Learning Discriminant Face Descriptor

By Zhen Lei, Matti Pietikäinen, S. Li. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014

348 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/7bdcd85efd1e3ce14b7934ff642b76f017419751

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

In Signal Processing

1. Zhen Lei
2. Ran He
3. Xiaoming Liu
4. S. Li
5. Weihong Deng
6. Zhenan Sun
7. Sébastien Marcel
8. Anil K. Jain

Citations in the corpus

• Learning LBP structure by maximizing the conditional mutual information (2015, background): “In [36], Lei et al. proposed to iteratively learn discriminant image filters and neighborhood sampling strategy.”
• Unconstrained Face Recognition: Identifying a Person of Interest From a Media Collection (2014, background): “, [19]–[24]) have reported performance on the LFW database, but all of them can be grouped in to single media (single image vs.”
• Learning Face Representation from Scratch (2014, methodology): “Before CNN becomes popular, many good filter learning methods [19, 14] were proposed to learn the parameters of two-layer models but they are difficult to generalize to deep architectures.”
• Learning Compact Binary Face Descriptor for Face Recognition (2015, methodology): “Moreover, we observe that our CBFD is more efficient DFD in terms of the feature extraction time.”
• Local binary features for texture classification: Taxonomy and experimental study (2017, methodology): “The DFD descriptor performs well in face identi fi cation and veri fi cation, however it involves a number of parameters, has high dimensionality, a time consuming training process, and high training data needs”
• Extended local binary patterns for face recognition (2016, methodology): “The DFD method was the only one to perform similarly, however it is quite complex, involving”
• Labeled Faces in the Wild: A Survey (2016, background): “11 Learning Discriminant Face Descriptor for Face Recognition, 2014 [58]”
• Multi-Directional Multi-Level Dual-Cross Patterns for Robust Face Recognition (2014, background): “More recently, there has been increased demand for recognition of unconstrained face images, such as those collected from the internet [1] or captured by mobile devices and surveillance cameras [2].”
• Wasserstein CNN: Learning Invariant Features for NIR-VIS Face Recognition (2017, methodology): “The results of LCFS, C-DFD and CDFL are from [12], and those of the remaining compared methods are from their published papers.”
• Deep Face Recognition: A Survey (2018, background): “In the early 2010s, learning-based local descriptors were introduced to the FR community [21][89][22], in which local filters are learned for better distinctiveness, and the encoding codebook is learned for better compactness.”
• Robust Face Recognition via Multimodal Deep Face Representation (2015, background): “Representative learning-based descriptors include Binarised Statistical Image Features (BSIF) [7], [14] and Discriminant Face Descriptor (DFD) [15], et al. .”