{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T06:14:58Z","timestamp":1744179298042,"version":"3.27.0"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2023,4,25]],"date-time":"2023-04-25T00:00:00Z","timestamp":1682380800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,4,25]],"date-time":"2023-04-25T00:00:00Z","timestamp":1682380800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1007\/s00530-023-01095-w","type":"journal-article","created":{"date-parts":[[2023,4,25]],"date-time":"2023-04-25T10:03:11Z","timestamp":1682416991000},"page":"2137-2152","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Face attribute recognition via end-to-end weakly supervised regional location"],"prefix":"10.1007","volume":"29","author":[{"given":"Jian","family":"Shi","sequence":"first","affiliation":[]},{"given":"Ge","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Jinyu","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Zhihui","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Haojie","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,4,25]]},"reference":[{"key":"1095_CR1","doi-asserted-by":"crossref","unstructured":"Berg, T., Belhumeur, P.: Poof: part-based one-vs.-one features for fine-grained categorization, face verification, and attribute estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 955\u2013962 (2013)","DOI":"10.1109\/CVPR.2013.128"},{"key":"1095_CR2","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1016\/j.cviu.2014.02.010","volume":"122","author":"F Song","year":"2014","unstructured":"Song, F., Tan, X., Chen, S.: Exploiting relationship between attributes for improved face verification. Comput. Vis. Image Underst. 122, 143\u2013154 (2014)","journal-title":"Comput. Vis. Image Underst."},{"issue":"7","key":"1095_CR3","doi-asserted-by":"publisher","first-page":"1761","DOI":"10.1109\/TPAMI.2018.2842770","volume":"41","author":"R He","year":"2018","unstructured":"He, R., Wu, X., Sun, Z., Tan, T.: Wasserstein cnn: learning invariant features for nir-vis face recognition. IEEE Trans. Pattern Anal. Mach. Intell. 41(7), 1761\u20131773 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"10","key":"1095_CR4","doi-asserted-by":"publisher","first-page":"2552","DOI":"10.1109\/TPAMI.2019.2919284","volume":"42","author":"R He","year":"2020","unstructured":"He, R., Tan, T., Davis, L., Sun, Z.: Robust rgb-d face recognition using attribute-aware loss. IEEE Trans. Pattern Anal. Mach. Intell. 42(10), 2552\u20132566 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1095_CR5","doi-asserted-by":"crossref","unstructured":"Fan, C., Wang, Z., Li, J., Wang, S., Sun, X.: Robust facial expression recognition with global-local joint representation learning. In: Multimedia Systems, pp. 1\u201311 (2022)","DOI":"10.1007\/s00530-022-00907-9"},{"key":"1095_CR6","doi-asserted-by":"crossref","unstructured":"Jagadeesh, M., Baranidharan, B.: Facial expression recognition of online learners from real-time videos using a novel deep learning model. In: Multimedia Systems, pp. 1\u201322 (2022)","DOI":"10.1007\/s00530-022-00957-z"},{"key":"1095_CR7","doi-asserted-by":"publisher","first-page":"2593","DOI":"10.1109\/TIFS.2021.3059274","volume":"16","author":"Y Fang","year":"2021","unstructured":"Fang, Y., Xiao, Z., Zhang, W., Huang, Y., Wang, L., Boujemaa, N., Geman, D.: Attribute prototype learning for interactive face retrieval. IEEE Trans. Inf. Forensics Secur. 16, 2593\u20132607 (2021)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"issue":"1","key":"1095_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13640-018-0282-x","volume":"2018","author":"Y Fang","year":"2018","unstructured":"Fang, Y., Yuan, Q.: Attribute-enhanced metric learning for face retrieval. EURASIP J. Image Video Process. 2018(1), 1\u20139 (2018)","journal-title":"EURASIP J. Image Video Process."},{"issue":"3","key":"1095_CR9","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1109\/TBIOM.2021.3082038","volume":"3","author":"X Di","year":"2021","unstructured":"Di, X., Patel, V.M.: Multimodal face synthesis from visual attributes. IEEE Trans. Biom. Behav. Identity Sci. 3(3), 427\u2013439 (2021)","journal-title":"IEEE Trans. Biom. Behav. Identity Sci."},{"key":"1095_CR10","doi-asserted-by":"crossref","unstructured":"Cao, J., Li, Y., Zhang, Z.: Partially shared multi-task convolutional neural network with local constraint for face attribute learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4290\u20134299 (2018)","DOI":"10.1109\/CVPR.2018.00451"},{"key":"1095_CR11","doi-asserted-by":"crossref","unstructured":"Rudd, E.M., G\u00fcnther, M., Boult, T.E.: Moon: A mixed objective optimization network for the recognition of facial attributes. In: European Conference on Computer Vision, pp. 19\u201335 (2016)","DOI":"10.1007\/978-3-319-46454-1_2"},{"key":"1095_CR12","doi-asserted-by":"crossref","unstructured":"Hand, E.M., Chellappa, R.: Attributes for improved attributes: a multi-task network utilizing implicit and explicit relationships for facial attribute classification. In: Thirty-First AAAI Conference on Artificial Intelligence, pp. 4068\u20134074 (2017)","DOI":"10.1609\/aaai.v31i1.11229"},{"issue":"11","key":"1095_CR13","doi-asserted-by":"publisher","first-page":"2597","DOI":"10.1109\/TPAMI.2017.2738004","volume":"40","author":"H Han","year":"2017","unstructured":"Han, H., Jain, A.K., Wang, F., Shan, S., Chen, X.: Heterogeneous face attribute estimation: a deep multi-task learning approach. IEEE Trans. Pattern Anal. Mach. Intell. 40(11), 2597\u20132609 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1095_CR14","doi-asserted-by":"crossref","unstructured":"Zhang, N., Paluri, M., Ranzato, M., Darrell, T., Bourdev, L.: Panda: Pose aligned networks for deep attribute modeling. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1637\u20131644 (2014)","DOI":"10.1109\/CVPR.2014.212"},{"key":"1095_CR15","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Girshick, R., Malik, J.: Actions and attributes from wholes and parts. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2470\u20132478 (2015)","DOI":"10.1109\/ICCV.2015.284"},{"key":"1095_CR16","doi-asserted-by":"crossref","unstructured":"Bourdev, L., Malik, J.: Poselets: Body part detectors trained using 3d human pose annotations. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 1365\u20131372 (2009)","DOI":"10.1109\/ICCV.2009.5459303"},{"key":"1095_CR17","doi-asserted-by":"crossref","unstructured":"Bourdev, L., Maji, S., Malik, J.: Describing people: a poselet-based approach to attribute classification. In: 2011 International Conference on Computer Vision, pp. 1543\u20131550 (2011)","DOI":"10.1109\/ICCV.2011.6126413"},{"key":"1095_CR18","doi-asserted-by":"crossref","unstructured":"Kalayeh, M.M., Gong, B., Shah, M.: Improving facial attribute prediction using semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6942\u20136950 (2017)","DOI":"10.1109\/CVPR.2017.450"},{"issue":"4","key":"1095_CR19","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1109\/TAFFC.2018.2820048","volume":"11","author":"U Mahbub","year":"2018","unstructured":"Mahbub, U., Sarkar, S., Chellappa, R.: Segment-based methods for facial attribute detection from partial faces. IEEE Trans. Affect. Comput. 11(4), 601\u2013613 (2018)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"1095_CR20","doi-asserted-by":"crossref","unstructured":"Ding, H., Zhou, H., Zhou, S.K., Chellappa, R.: A deep cascade network for unaligned face attribute classification. In: Thirty-Second AAAI Conference on Artificial Intelligence, pp. 6789\u20136796 (2018)","DOI":"10.1609\/aaai.v32i1.12303"},{"key":"1095_CR21","doi-asserted-by":"crossref","unstructured":"Wang, Y., Morariu, V.I., Davis, L.S.: Learning a discriminative filter bank within a cnn for fine-grained recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4148\u20134157 (2018)","DOI":"10.1109\/CVPR.2018.00436"},{"key":"1095_CR22","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"1095_CR23","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.: Ssd: single shot multibox detector. In: European Conference on Computer Vision, pp. 21\u201337 (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"1095_CR24","unstructured":"Huang, G.B., Mattar, M., Berg, T., Learned-Miller, E.: Labeled faces in the wild: a database for studying face recognition in unconstrained environments. Tech. Rep. (2008)"},{"key":"1095_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3730\u20133738 (2015)","DOI":"10.1109\/ICCV.2015.425"},{"key":"1095_CR26","doi-asserted-by":"publisher","first-page":"2002","DOI":"10.1007\/s11263-020-01308-z","volume":"128","author":"X Zheng","year":"2020","unstructured":"Zheng, X., Guo, Y., Huang, H., Li, Y., He, R.: A survey of deep facial attribute analysis. Int. J. Comput. Vis. 128, 2002\u20132034 (2020)","journal-title":"Int. J. Comput. Vis."},{"key":"1095_CR27","unstructured":"Taherkhani, F., Dabouei, A., Soleymani, S., Dawson, J., Nasrabadi, N.M.: Tasks structure regularization in multi-task learning for improving facial attribute prediction (2021). arXiv:2108.04353"},{"issue":"1","key":"1095_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3418285","volume":"12","author":"M Duan","year":"2021","unstructured":"Duan, M., Li, K., Li, K., Tian, Q.: A novel multi-task tensor correlation neural network for facial attribute prediction. Trans. Intell. Syst. Technol. 12(1), 1\u201322 (2021)","journal-title":"Trans. Intell. Syst. Technol."},{"key":"1095_CR29","doi-asserted-by":"crossref","unstructured":"Chen, Z., Liu, F., Zhao, Z.: Let them choose what they want: a multi-task cnn architecture leveraging mid-level deep representations for face attribute classification. In: 2021 IEEE International Conference on Image Processing (ICIP), pp. 879\u2013883 (2021)","DOI":"10.1109\/ICIP42928.2021.9506456"},{"key":"1095_CR30","doi-asserted-by":"crossref","unstructured":"Fang, K., Yang, J.: Robust deep facial attribute prediction against adversarial attacks. In: 2021 7th International Conference on Computing and Artificial Intelligence, pp. 202\u2013207 (2021)","DOI":"10.1145\/3467707.3467737"},{"key":"1095_CR31","unstructured":"Fang, K., Tao, Q., Wu, Y., Li, T., Cai, J., Cai, F., Huang, X., Yang, J.: Learn robust features via orthogonal multi-path (2020). arXiv:2010.12190"},{"key":"1095_CR32","doi-asserted-by":"crossref","unstructured":"Singh, K.K., Lee, Y.J.: End-to-end localization and ranking for relative attributes. In: European Conference on Computer Vision, pp. 753\u2013769 (2016)","DOI":"10.1007\/978-3-319-46466-4_45"},{"key":"1095_CR33","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., et al.: Spatial transformer networks. In: Advances in Neural Information Processing Systems, pp. 2017\u20132025 (2015)"},{"issue":"2","key":"1095_CR34","doi-asserted-by":"publisher","first-page":"328","DOI":"10.3390\/s20020328","volume":"20","author":"K Khan","year":"2020","unstructured":"Khan, K., Attique, M., Khan, R.U., Syed, I.S., Chung, T.S.: A multi-task framework for facial attributes classification through end-to-end face parsing and deep convolutional neural networks. Sensors 20(2), 328 (2020)","journal-title":"Sensors"},{"key":"1095_CR35","doi-asserted-by":"crossref","unstructured":"Ge, H., Dong, J., Zhang, L.: Face attributes recognition based on one-way inferential correlation between attributes. In: MultiMedia Modeling, pp. 253\u2013265 (2020)","DOI":"10.1007\/978-3-030-37731-1_21"},{"key":"1095_CR36","doi-asserted-by":"crossref","unstructured":"Deng, Z., Fang, Y., Zhang, Y.: Face attribute estimation with hmax-gcnet model. In: Biometric Recognition, pp. 392\u2013399 (2021)","DOI":"10.1007\/978-3-030-86608-2_43"},{"key":"1095_CR37","doi-asserted-by":"crossref","unstructured":"Chen, Z., Gu, S., Zhu, F., Xu, J., Zhao, R.: Improving facial attribute recognition by group and graph learning. In: 2021 IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136 (2021)","DOI":"10.1109\/ICME51207.2021.9428078"},{"key":"1095_CR38","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: Arcface: additive angular margin loss for deep face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4690\u20134699 (2019)","DOI":"10.1109\/CVPR.2019.00482"},{"key":"1095_CR39","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"1095_CR40","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921\u20132929 (2016)","DOI":"10.1109\/CVPR.2016.319"},{"key":"1095_CR41","doi-asserted-by":"crossref","unstructured":"Tang, C., Sheng, L., Zhang, Z., Hu, X.: Improving pedestrian attribute recognition with weakly-supervised multi-scale attribute-specific localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4997\u20135006 (2019)","DOI":"10.1109\/ICCV.2019.00510"},{"issue":"6","key":"1095_CR42","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1007\/s11263-018-1134-y","volume":"127","author":"J Deng","year":"2019","unstructured":"Deng, J., Roussos, A., Chrysos, G.G., Ververas, E., Kotsia, I., Shen, J., Zafeiriou, S.: The menpo benchmark for multi-pose 2d and 3d facial landmark localisation and tracking. Int. J. Comput. Vis. 127(6), 599\u2013624 (2019)","journal-title":"Int. J. Comput. Vis."},{"key":"1095_CR43","unstructured":"Guo, J., Deng, J., Xue, N., Zafeiriou, S.: Stacked dense u-nets with dual transformers for robust face alignment. In: British Machine Vision Conference, p. 44 (2018)"},{"key":"1095_CR44","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Zhou, Y., Yu, J., Kotsia, I., Zafeiriou, S.: Retinaface: single-stage dense face localisation in the wild (2019). arXiv:1905.00641","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"1095_CR45","unstructured":"Zhong, Z., Zheng, L., Kang, G., Li, S., Yang, Y.: Random erasing data augmentation (2017). arXiv:1708.04896"},{"issue":"2","key":"1095_CR46","first-page":"1","volume":"13","author":"L Mao","year":"2020","unstructured":"Mao, L., Yan, Y., Xue, J.-H., Wang, H.: Deep multi-task multi-label cnn for effective facial attribute classification. IEEE Trans. Affect. Comput. 13(2), 1 (2020)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"1095_CR47","doi-asserted-by":"crossref","unstructured":"Shu, Y., Yan, Y., Chen, S., Xue, J.-H., Shen, C., Wang, H.: Learning spatial-semantic relationship for facial attribute recognition with limited labeled data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11916\u201311925 (2021)","DOI":"10.1109\/CVPR46437.2021.01174"},{"key":"1095_CR48","doi-asserted-by":"crossref","unstructured":"Ankit, K.S., Hassan, F.: Slim-cnn: a light-weight cnn for face attribute prediction. In: 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020), pp. 329\u2013335 (2020)","DOI":"10.1109\/FG47880.2020.00085"},{"key":"1095_CR49","doi-asserted-by":"crossref","unstructured":"Li, K., Zhang, J., Shan, S.: Learning shape-appearance based attributes representation for facial attribute recognition with limited labeled data. In: 2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021), pp. 1\u20138 (2021)","DOI":"10.1109\/FG52635.2021.9667063"},{"key":"1095_CR50","first-page":"1097","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Adv. Neural. Inf. Process. Syst. 25, 1097\u20131105 (2012)","journal-title":"Adv. Neural. Inf. Process. Syst."}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-023-01095-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-023-01095-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-023-01095-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T04:31:21Z","timestamp":1729312281000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-023-01095-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,25]]},"references-count":50,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,8]]}},"alternative-id":["1095"],"URL":"https:\/\/doi.org\/10.1007\/s00530-023-01095-w","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"type":"print","value":"0942-4962"},{"type":"electronic","value":"1432-1882"}],"subject":[],"published":{"date-parts":[[2023,4,25]]},"assertion":[{"value":"25 September 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 April 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 April 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}