Deep Learning in Face Analysis

Abstract

In this talk the speaker will share recent advances on using deep learning techniques for various face analysis tasks. Specifically, he will discuss some state-of-the-art approaches to solving some of the fundamental challenges in face detection, face attribute recognition, and face hallucination. He will highlight effective techniques for training deep convolutional networks for predicting face attributes in the wild. In addition, he discuss the use of face attributes as rich contexts to facilitate accurate face detection in return. He will then present his recent work on hallucinating faces of unconstrained poses and with very low resolution. In particular, he will show how face hallucination and dense correspondence field estimation can be optimized in a unified deep network.

Biography

Chen Change Loy is a Research Assistant Professor in the Chinese University of Hong Kong. He received his PhD (2010) in Computer Science from the Queen Mary University of London. From Dec. 2010 – Mar. 2013, he was a postdoctoral researcher at Vision Semantics Ltd. He has been involved in two European FP7 computer vision projects on security and surveillance using multi-camera CCTV systems, SAMURAI (2008-2011) and GETAWAY (2011-2014). He serves as an Associate Editor for IET Computer Vision Journal. He also serves as regular reviewer for top-ranking journals (TPAMI, IJCV, TIP, TCSVT, PR) and conferences (ECCV, ICCV, CVPR, ACCV, BMVC). The book “Person Re-identification” that he co-edited has recorded over 39,000 eBook chapter downloads since its online publication on January 2014 (top 25% most downloaded eBooks in the relevant Springer eBook Collection in 2015). He is currently a member of IEEE. His research interests include computer vision and pattern recognition, with focus on face analysis, deep learning, and visual surveillance.

References

S. Zhu, S. Liu, C. C. Loy, X. Tang, " Deep cascaded bi-network for face hallucination," in Proceedings of European Conference on Computer Vision (ECCV), 2016
S. Yang, P. Luo, C. C. Loy, X. Tang, " WIDER FACE: A face detection benchmark," in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016
C. Huang, Y. Li, C. C. Loy, X. Tang, " Learning deep representation for imbalanced classification," in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016
S. Zhu, C. Li, C. C. Loy, X. Tang, " Unconstrained face alignment via cascaded compositional learning," in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016
S. Yang, P. Luo, C. C. Loy, X. Tang, " From facial part responses to face detection: A deep learning approach," in Proceedings of IEEE International Conference on Computer Vision (ICCV), 2015
Z. Zhang, P. Luo, C. C. Loy, X. Tang, "Learning deep representation for face alignment with auxiliary attributes," IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 38, no. 5, pp. 918–930, 2015
C. Dong, C. C. Loy, K. He, and X. Tang, "Image super-resolution using deep convolutional networks," IEEE Transactions on PatternAnalysis and Machine Intelligence (TPAMI), vol. 38, no. 2, pp. 295-307, 2015
S. Zhu, C. Li, C. C. Loy, X. Tang, "Face alignment by coarse-to-fine shape searching," in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015
C. Dong, C. C. Loy, K. He, X. Tang, "Learning a deep convolutional network for image super-resolution," in Proceedings of European Conference on Computer Vision (ECCV), 2014
Z. Zhang, P. Luo, C. C. Loy, X. Tang, "Facial landmark detection by deep multi-task learning," in Proceedings of European Conference on Computer Vision (ECCV), 2014

Chen-change Loy
The Chinese University of Hong Kong