Mnemonic Descent Method: A Recurrent Process Applied for End-to-End Face Alignment

By George Trigeorgis, Patrick Snape, Mihalis A. Nicolaou, Epameinondas Antonakos, Stefanos P. Zafeiriou. Computer Vision and Pattern Recognition, 2016

362 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/aa99593486a1649f520f7c3a78d424de2c4d04e6

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

DenseReg: Fully Convolutional Dense Shape Regression In-the-Wild (2016, methodology): “Given the lack of state-of-the-art deformable models on human ear, we compare DenseReg with DenseReg+AAM and DenseReg+MDM.”
From Facial Expression Recognition to Interpersonal Relation Prediction (2016, background): “2015a), face landmark detection (Zhang et al. 2015a; Zhu et al. 2016; Trigeorgis et al. 2016), face attribute recognition (Liu et al.”
Deforming Autoencoders: Unsupervised Disentangling of Shape and Appearance (2018, background): “In the context of deep learning several works have aimed at incorporating deformations and alignment in a supervised setting, including Spatial Transformers [15], Deep Epitomic Networks [16], Deformable CNNs [17], Mass Displacement Networks [18], Mnemonic Descent [19], or Densereg [20].”
Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression (2019, neutral): “…7.69 SDM CVPR 13 [63] 5.57 15.40 7.50 LBF CVPR 14 [45] 4.95 11.98 6.32 CFSS CVPR 15 [71] 4.73 9.98 5.76 TCDCN 16’ [70] 4.80 8.60 5.54 MDM CVPR 16 [54] 4.83 10.14 5.88 RAR ECCV 16 [62] 4.12 8.35 4.94 DVLN CVPR 17 [59] 3.94 7.62 4.66 TSR CVPR 17 [37] 4.36 7.56 4.99 DSRN CVPR 18 [41] 4.12 9.68 5.21…”
Whole-Body Human Pose Estimation in the Wild (2020, neutral): “For facial keypoint localization, cascaded networks [6,55,58,66] and multi-task learning [57,68] are widely adopted.”
Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks (2017, methodology): “C V ] 2 3 O ct 2 ing deep neural networks, different network types have been explored, such as the Convolutional Neural Network (CNN) [55], Auto-Encoder Network [73] and Recurrent Neural Network (RNN) [58, 64].”
Style Aggregated Network for Facial Landmark Detection (2018, methodology): “08 error is also employed for evaluation [6, 55].”
Multi-scale Fully Convolutional Network for Face Detection in the Wild (2017, background): “Facial attribute information can also help in detecting faces [40, 3, 31].”
Automatic Analysis of Facial Actions: A Survey (2019, methodology): “Finally, [178] cast the cascaded regression as a Recurrent CNN and performed endto-end training of the cascade.”
How Far are We from Solving the 2D & 3D Face Alignment Problem? (and a Dataset of 230,000 3D Facial Landmarks) (2017, methodology): “We compare the performance of 2D-FAN on all the aforementioned datasets with that of an unconventional baseline: the performance of a recent state-of-the-art method, namely MDM [40] on LFPW test set, initialized with the ground truth bounding boxes.”
Face Alignment in Full Pose Range: A 3D Total Solution (2015, methodology): “including RCPR [42], ESR [10], LBF [35], CFSS [36], SDM [71], MDM [29], RMFA [72] and TSPM [18].”
PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop (2021, neutral): “To put our approach in a broader view, there have been remarkable efforts made to involve iterative fitting strategies in other computer vision tasks, including facial landmark localization [58, 52], human/hand pose estimation [39, 7], etc.”
Deep Alignment Network: A Convolutional Neural Network for Robust Face Alignment (2017, methodology): “• the mean distance between the localized landmarks and the ground truth landmarks divided by the interpupil distance (the distance between the eye centers) [30, 23],”
Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors (2018, neutral): “25 MDM [33] 4.”
3FabRec: Fast Few-Shot Face Alignment by Reconstruction (2019, background): “Current models using deep convolutional neural networks, however, quickly became the best-performing approaches, starting with deep alignment networks [42], fullyconvolutional networks [27], coordinate regression models [28, 45], or multi-task learners [36], with the deep networks being able to capt”
Look at Boundary: A Boundary-Aware Face Alignment Algorithm (2018, methodology): “For other dataset, we follow MDM [51] and [39] to use outer-eye-corner distance as the “inter-ocular” normalising factor.”
Teacher Supervises Students How to Learn From Partially Labeled Images for Facial Landmark Detection (2019, methodology): “08 error is also employed for evaluation [6, 40].”
3D Face Morphable Models "In-the-Wild" (2017, background): “During the past few years, we have witnessed significant improvements in various face analysis tasks such as face detection [19, 42] and 2D facial landmark localisation on static images [40, 21, 6, 38, 43, 4, 5, 36].”
Facial Landmark Detection: A Literature Survey (2018, background): “In [96], instead of training multiple networks in a cascaded manner, Trige-orgis et. al trained a deep convolutional Recurrent Neural Network (RNN) for end-to-end facial landmark detection to mimic the cascaded behavior.”