Learn to Combine Multiple Hypotheses for Accurate Face Alignment

By Junjie Yan, Zhen Lei, Dong Yi, S. Li. 2013

133 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

Cascade R-CNN: Delving Into High Quality Object Detection (2017, methodology): “The difficult regression task can be decomposed into a sequence of simpler steps, inspired by the works of cascade pose regression [6] and face alignment [2, 35].”
Nonlinear 3D Face Morphable Model (2018, unknown): “state-of-the-art methods, SDM [41] and 3DDFA [45], on the AFLW2000 dataset.”
HyperFace: A Deep Multi-Task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition (2019, unknown): “These include both regression-based [4], [26], [52], [55], [56], [57] and model-based [7], [35], [40] methods.”
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].”
Image and Vision Computing (2016, unknown): “Alignment using dense (a) Baltrusaitis et al. [41] (b) Hasan et al. [42] (c) Jaiswal et al. [43] (d) Milborrow et al. [45] (e) Yan et al. [47] (f) Zhou et al. [48] (g) Ground truth landmark mark-ups is much more diﬃcult and the performance would get worse.”
Adaptive 3D Face Reconstruction from Unconstrained Photo Collections (2017, methodology): “To estimate 2D landmarks, we employ the state-of-the-art cascade of regressors approach [17] to automatically fit q1⁄468 landmarks denoted as W 2 R(2) q onto each image.”
Mnemonic Descent Method: A Recurrent Process Applied for End-to-End Face Alignment (2016, unknown): “[58] Intra-face [56] Chehra [3] ERT PO-CR”