Frontal to profile face verification in the wild

By Soumyadip Sengupta, Jun-Cheng Chen, Carlos Domingo Castillo, Vishal M. Patel, Ramalingam Chellappa, David W. Jacobs. IEEE Workshop/Winter Conference on Applications of Computer Vision, 2016

842 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/100105d6c97b23059f7aa70589ead2f61969fbc3

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

Quality-Agnostic Image Recognition via Invertible Decoder (2021, methodology): “Accuracy (%) on face benchmarks such as AgeDB-30 [34] and CFP-FP [39] in four resolution types.”
RetinaFace: Single-stage Dense Face Localisation in the Wild (2019, background): “LFW [24], CFP-FP [46], AgeDB-30 [35] and IJBC [34]), and keep the embedding network (i.”
ArcFace: Additive Angular Margin Loss for Deep Face Recognition (2018, background): “LFW [10] 5,749 13,233 CFP-FP [28] 500 7,000 AgeDB-30 [19] 568 16,488 CPLFW [44] 5,749 11,652 CALFW [45] 5,749 12,174 YTF [38] 1,595 3,425”
Multi-Task Convolutional Neural Network for Pose-Invariant Face Recognition (2017, methodology): “We achieve comparable or superior performance to state-of-the-art methods on Multi-PIE, LFW [13], CFP [29], and IJB-A [19].”
ElasticFace: Elastic Margin Loss for Deep Face Recognition (2021, methodology): “CFP-FP evaluation contains 3500 genuine pairs and 3500 imposter pairs.”
VarGFaceNet: An Efficient Variable Group Convolutional Neural Network for Lightweight Face Recognition (2019, methodology): “In Tabel 4, the plain VarGNet has lower accuracy in LFW, CFP-FP, AgeDB-30.”
Circle Loss: A Unified Perspective of Pair Similarity Optimization (2020, methodology): “For evaluation, we adopt MegaFace Challenge 1 (MF1) [12], IJB-C [17], LFW [10], YTF [37] and CFPFP [23] datasets and the official evaluation protocols are used.”
The Shallow End: Empowering Shallower Deep-Convolutional Networks through Auxiliary Outputs (2016, methodology): “We adopt the large-scale data set MS1M [8] as the training data and four benchmark data sets as the validation data, including LFW [20], CFP-FP [38], AgeDB-30 [31], and MegaFace [21].”
SphereFace Revived: Unifying Hyperspherical Face Recognition (2021, neutral): “8M train LFW [77] 5,749 13,233 validation AgeDB-30 [78] 568 16,488 validation CALFW [79] 5,749 11,652 validation CPLFW [80] 5,749 12,174 validation CFP [81] 500 7,000 validation VGGFace2_test [75] 500 173k validation IJB-B [82] 1,845 76.”
Unsupervised Domain-Specific Deblurring via Disentangled Representations (2019, methodology): “We evaluate the proposed approach on three datasets: CelebA dataset [20], BMVC Text dataset [9], and CFP dataset [34].”
AdaFace: Quality Adaptive Margin for Face Recognition (2022, methodology): “• High Quality: LFW [11], CFP-FP [27], CPLFW [43] AgeDB [25] and CALFW [44] are popular benchmarks for FR in the well controlled setting.”
Exclusivity-Consistency Regularized Knowledge Distillation for Face Recognition (2020, methodology): “– We conduct extensive experiments on a variety of face recognition benchmarks, including LFW [17], CALFW [59], CPLFW [60], SLLFW[8], AgeDB [32], CFP [38], RFW [43], MegaFace [20], Trillion-Pairs [6] and IQIYI-VID [30] have verified the superiority of our approach over the state-of-the-arts.”
Global-Local GCN: Large-Scale Label Noise Cleansing for Face Recognition (2020, methodology): “Ten-fold verification sets [12, 17, 26, 35, 40, 55, 56] are used to test face verification accuracy.”
Past, Present, and Future of Face Recognition: A Review (2020, neutral): “This model is trained using a self-collected dataset constructed from three standard datasets: LFW, CFP, and CASIA-WebFace, employing three classes of facial image capture: left, front, and right side.”
Deep Face Recognition: A Survey (2018, background): “For example, CALFW [188], MORPH [189], CACD [191] and FG-NET [194] are commonly used datasets with different age range; CFP [182] only focuses on frontal and profile face, CPLFW [181] is extended from LFW and contains different poses.”