Bayesian Face Revisited: A Joint Formulation

By Dong Chen, Xudong Cao, Liwei Wang, Fang Wen. 2012

436 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

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

In Signal Processing

Citations in the corpus

FaceNet: A unified embedding for face recognition and clustering (2015, methodology): “Both PCA and a Joint Bayesian model [2] that effectively correspond to a linear transform in the embedding space are employed.”
Learning to Compare: Relation Network for Few-Shot Learning (2017, background): “Also related are conventional metric learning approaches [26, 7] that focus on learning a shallow (linear) Mahalanobis metric for a fixed feature representa-”
Deep Learning Face Representation by Joint Identification-Verification (2014, methodology): “Using the learned feature representation and a recently proposed face veriﬁcation model [3], we achieved the highest 99 .”
The MegaFace Benchmark: 1 Million Faces for Recognition at Scale (2015, neutral): “Note also that [23] and [32] are contemporaneous, as their arxiv papers appeared after ours [2].”
Learning Face Representation from Scratch (2014, background): “Besides the above publicly accessible datasets, there are three large scale private datasets: Facebook’s SFC [26], CUHK’s CelebFaces [24] and MSRA’s WDRef [4].”
Naive-Deep Face Recognition: Touching the Limit of LFW Benchmark or Not? (2015, methodology): “Extensive works have been done to push the accuracy limit on it [3, 16, 4, 1, 2, 5, 11, 10, 12, 14, 13, 17, 9].”
Surpassing Human-Level Face Verification Performance on LFW with GaussianFace (2014, methodology): “Figure 4 shows the results of this combination compared with state-of-the-art methods [9, 5, 14, 47, 13, 53, 59, 1, 20, 16].”
Deeply learned face representations are sparse, selective, and robust (2014, methodology): “We also test the high-dimensional LBP features plus Joint Bayesian models [7] for comparison.”
Wasserstein CNN: Learning Invariant Features for NIR-VIS Face Recognition (2017, background): “, lightings, poses, and expressions) [18] and removing spectrum information is helpful for the NIR-VIS performance [19].”
A Light CNN for Deep Face Representation With Noisy Labels (2015, neutral): “ classiﬁers or multipatch ensemble models. Some methods in this group are often based on strong assumptions of data distributions that may not make effect on various situations, such as Joint Bayesian[2] and Gaussian Processing [13]. Although multipatch ensemble enhances robustness of features from ”
Fisher Vector Faces in the Wild (2013, background): “Recently, a “joint Bayesian” approach to face similarity learning has been employed in [5, 6].”
Channel-Level Acceleration of Deep Face Representations (2015, methodology): “Afterwards, we train a Joint Bayesian model [35] based on these extracted features for the face verification task.”
Similarity Metric Learning for Face Recognition (2013, methodology): “Shifting to the unrestricted setting, our method achieves 90.75%, which is competitive with the current state-of-the-art result 90.90% in [4].”
RepMet: Representative-based metric learning for classification and one-shot object detection (2018, methodology): “To that end, a non-parametric approach such as k-Nearest-Neighbors (k-NN) is commonly used to model the class distributions in the learned embedding space [38, 35, 30], though in some cases parametric models are also used [4].”
Sketch-a-Net: A Deep Neural Network that Beats Humans (2016, background): “JB (Chen et al. 2012), initially designed for face verification, were designed to fully explore such inter-model correlations.”
Probabilistic Elastic Matching for Pose Variant Face Verification (2013, background): “In recent years, we have witnessed more and more research efforts on face recognition under uncontrolled settings [21, 14, 18, 29, 7].”
Unconstrained face verification using deep CNN features (2015, methodology): “In the first category, Ahonen et al. [1] showed that the Local Binary Pattern (LBP) is effective for face recognition.”