Incremental Face Alignment in the Wild

By Akshay Asthana, Stefanos P. Zafeiriou, Shiyang Cheng, Maja Pantic. 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014

467 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/c64e5225f585b1483858ed67dc5953d663412b89

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 Signal Processing

Citations in the corpus

The First Facial Landmark Tracking in-the-Wild Challenge: Benchmark and Results (2015, methodology): “Other methods were assessed on a small number of short (few seconds in length) annotated facial videos [45, 14].”
Real-Time Eye Blink Detection using Facial Landmarks (2016, methodology): “The EAR SVM classifiers are tested with both landmark detectors Chehra [1] and Intraface [16].”
Facial Expression Analysis under Partial Occlusion (2018, methodology): “It is interesting to observe that recently developed face analyzers such as Intraface [Torre, et al. 2015] and incremental face model [Asthana et al. 2014] have achieved promising results of detecting, tracking and recognizing facial features even under moderate realistic occlusion.”
Automatic Analysis of Facial Actions: A Survey (2019, methodology): “This was exploited by [11], which proposed an extension of [203] capable of performing incremental learning.”
AVEC 2017: Real-life Depression, and Affect Recognition Workshop and Challenge (2017, methodology): “e facial features have been extracted for each video frame (frame step 20 ms) using the Chehra face tracker [1].”
The Visual Object Tracking VOT2016 Challenge Results (2016, methodology): “To adapt to variations in target appearance and shape over time, TRIC-track takes inspiration from the incremental learning of cascaded regression of [72] applying a sequential incremental update.”
A Novel Space-Time Representation on the Positive Semidefinite Cone for Facial Expression Recognition (2017, methodology): “In particular, advances in landmarks detection [3, 34, 44] have opened the door to accurate geometry-driven approaches.”
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.”
3D Face Morphable Models "In-the-Wild" (2017, background): “During the past few years, we have witnessed significant improvements in various face analysis tasks such as face detection [19, 42] and 2D facial landmark localisation on static images [40, 21, 6, 38, 43, 4, 5, 36].”
Facial Landmark Detection: A Literature Survey (2018, unknown): “Incremental face alignment (Asthana et al. 2014) d&t y bc 49 http://ibug.”
The Visual Object Tracking VOT2015 Challenge Results (2015, methodology): “To adapt to variations in target appearance and shape over time, TRIC-track takes inspiration from the incremental learning of cascaded regression of [1] applying a sequential incremental update.”
Large-Margin Softmax Loss for Convolutional Neural Networks (2016, methodology): “As preprocessing, we use IntraFace (Asthana et al., 2014) to align the face images and then crop them based on 5 points.”
OpenFace 2.0: Facial Behavior Analysis Toolkit (2018, methodology): “DRMF [5] — Discriminative Response Map Fitting performs regression on patch expert response maps directly rather than using optimization over the parameter space.”
OpenFace: An open source facial behavior analysis toolkit (2016, methodology): “For comparison, we report the results of using Chehra framework [5], CLM [50], CLM-Z [9], and Regression Forests [21].”
Image and Vision Computing (2016, unknown): “…can be separated in two major categories: (a) those captured under controlled conditions , e.g. Multi-PIE [25], XM2VTS [26], FRGC-V2 [27], and AR [28], and (b) those captured under totally unconstrained conditions (in-the-wild), e.g. LFPW [29], HELEN [30], AFW[18], AFLW[31], and IBUG [32].”
Mnemonic Descent Method: A Recurrent Process Applied for End-to-End Face Alignment (2016, methodology): “Each linear regressor simply learns how to regress from a particular fixed variance of shape perturbations to the ground-truth [3].”