Robust Discriminative Response Map Fitting with Constrained Local Models

By Akshay Asthana, Stefanos P. Zafeiriou, Shiyang Cheng, Maja Pantic. 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013

583 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/7aca7e45130c5c0c954281a3c3fa3bccf74597c9

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

In Statistics and Probability

Citations in the corpus

Remote Heart Rate Measurement from Face Videos under Realistic Situations (2014, methodology): “To this end, we first apply Viola-Jones face detector to detect the face rectangle on the first frame of the input video, then use Discriminative Response Map Fitting (DRMF) method [1] to find the coordinates of 66 facial landmarks inside the face rectangle.”
Recombinator Networks: Learning Coarse-to-Fine Feature Aggregation (2015, methodology): “Keypoint localization methods: Our task of interest is the well studied problem of facial keypoint localization [42, 40, 36, 2, 31, 38, 6, 33, 7, 18, 43] illustrated in Figure 1.”
Less is More: Micro-expression Recognition from Video using Apex Frame (2016, methodology): “a landmark detector called Discriminative Response Map Fitting (DRMF) [46]; (2) The regions of interest that indicate the facial region with important micro-expression details are extracted according to the landmark coordinates; (3) The LBP feature descriptor is utilized to obtain the features of ea”
High-fidelity Pose and Expression Normalization for face recognition in the wild (2015, background): “[6] build a look up table containing 3D landmark configurations for each pose.”
Face alignment by coarse-to-fine shape searching (2015, unknown): “78 DRMF [3] 6.”
A Main Directional Mean Optical Flow Feature for Spontaneous Micro-Expression Recognition (2016, methodology): “That is, 13 feature points are first detected in all frames by using the DRMF method, and then, each frame is aligned with the first frame by applying an affine transformation determined by the correspondence of feature points.”
Constrained Local Neural Fields for Robust Facial Landmark Detection in the Wild (2013, methodology): “There have been a number of different methods proposed as patch experts: various SVR models and logistic regressors, or even simple template matching techniques.”
Rendering of Eyes for Eye-Shape Registration and Gaze Estimation (2015, result): “We also compared our approach with the following state-of-the-art facial landmark detectors trained on in-the-wild data: CLNF [36], Supervised Descent Method (SDM) [38], Discriminative Response Map Fitting (DRMF) [39], and tree based face and landmark detector [40].”
Video-Based Facial Micro-Expression Analysis: A Survey of Datasets, Features and Algorithms (2021, methodology): “Patel et al. [75] used a discriminative response map ﬁtting (DRMF) model [102] to locate key points of the face based on the FACS system.”
Self-Adaptive Matrix Completion for Heart Rate Estimation from Face Videos under Realistic Conditions (2016, background): “nificant improvements in face tracking and alignment methods [3, 21, 13, 14, 29], facial-based remote heart rate estimation has recently become very popular [17, 30, 10, 25].”
OpenFace 2.0: Facial Behavior Analysis Toolkit (2018, background): “While some facial landmark detectors include head pose estimation capabilities [4], [5], most ignore this important behavioral cue.”
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].”
Latent Factor Guided Convolutional Neural Networks for Age-Invariant Face Recognition (2016, methodology): “For each face image, we use the recently proposed algorithms [2, 37, 3] to detect the facial landmarks in images.”
Incremental Face Alignment in the Wild (2014, methodology): “The training procedure of the discriminative methods in [15, 32, 2] can be summarized as follows: Find a function g that can map an initial shape s of image Ii to the ground-truth shape s ∗ i , as g(s , It, f) = s ∗ i .”
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].”
Learning Deep Representation for Face Alignment with Auxiliary Attributes (2014, background): “Such pose information can be leveraged as an additional source of information to constrain the solution space of landmark estimation.”
Image and Vision Computing (2016, unknown): “Furthermore, we computed the bounding boxes of all the aforementioned databases by using our in-house face detector, the one that is also employed in [17], which is a variant of [18].”
OpenFace: An open source facial behavior analysis toolkit (2016, methodology): “DRMF[4] DRMF[4] X X X X”
Unsupervised Learning of Object Landmarks by Factorized Spatial Embeddings (2017, methodology): “Method Mean Error (68 pts) DRMF [2] 9.”