{"type":"ScholarlyArticle","title":"Deeply-learned Hybrid Representations for Facial Age Estimation","authors":[{"name":"Zichang Tan","slug":"zichang-tan","given":"Zichang","family":"Tan","affiliation":"CBSR&NLPR , Institute of Automation , Chinese Academy of Sciences , Beijing , China; University of Chinese Academy of Sciences , Beijing , China"},{"name":"Yang Yang","slug":"yang-yang","given":"Yang","family":"Yang","affiliation":"CBSR&NLPR , Institute of Automation , Chinese Academy of Sciences , Beijing , China; University of Chinese Academy of Sciences , Beijing , China"},{"name":"Jun Wan","slug":"jun-wan","given":"Jun","family":"Wan","affiliation":"CBSR&NLPR , Institute of Automation , Chinese Academy of Sciences , Beijing , China; University of Chinese Academy of Sciences , Beijing , China"},{"name":"Guodong Guo","slug":"guodong-guo","given":"Guodong","family":"Guo","affiliation":"Institute of Deep Learning , Baidu Research , Beijing , China; National Engineering Laboratory for Deep Learning Technology and Application , Beijing , China"},{"name":"Stan Z. Li","slug":"stan-z-li","given":"Stan Z.","family":"Li","affiliation":"CBSR&NLPR , Institute of Automation , Chinese Academy of Sciences , Beijing , China; University of Chinese Academy of Sciences , Beijing , China; Faculty of Information Technology , Macau University of Science and Technology , Macau , China"}],"abstract":"In this paper, we propose a novel unified network named Deep Hybrid-Aligned Architecture for facial age estimation. It contains global, local and global-local branches. They are jointly optimized and thus can capture multiple types of features with complementary information. In each branch, we employ a separate loss for each sub-network to extract the independent features and use a recurrent fusion to explore correlations among those region features. Considering that the pose variations may lead to misalignment in different regions, we design an Aligned Region Pooling operation to generate aligned region features. Moreover, a new large age dataset named Web-FaceAge owning more than 120K samples is collected under diverse scenes and spanning a large age range. Experiments on five age benchmark datasets, including Web-FaceAge, Morph, FG-NET, CACD and Chalearn LAP 2015, show that the proposed method outperforms the state-of-the-art approaches significantly.","doi":"10.24963/ijcai.2019/492","url":"https://ijcai.org/proceedings/2019/492","pdf":"https://ijcai.org/proceedings/2019/0492.pdf","markdown":"https://ijcai.org/proceedings/2019/492.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/492","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Machine Learning M-Z","track":"Main track","number":492,"pages":{"first":3548,"last":3554},"keywords":["Computer Vision: Biometrics, Face and Gesture Recognition","Machine Learning: Deep Learning","Computer Vision: Recognition: Detection, Categorization, Indexing, Matching, Retrieval, Semantic Interpretation"],"videos":[],"references":[{"position":1,"raw":"[Agustsson et al., 2017] Eirikur Agustsson, Radu Timofte, and Luc Van Gool. Anchored regression networks applied to age estimation and super resolution. In ICCV, 2017.","title":"Anchored regression networks applied to age estimation and super resolution","authors":"Radu Eirikur Agustsson, Luc Timofte, Van Gool","year":"2017","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Chen et al., 2014] Bor-Chun Chen, Chu-Song Chen, and Winston H Hsu. Cross-age reference coding for age- invariant face recognition and retrieval. In ECCV, 2014.","title":"Cross-age reference coding for ageinvariant face recognition and retrieval","authors":"Chu-Song Bor-Chun Chen, Winston H Chen, Hsu","year":"2014","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Escalera et al., 2015] Sergio Escalera, Junior Fabian, Pablo Pardo, Xavier Baró, Jordi Gonzalez, Hugo J Escalante, Dusan Misevic, Ulrich Steiner, and Isabelle Guyon. Chalearn looking at people 2015: Apparent age and cul- tural event recognition datasets and results. In ICCVW, 2015.","title":"Chalearn looking at people 2015: Apparent age and cultural event recognition datasets and results","authors":"Sergio Escalera, Junior Fabian, Pablo Pardo, Xavier Baró, Jordi Gonzalez, Hugo J Escalante, Dusan Misevic, Ulrich Steiner, Isabelle Guyon","year":"2015","venue":"ICCVW","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Gao et al., 2018] Bin-Bin Gao, Hong-Yu Zhou, Jianxin Wu, and Xin Geng. Age estimation using expectation of label distribution learning. IJCAI, 2018.","title":"Age estimation using expectation of label distribution learning","authors":"Gao","year":"2018","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/99"},{"position":5,"raw":"[Guo and Mu, 2013] Guodong Guo and Guowang Mu. Joint estimation of age, gender and ethnicity: Cca vs. pls. In FG, 2013.","title":"Joint estimation of age, gender and ethnicity: Cca vs","authors":"Mu Guo, Guodong Guo, Guowang Mu","year":"2013","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Guo et al., 2016] Yandong Guo, Lei Zhang, Yuxiao Hu, X- iaodong He, and Jianfeng Gao. Ms-celeb-1m: A dataset and benchmark for large-scale face recognition. In ECCV, 2016.","title":"Ms-celeb-1m: A dataset and benchmark for large-scale face recognition","authors":"Yandong Guo, Lei Zhang, Yuxiao Hu, Xiaodong He, Jianfeng Gao","year":"2016","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[He et al., 2016] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recog- nition. In CVPR, 2016.","title":"Deep residual learning for image recognition","authors":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hochreiter and Schmidhuber, 1997] Sepp Hochreiter and Jürgen Schmidhuber. Long short-term memory. Neural computation, 1997.","title":"Long short-term memory","authors":"Sepp Hochreiter, Jürgen Schmidhuber","year":"1997","venue":"Neural computation","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Jaderberg et al., 2015] Max Jaderberg, Karen Simonyan, Andrew Zisserman, et al. Spatial transformer networks. In NIPS, 2015.","title":"Spatial transformer networks","authors":"Jaderberg","year":"2015","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Li et al., 2017a] Wei Li, Farnaz Abtahi, and Zhigang Zhu. Action unit detection with region adaptation, multi- labeling learning and optimal temporal fusing. In CVPR, 2017.","title":"Action unit detection with region adaptation, multilabeling learning and optimal temporal fusing","authors":"Li","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Li et al., 2017b] Wei Li, Xiatian Zhu, and Shaogang Gong. Person re-identification by deep joint learning of multi- loss classification. IJCAI, 2017.","title":"Person re-identification by deep joint learning of multiloss classification","authors":"Li","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Li et al., 2018] Kai Li, Junliang Xing, Chi Su, Weiming Hu, Yundong Zhang, and Stephen Maybank. Deep cost- sensitive and order-preserving feature learning for cross- population age estimation. In CVPR, 2018.","title":"Deep costsensitive and order-preserving feature learning for crosspopulation age estimation","authors":"Kai Li, Junliang Xing, Chi Su, Weiming Hu, Yundong Zhang, Stephen Maybank","year":"2018","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Liu et al., 2015] Xin Liu, Shaoxin Li, Meina Kan, Jie Zhang, Shuzhe Wu, Wenxian Liu, Hu Han, Shiguang Shan, and Xilin Chen. Agenet: Deeply learned regres- sor and classifier for robust apparent age estimation. In ICCVW, 2015.","title":"Agenet: Deeply learned regressor and classifier for robust apparent age estimation","authors":"Xin Liu, Shaoxin Li, Meina Kan, Jie Zhang, Shuzhe Wu, Wenxian Liu, Hu Han, Shiguang Shan, Xilin Chen","year":"2015","venue":"ICCVW","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Maaten and Hinton, 2008] Laurens van der Maaten and Ge- offrey Hinton. Visualizing data using t-sne. JMLR, 2008.","title":"Laurens van der Maaten and Geoffrey Hinton","authors":"Hinton Maaten","year":"2008","venue":"Visualizing data using t-sne","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Niu et al., 2016] Zhenxing Niu, Mo Zhou, Le Wang, Xin- bo Gao, and Gang Hua. Ordinal regression with multiple output cnn for age estimation. In CVPR, 2016.","title":"Ordinal regression with multiple output cnn for age estimation","authors":"Zhenxing Niu, Mo Zhou, Le Wang, Xinbo Gao, Gang Hua","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Pan et al., 2018] Hongyu Pan, Hu Han, Shiguang Shan, and Xilin Chen. Mean-variance loss for deep age estimation from a face. In CVPR, 2018.","title":"Mean-variance loss for deep age estimation from a face","authors":"Pan","year":"2018","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Ren et al., 2015] Shaoqing Ren, Kaiming He, Ross Gir- shick, and Jian Sun. Faster r-cnn: Towards real-time object detection with region proposal networks. In NIPS, 2015.","title":"Faster r-cnn: Towards real-time object detection with region proposal networks","authors":"Ren","year":"2015","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Ricanek and Tesafaye, 2006] Karl Ricanek and Tamirat Tesafaye. Morph: A longitudinal image database of nor- mal adult age-progression. In FG, 2006.","title":"Karl Ricanek and Tamirat Tesafaye. Morph: A longitudinal image database of normal adult age-progression","authors":"Tesafaye Ricanek","year":"2006","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Rothe et al., 2018] Rasmus Rothe, Radu Timofte, and Luc Van Gool. Deep expectation of real and apparent age from a single image without facial landmarks. IJCV, 2018.","title":"Deep expectation of real and apparent age from a single image without facial landmarks","authors":"Radu Rasmus Rothe, Luc Timofte, Van Gool","year":"2018","venue":"IJCV","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Shen et al., 2018] Wei Shen, Yilu Guo, Yan Wang, Kai Zhao, Bo Wang, and Alan L. Yuille. Deep regression forests for age estimation. In CVPR, 2018.","title":"Deep regression forests for age estimation","authors":"Wei Shen, Yilu Guo, Yan Wang, Kai Zhao, Bo Wang, Alan L Yuille","year":"2018","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Singh and Lee, 2016] Krishna Kumar Singh and Yong Jae Lee. End-to-end localization and ranking for relative at- tributes. In ECCV, 2016.","title":"End-to-end localization and ranking for relative attributes","authors":"Lee ; Singh, Krishna Kumar Singh, Yong Jae, Lee","year":"2016","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Tan et al., 2016] Zichang Tan, Shuai Zhou, Jun Wan, Zhen Lei, and Stan Z Li. Age estimation based on a single network with soft softmax of aging modeling. In ACCV, 2016.","title":"Age estimation based on a single network with soft softmax of aging modeling","authors":"Tan","year":"2016","venue":"ACCV","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Tan et al., 2018] Zichang Tan, Jun Wan, Zhen Lei, Ruicon- g Zhi, Guodong Guo, and Stan Z. Li. Efficient group-n encoding and decoding for facial age estimation. IEEE TPAMI, 2018.","title":"Efficient group-n encoding and decoding for facial age estimation","authors":"Tan","year":"2018","venue":"IEEE TPAMI","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Tan et al., 2019] Zichang Tan, Yang Yang, Jun Wan, Hanyuan Hang, Guodong Guo, and Li Stan Z. Attention based pedestrian attribute analysis. IEEE TIP, 2019.","title":"Attention based pedestrian attribute analysis","authors":"Zichang Tan, Yang Yang, Jun Wan, Hanyuan Hang, Guodong Guo, Li Stan, Z","year":"2019","venue":"IEEE TIP","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Wan et al., 2018] Jun Wan, Zichang Tan, Zhen Lei, Guodong Guo, and Stan Z. Li. Auxiliary demographic in- formation assisted age estimation with cascaded structure. IEEE TCYB, 2018.","title":"Auxiliary demographic information assisted age estimation with cascaded structure","authors":"Wan","year":"2018","venue":"IEEE TCYB","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Wei et al., 2017] Longhui Wei, Shiliang Zhang, Hantao Yao, Wen Gao, and Qi Tian. Glad: global-local-alignment descriptor for pedestrian retrieval. In ACM MM, 2017.","title":"Glad: global-local-alignment descriptor for pedestrian retrieval","authors":"Wei","year":"2017","venue":"ACM MM","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Yang et al., 2018] Tsun-Yi Yang, Yi-Hsuan Huang, Yen-Yu Lin, Pi-Cheng Hsiu, and Yung-Yu Chuang. Ssr-net: A compact soft stagewise regression network for age estima- tion. In IJCAI, 2018.","title":"Ssr-net: A compact soft stagewise regression network for age estimation","authors":"Tsun-Yi Yang, Yi-Hsuan Huang, Yen-Yu Lin, Pi-Cheng Hsiu, Yung-Yu Chuang","year":"2018","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/150"},{"position":28,"raw":"[Yi et al., 2014] Dong Yi, Zhen Lei, and Stan Z Li. Age es- timation by multi-scale convolutional network. In ACCV, 2014.","title":"Age estimation by multi-scale convolutional network","authors":"Dong Yi, Zhen Lei, Stan Z Li","year":"2014","venue":"ACCV","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Zhao et al., 2018] Xin Zhao, Liufang Sang, Guiguang Ding, Yuchen Guo, and Xiaoming Jin. Grouping attribute recog- nition for pedestrian with joint recurrent learning. In IJ- CAI, 2018.","title":"Grouping attribute recognition for pedestrian with joint recurrent learning","authors":"Xin Zhao, Liufang Sang, Guiguang Ding, Yuchen Guo, Xiaoming Jin","year":"2018","venue":"IJ-CAI","doi":null,"url":null,"internal_url":"/proceedings/2018/441"},{"position":30,"raw":"[Zhu et al., 2015] Yu Zhu, Yan Li, Guowang Mu, and Guodong Guo. A study on apparent age estimation. In ICCVW, 2015.","title":"A study on apparent age estimation","authors":"Yu Zhu, Yan Li, Guowang Mu, Guodong Guo","year":"2015","venue":"ICCVW","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}