Fisher Vector Faces in the Wild

By Karen Simonyan, Omkar M. Parkhi, Andrea Vedaldi, Andrew Zisserman. 2013

487 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

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

Citations in the corpus

Multi-view Convolutional Neural Networks for 3D Shape Recognition (2015, methodology): “We use the large-margin metric learning algorithm and implementation from [32], with p < d to make the final descriptor compact (p = 128 in our experiments).”
Fisher Vectors Derived from Hybrid Gaussian-Laplacian Mixture Models for Image Annotation (2014, positive): “However, the leading pooling technique in recent years is the Fisher Vector [32], which provided state-of-the-art results on many different applications [38, 31, 2, 33].”
Deeply learned face representations are sparse, selective, and robust (2014, background): “Only very recently, deep learning achieved great success on face recognition [27, 25, 23] and significantly outperformed systems using low level features [2, 22, 6, 4].”
Deep Face Recognition (2015, methodology): “Fisher Vector Faces in the Wild.”
Multi-Task Convolutional Neural Network for Pose-Invariant Face Recognition (2017, unknown): “ts and the losses of each task for m-CNN and p-CNN models during the training process. TABLE III MULTI-PIE PERFORMANCE COMPARISON IN SETTING III OF TABLE I. Avg. 90 75 60 45 30 15 Fisher Vector [41] 66.60 24.53 45.51 68.71 80.33 87.21 93.30 FIP 20 [61] 67:87 34:13 47:32 61:64 78:89 89:23 95:88 FIP”
Locally-Transferred Fisher Vectors for Texture Classification (2017, background): “For example, dimensionality reduction with a large margin construct is designed and shows improvement in face recognition over the high-dimensional FV descriptor [23].”
RNN Fisher Vectors for Action Recognition and Image Annotation (2015, background): “C V ] 12 D ec Recurrent Neural Networks (RNNs) have had considerable success in classifying and predicting sequences.”
A Comprehensive Survey on Pose-Invariant Face Recognition (2015, background): “Recent studies [Li et al. 2014; Zhu et al. 2014a] reveal that the best NFFR algorithms [Chen et al. 2013; Taigman et al. 2009; Simonyan et al. 2013; Li et al. 2013] on LFW perform poorly in recognizing faces with large poses.”
Face Recognition Systems: A Survey (2020, methodology): “ Fisherface and linear discriminative analysis (LDA) [64,65]: The Fisherface method is based on the same principle of similarity as the Eigenfaces method.”
Hybrid Deep Learning for Face Verification (2013, methodology): “To handle large-scale data with complex distributions, large amount of over-completed features may need to be extracted from the face [12, 7, 25].”
Deep Fisher Networks for Large-Scale Image Classification (2013, methodology): “Since FV was shown to outperform other encodings [6] and achieve very good performance on various image recognition benchmarks [21, 28], we use it as the basis of our framework.”
High-fidelity Pose and Expression Normalization for face recognition in the wild (2015, methodology): “Fisher vector [41], Learning Based Descriptor [17] and Probabilistic Elastic Matching [32] use unsupervised learning techniques to learn encoders from training examples.”
Unconstrained face verification using deep CNN features (2015, methodology): “For the JANUS CS2 dataset, we compare the results of our DCNN method with the FV approach proposed in [21] and two other commercial off-the-shelf matchers, COTS1 and GOTS [16].”
DeepFace: Closing the Gap to Human-Level Performance in Face Verification (2014, background): “LFW-a [29]) help to improve recognition algorithms by providing a normalized input [26].”
Discriminative Deep Metric Learning for Face Verification in the Wild (2014, methodology): “Typical face feature descriptors include SIFT [22], LBP [1], probabilistic elastic matching (PEM) [21], and fisher vector faces [28].”