Corpus ID: 231861888

Searching for Alignment in Face Recognition

@article{Xu2021SearchingFA,
  title={Searching for Alignment in Face Recognition},
  author={Xiaqing Xu and Qiang Meng and Yunxiao Qin and Jianzhu Guo and Chenxu Zhao and Feng Zhou and Zhen Lei},
  journal={ArXiv},
  year={2021},
  volume={abs/2102.05447}
}
A standard pipeline of current face recognition frameworks consists of four individual steps: locating a face with a rough bounding box and several fiducial landmarks, aligning the face image using a pre-defined template, extracting representations and comparing. Among them, face detection, landmark detection and representation learning have long been studied and a lot of works have been proposed. As an essential step with a significant impact on recognition performance, the alignment step has… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 41 REFERENCES
Recursive Spatial Transformer (ReST) for Alignment-Free Face Recognition
  • 35
  • PDF
FaceNet: A unified embedding for face recognition and clustering
  • 6,101
  • PDF
DeepFace: Closing the Gap to Human-Level Performance in Face Verification
  • 4,327
  • PDF
Are External Face Features Useful for Automatic Face Classification?
  • 21
Pushing the frontiers of unconstrained face detection and recognition: IARPA Janus Benchmark A
  • 501
  • Highly Influential
  • PDF
Attentional Feature-Pair Relation Networks for Accurate Face Recognition
  • 10
  • PDF
Deep Learning Face Representation by Joint Identification-Verification
  • 1,628
  • PDF
S^3FD: Single Shot Scale-Invariant Face Detector
  • 264
  • PDF
Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments
  • 71
  • Highly Influential
  • PDF
Large-Scale Bisample Learning on ID Versus Spot Face Recognition
  • 21
  • PDF
...
1
2
3
4
5
...