Probabilistic Elastic Matching for Pose Variant Face Verification

By Haoxiang Li, Gang Hua, Zhe L. Lin, Jonathan Brandt, Jianchao Yang. 2013

228 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Probabilistic & Bayesian Methods

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 Probabilistic & Bayesian Methods

Citations in the corpus

CrossTransformers: spatially-aware few-shot transfer (2020, background): “Part-based correspondences for recognition [103] have been particularly successful in fine-grained face retrieval and recognition [48, 95].”
Surpassing Human-Level Face Verification Performance on LFW with GaussianFace (2014, methodology): “Face verification, which is the task of determining whether a pair of face images are from the same person, has been an active research topic in computer vision for decades [28, 22, 46, 5, 47, 31, 14, 9].”
A Comprehensive Survey on Pose-Invariant Face Recognition (2015, methodology): “…[Wiskott et al. 1997; Chen et al. 2013; Ding et al. 2015]; (c) tight semantic correspondence realized with various techniques, for example, 3D face model [Li et al. 2009; Yi et al. 2013], GMM [Li et al. 2013], MRF [Arashloo and Kittler 2011], and stereo matching [Castillo and Jacobs 2011b].”
High-fidelity Pose and Expression Normalization for face recognition in the wild (2015, methodology): “The feature level normalization aims at designing face representations with robustness to pose and expression variations [21, 32, 44, 35, 42].”
DeepFace: Closing the Gap to Human-Level Performance in Face Verification (2014, unknown): “2 APEM+FUSION [22] 79.”
Probabilistic Face Embeddings (2019, background): “Meanwhile, some studies [19, 9] have attempted to build a fuzzy model of a given face using the features of face parts.”
Do We Really Need to Collect Millions of Faces for Effective Face Recognition? (2016, background): “Exploiting pose augmentation at test time: The Achilles heel of many face recognition systems is cross pose face matching; particularly when one of the two images is viewed at an extreme, near profile angle [43,20,6].”
Comparator Networks (2018, background): “In [20], the face image is densely partitioned into overlapping patches at multiple scales, and each of the patches is represented by local features, such as Local Binary Pattern (LBP) or SIFT, then represented as a bag of spatial-appearance features by clustering.”
Labeled Faces in the Wild: A Survey (2016, methodology): “4 The training and testing work-flow of the probabilistic elastic matching [60].”
Learning Expressionlets on Spatio-temporal Manifold for Dynamic Facial Expression Recognition (2014, methodology): “Inspired by [10, 16], we employ a Gaussian Mixture Model (GMM) to learn the UMM by estimating the appearance and location distribution of all the 3D block features.”
Automated Facial Trait Judgment and Election Outcome Prediction: Social Dimensions of Face (2015, background): “[31], emotional state [11, 10], and identity [38, 22], each of which has been studied intensively both in human perception and computer vision.”
Neural Aggregation Network for Video Face Recognition (2016, background): “Video face recognition has caught more and more attention from the community in recent years [29, 17, 30, 5, 20, 18, 19, 21, 10, 26, 23].”
Frontal to profile face verification in the wild (2016, unknown): “47% in restricted settings) and [21] (84.”