Face recognition across pose: A review

By Xiaozheng Zhang, Yongsheng Gao. Pattern Recognition, 2009

534 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/27cad662bbe099539f74d5edb434007bea66f393

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Xiaogang Wang
3. Luc Van Gool
4. Xiaoou Tang
5. Yi Yang
6. Ming-Hsuan Yang
7. Bernt Schiele
8. Yu Qiao

In Signal Processing

1. Weihong Deng
2. Mei Wang
3. Xiaoou Tang
4. Xiaoming Liu
5. Dacheng Tao
6. Xiaogang Wang
7. Ping Luo
8. Changxing Ding

Citations in the corpus

• Face Recognition Across Non-Uniform Motion Blur, Illumination, and Pose (2015, background): “A good survey article on this issue can be found in [25].”
• A review of biometric technology along with trends and prospects (2014, methodology): “An automated face recognition system establishes the identity of an individual based on the computation of 2D or 3D features (refer table 2) [84, 85].”
• Deep Face Recognition: A Survey (2018, background): “Over the past few years, there have been several surveys on FR [222], [18], [3], [78], [136] and its subdomains, including illumination-invariant FR [234], 3D FR [136], pose-invariant FR [216] and so on.”
• Deep Learning Identity-Preserving Face Space (2013, background): “In many practical applications, the pose and illumination changes become the bottleneck for face recognition [36].”
• Learning Pose-Aware Models for Pose-Invariant Face Recognition in the Wild (2019, background): “Researchers have long acknowledged that face matching techniques struggle when presented with images of faces in extremely different poses [21], [22], [23], [24].”
• Deep Metric Learning for Practical Person Re-Identification (2014, background): “Similar to the history of face recognition [15], the future direction of feature representation must be based on precise body parts segmentation, person alignment and pose normalization.”
• Zero-effort payments: design, deployment, and lessons (2014, background): “However, these results are obtained by constraining subject poses to be either frontfacing [26] or constant across frames [35].”
• A Comprehensive Survey on Pose-Invariant Face Recognition (2015, background): “face recognition Zhao et al. (2003). Of the existing works, the survey on face recognition across pose Zhang and Gao (2009) that summarizes PIFR approaches before 2009 is the most relevant to this paper.”