Feature Detection and Tracking with Constrained Local Models

By David Cristinacce, Tim Cootes. British Machine Vision Conference, 2006

828 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/995b2868326837cde96e01390f87b2dee6239bdb

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

3D Constrained Local Model for rigid and non-rigid facial tracking (2012, methodology): “Constrained Local Model (CLM) [10] techniques use the same PDM formulation.”
A Semi-automatic Methodology for Facial Landmark Annotation (2013, methodology): “This is the first attempt to create a tool suitable for annotating massive facial databases.”
A Main Directional Mean Optical Flow Feature for Spontaneous Micro-Expression Recognition (2016, methodology): “…feature for micro-expression recognition , we first detect and divide the face region into ROIs in video clips by utilizing a set of facial feature points obtained from an instance, called discriminative response map fitting (DRMF) [24], of the constrained local models [25], [26] (Section 3.1).”
Optimization on a Budget: A Reinforcement Learning Approach (2008, methodology): “The approach outlined in this document could in principle learn to combine these two methods to perform efficient optimization.”
Prediction of the Leadership Style of an Emergent Leader Using Audio and Visual Nonverbal Features (2017, neutral): “This method first finds facial landmarks per participant using the Constrained Local Model (CLM) [68] which converts the facial”
Dog Breed Classification Using Part Localization (2012, background): “A good deal of work has also addressed the localization of ﬁducial points and parts of human faces [20–22 , 6].”
Facial point detection using boosted regression and graph models (2010, methodology): “Our method is also more accurate than the current state of the art in facial point detecti on [3, 14, 23].”
Facial Landmark Detection: A Literature Survey (2018, methodology): “5, the CLM methods (Cristinacce and Cootes 2006;Saragih et al. 2011) infer the landmark locations x based on the global facial shape patterns as well as the independent local appearance information around each landmark,”
Automatic facial expression recognition using features of salient facial patches (2015, background): “However, these methods usually require very accurate and reliable detection as well as tracking of the facial landmarks which are difficult to achieve in many practical situations.”
Deformable Model Fitting by Regularized Landmark Mean-Shift (2010, methodology): “Examples of the misalignment error functions include the Mahalanobis distance over local patch appearance (Cootes and Taylor 1992) and the boosted Harr-like feature based classifier (Cristinacce and Cootes 2006).”
Image and Vision Computing (2016, neutral): “…further divided to those that use discriminative response map functions, such as Active Shape Models (ASMs) [14], Constrained Local Models (CLMs) [15–17] and Deformable Part Models (DPMs) [18], those that learn a cascade of regression functions, such as Supervised Descent Method (SDM) [19] and…”
Constrained Local Neural Fields for Robust Facial Landmark Detection in the Wild (2013, background): “One of the most promising is the Constrained Local Model (CLM) proposed by Cristinacce and Cootes [5], and various extensions that followed [1, 3, 15, 20].”
Face detection, pose estimation, and landmark localization in the wild (2012, methodology): “This makes our overall model linear in the number of parts and the size of the image, similar to other models such as AAMs and CLMs.”
Deep Alignment Network: A Convolutional Neural Network for Robust Face Alignment (2017, methodology): “Face alignment has a long history, starting with the early Active Appearance Models [5, 20], moving to Constrained Local Models [7, 1] and recently shifting to methods based on Cascaded Shape Regression (CSR) [32, 4, 21, 18, 16, 30, 13] and deep learning [34, 10, 29, 31, 3].”
Deeply Learning Deformable Facial Action Parts Model for Dynamic Expression Analysis (2014, methodology): “For example, in [8,9], Active Appearance Model [10] and Constrained Local Model [11] are used to encode shape and texture variations respectively.”
Object Detection Using Strongly-Supervised Deformable Part Models (2012, neutral): “Such models have been recently applied to a number of computer vision problems including object recognition [1, 7, 2], human pose estimation [8–10], action recognition [11] and facial feature detection [12].”
How Far are We from Solving the 2D & 3D Face Alignment Problem? (and a Dataset of 230,000 3D Facial Landmarks) (2017, background): “Traditionally, the metric used for face alignment is the point-to-point Euclidean distance normalized by the interocular distance [10, 29, 33].”
State of the Art on Monocular 3D Face Reconstruction, Tracking, and Applications (2018, methodology): “Local methods often use constraints to stabilize the estimation [SLC11a,CC06,BRM12,AZCP13].”
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”