Automatic feature localisation with constrained local models

By David Cristinacce, Tim Cootes. Pattern Recognition, 2008

383 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/5c3428d5c47e613fb394f2ffbd9668aa82e9e035

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

Recombinator Networks: Learning Coarse-to-Fine Feature Aggregation (2015, background): “There have been many other approaches to general keypoint localization, including active appearance models [8, 41], constrained local models [10, 20, 11, 2], active shape models [12], point distribution models [9], structured model prediction [3, 30], tree structured face models [43], group sparse l”
Unsupervised Learning of Object Landmarks by Factorized Spatial Embeddings (2017, methodology): “Examples include Active Appearance Models [11], along with subsequent improvements [44, 12] and others using templates [51] or parts [80].”
Face Alignment in Full Pose Range: A 3D Total Solution (2015, methodology): “Most fitting methods can be divided into two categories: the template fitting based [7], [27] and regression based [9],”
Multimodal Spontaneous Emotion Corpus for Human Behavior Analysis (2016, methodology): “Then the Constrained Local Model (CLM) [6] is applied to sequentially perform independent facial landmark detection and global refinement based on the face shape pattern constraint.”
Supervised Descent Method and Its Applications to Face Alignment (2013, methodology): “Constrained Local Models (CLM) [13] model this prior similarly as AAMs assuming all faces lie in a linear subspace expanded by PCA bases.”
Convolutional MKL Based Multimodal Emotion Recognition and Sentiment Analysis (2016, methodology): “The constrained local model (CLM) is used to find the outline of the face in each frame [30].”
Random Forests for Real Time 3D Face Analysis (2012, methodology): “2006) or Active Shape Models (Cristinacce and Cootes 2008) are needed.”
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].”
A Survey on Human Motion Analysis from Depth Data (2013, methodology): “of the facial features configuration like pictorial structures [78, 79] or Active Shape Models [80] can be used.”
Learn to Combine Multiple Hypotheses for Accurate Face Alignment (2013, methodology): “In [7], the ASM is generalized to be constrained local model (CLM), where every landmark has a descriptor to capture appearance, and these descriptors were constrained by a shape model.”
Statistical shape models for 3D medical image segmentation: A review (2009, methodology): “An efficient use of the Nelder–Mead simplex optimizer is demonstrated by Cristinacce and Cootes (2008) for constrained local models, which reach similar speed as AAM.”
Mnemonic Descent Method: A Recurrent Process Applied for End-to-End Face Alignment (2016, background): “Face alignment has a long and rich history that includes the introduction of many important works in computer vision such as Active Appearance Models [13, 35, 2], Constrained Local Models [16, 41] and 3D Morphable Models [8].”