1109\/CVPR.2015.7299134"},{"key":"10.1016\/j.cviu.2021.103171_b48","doi-asserted-by":"crossref","unstructured":"Zhu, X., Ramanan, D., 2012. Face detection, pose estimation, and landmark localization in the wild. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2879\u20132886, doi:10.1109\/CVPR.2012.6248014.","DOI":"10.1109\/CVPR.2012.6248014"}],"container-title":["Computer Vision and Image Understanding"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314221000151?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314221000151?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T09:18:37Z","timestamp":1761038317000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1077314221000151"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4]]},"references-count":48,"alternative-id":["S1077314221000151"],"URL":"https:\/\/doi.org\/10.1016\/j.cviu.2021.103171","relation":{},"ISSN":["1077-3142"],"issn-type":[{"value":"1077-3142","type":"print"}],"subject":[],"published":{"date-parts":[[2021,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Facial landmarks localization using cascaded neural networks","name":"articletitle","label":"Article Title"},{"value":"Computer Vision and Image Understanding","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cviu.2021.103171","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2021 Elsevier Inc. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"103171"}}