Deformable Model Fitting by Regularized Landmark Mean-Shift

By Jason M. Saragih, Simon Lucey, Jeffrey F. Cohn. International Journal of Computer Vision, 2010

904 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/4998462014c907c519ae801af39cf58a4c538bc9

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

Non-contact video-based pulse rate measurement on a mobile service robot (2014, background): “Since detailed explanation lies above the scope of this paper, the interested reader is referred to [20].”
Modeling Facial Geometry Using Compositional VAEs (2018, methodology): “They have been successfully used to overcome the ambiguities associated with monocular face tracking [24, 2, 8, 14, 15, 9, 32].”
HyperFace: A Deep Multi-Task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition (2019, methodology): “AAM) [57], Constrained Local Model (CLM) [36], Oxford facial landmark detector [9], Zhu [57], FaceDPL [58], JointCascade [5], 1. http://vis-www.cs.umass.edu/fddb/results.html CDM [52], RCPR [3], ESR [4], SDM [46] and 3DDFA [56].”
Face Alignment at 3000 FPS via Regressing Local Binary Features (2014, methodology): “Instead of modeling holistic appearance, “Constrained Local Model” [ 8, 9, 10, 1, 35, 29, 34, 26] learns a set of local experts (detectors [9, 31, 24, 1, 34] or regressors [ 10, 29, 11]) and constrains them using various shape models.”
Realtime facial animation with on-the-fly correctives (2013, methodology): “These include active appearance model [Cootes et al. 1998], Eigen points [Covell and Bregler 1996], the more recent landmark prediction techniques of Saragih and colleagues [Saragih et al. 2011], and the commercial solution, Live Driver, from Image Metrics [ImageMetrics 2012].”
OpenFace: An open source facial behavior analysis toolkit (2016, methodology): “Furthermore, even though there exist a number of ap- Tool Approach Landmark Head pose AU Gaze Train Fit Binary Real-time COFW[13] RCPR[13] FaceTracker CLM[50] dlib [34] [32] DRMF[4] DRMF[4] Chehra [5] GNDPM GNDPM[58] PO-CR[57] PO-CR [57] Menpo [3] AAM, CLM, SDM”
Look at Boundary: A Boundary-Aware Face Alignment Algorithm (2018, methodology): “In the literature of face alignment, besides classic meth-ods (ASMs [34, 23], AAMs [13, 41, 33, 25], CLMs [29, 42] and Cascaded Regression Models [7, 5, 58, 8, 72, 73, 18]), recently, state-of-the-art performance has been achieved with Deep Convolutional Neural Networks (DC-NNs).”
Constrained Local Neural Fields for Robust Facial Landmark Detection in the Wild (2013, methodology): “…is the Regularised Landmark Mean Shift [15] which finds a least squares solution to the following 1: argmin Δp (||p0 +Δp||2Λ−1 + ||JΔp0 − v||2), (5) where J is the Jacobian of the landmark locations with respect to the parameter vector p evaluated at p, Λ−1 is the matrix describing the prior on…”
Facial Landmark Detection: A Literature Survey (2018, methodology): “In the deterministic view point, CLM [24][84] ﬁnds the landmarks by minimizing the misalignment errors subject to the shape patterns: Here, x d represents the positions of diﬀerent landmarks in x .”
TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Tracking (2015, methodology): “, [x, y, t] with a kernel of size [32, 32, 200]).”
MoFA: Model-Based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction (2017, methodology): “Sparse Landmark Alignment In addition to dense photometric alignment, we propose an optional surrogate loss based on detected facial landmarks [46].”
3D Constrained Local Model for rigid and non-rigid facial tracking (2012, methodology): “Logistic regressor response maps [23, 27] using intensity contain strong responses along the edges, making it hard to find the actual feature position.”
Automatic facial expression recognition using features of salient facial patches (2015, background): “[29] who proposed Regularized Landmark Mean Shift (RLMS) algorithm with improved landmark localization accuracy.”
State of the Art on Monocular 3D Face Reconstruction, Tracking, and Applications (2018, methodology): “Online methods target teleconferencing scenarios and focus on driving target rigs (usually non-human avatars) with coarse-scale facial deformation or motion parameters to produce plausible animations [BWP13, CWLZ13, CHZ14, CXH03, LYYB13,SLC11a,WBLP11] (see Fig.”
Self-Supervised Multi-level Face Model Learning for Monocular Reconstruction at Over 250 Hz (2017, methodology): “We exploit this by using a weak supervision in the form of automatically detected 66 facial landmarks f ∈ F ⊂ R(2) [53] and associated confidence cf ∈ [0, 1] (1 confident).”
Automatic Analysis of Facial Actions: A Survey (2019, neutral): “the SVM margin [153].”