Face Alignment at 3000 FPS via Regressing Local Binary Features

By Shaoqing Ren, Xudong Cao, Yichen Wei. 2014

880 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

FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age (2019, background): “…image datasets [22, 31, 13, 69, 37, 24, 41, 68, 15, 27, 46, 8, 39] have been proposed and fostered research and development for automated face detection [35, 21], alignment [66, 44], recognition [57, 49], generation [67, 5, 26, 58], modiﬁcation [3, 32, 19], and attribute classiﬁcation [31, 37].”
3FabRec: Fast Few-Shot Face Alignment by Reconstruction (2019, neutral): “ruth landmarks, and with predicted landmark heatmaps, respectively. The ﬁfth column illustrates a failure case. 7 AFLW 300-W Method Full Frontal Com Chall. Full SDM [55] 4.05 2.94 5.57 15.40 7.52 LBF [40] 4.25 2.74 4.95 11.98 6.32 CFSS [61] 3.92 2.68 4.73 9.98 5.76 Two-Stage [29] 2.17 - 4.36 7.56 4.”
Facial Landmark Detection: A Literature Survey (2018, methodology): “In the existing methods (Ren et al. 2014), it is only shown that the cascaded regression methods can improve the performance over different cascaded stages, but it doesn’t know when to stop.”
AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild (2017, methodology): “A face alignment algorithm via regression local binary features [29],”
3D Face Reconstruction by Learning from Synthetic Data (2016, background): “As landmark detection algorithms have become faster and robust [13, 21, 25, 26] it is now common to use them for facial reconstruction.”
Face Alignment in Full Pose Range: A 3D Total Solution (2015, methodology): “training codes, including RCPR [42], ESR [10], LBF [35], CFSS [36], SDM [71], MDM [29], RMFA [72] and TSPM [18].”
High-Resolution Representations for Labeling Pixels and Regions (2019, neutral): “LBF [80] 4.”
Unsupervised Discovery of Object Landmarks as Structural Representations (2018, methodology): “For human faces, there are active appearance models [10, 38, 11], template-based methods [42, 83], regression-based methods [61, 12, 7, 48], and more recent methods based on deep neural networks [55, 77, 81, 82, 75, 70, 68, 33, 71].”
HyperFace: A Deep Multi-Task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition (2019, methodology): “Following the protocol described in [43], we use 3, 148 faces with 68-point annotations for training.”
Unsupervised Learning of Object Landmarks by Factorized Spatial Embeddings (2017, methodology): “Results on MAFL test set in terms of the inter-ocular distance as in [74, 52].”
Deep Alignment Network: A Convolutional Neural Network for Robust Face Alignment (2017, methodology): “The main differences between the variety of CSR based methods introduced in the literature lie in the choice of the feature extraction method φ and the regression method r t .”
Self-supervised learning of a facial attribute embedding from video (2018, neutral): “ebA Jakab et al. [21] (2018) – 3.08 Zhang et al. [64] (2018) – 3.15 Thewlis et al. [51] (2017) 9.30 6.67 Thewlis et al. [52] (2017) 7.97 5.83 Supervised Trained on CelebA MTCNN [65] (2014) – 5.39 LBF [45] (2014) 6.32 – CFSS [69] (2015) 5.76 – cGPRT [29] (2015) 5.71 – DDN [60] (2016) 5.65 – TCDCN [66”
An All-In-One Convolutional Neural Network for Face Analysis (2016, methodology): “7(a) shows comparisons with recently published methods such as CCL [57], HyperFace [36], LBF [38], SDM [47], ERT [22] and RCPR [1].”
Style Aggregated Network for Facial Landmark Detection (2018, background): “, a regressor, to map the features to the landmark locations [64, 10, 7, 42, 72, 67, 40].”