A FACS valid 3D dynamic action unit database with applications to 3D dynamic morphable facial modeling

Cosker, Darren; Krumhuber, Eva; Hilton, Adrian

doi:10.1109/iccv.2011.6126510

Cited by 129 publications

(109 citation statements)

References 25 publications

Supporting

Mentioning

109

Contrasting

Order By: Relevance

“…Few 3D dynamic face databases, such as the BU-4DFE [24], D3DFACS [6], Hi4D-ADSIP [13] have recently appeared for the purpose of facial expressions and/or action units recognition. However, other FR challenges, like pose variation and occlusion are not considered.…”

Section: Experimental Results On a New 3d Dynamic Face Datasetmentioning

confidence: 99%

“…Due to the absence of databases collecting 3D dynamic sequences for FR under adverse conditions, we constructed a new database, which includes scans exhibiting free pose variations, facial expressions, talking, internal and external occlusions. In so doing, our dataset differs from the few existing 3D dynamic face databases (also called 4D datasets) [6,13,24], which are collected for facial expressions and/or action units recognition under highly conditioned settings and using high-resolution 3D acquisition.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Grassmannian Framework for Face Recognition of 3D Dynamic Sequences with Challenging Conditions

Alashkar

Amor

Daoudi

2015

Computer Vision - ECCV 2014 Workshops

View full text Add to dashboard Cite

Section: Experimental Results On a New 3d Dynamic Face Datasetmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Grassmannian Framework for Face Recognition of 3D Dynamic Sequences with Challenging Conditions

Alashkar

Amor

Daoudi

2015

Computer Vision - ECCV 2014 Workshops

View full text Add to dashboard Cite

“…The first test consisted of 10-fold cross-validation performed on the Bosphorus database [19], which consists of static images of 105 subjects performing up to 24 AUs. Secondly, the D3DFACS database [3] was employed in order to perform cross-database testing, which is the first time tests of these kind have been performed on 3D AUs. This database consists of 10 subjects performing a wide range of single and combinations of AUs.…”

Section: Resultsmentioning

confidence: 99%

Binary Pattern Analysis for 3D Facial Action Unit Detection

Sandbach

Zafeiriou

Pantić

2012

Procedings of the British Machine Vision Conference 2012

View full text Add to dashboard Cite

In this paper we propose new binary pattern features for use in the problem of 3D facial action unit (AU) detection. Two representations of 3D facial geometries are employed, the depth map and the Azimuthal Projection Distance Image (APDI). To these the traditional Local Binary Pattern is applied, along with Local Phase Quantisation, Gabor filters and Monogenic filters, followed by the binary pattern feature extraction method. Feature vectors are formed for each feature type through concatenation of histograms formed from the resulting binary numbers. Feature selection is then performed using a two-stage GentleBoost approach. Finally, we apply Support Vector Machines as classifiers for detection of each AU. This system is tested in two ways. First we perform 10-fold cross-validation on the Bosphorus database, and then we perform cross-database testing by training on this database and then testing on apex frames from the D3DFACS database, achieving promising results in both.

show abstract

“…A simple integration of the solutions to obtain long-term 2D tracks is prone to drift due to error accumulation [11,9]. This can be improved by the automatic detection of occlusions, gross errors, and other ambiguities [32,34,31,29,25], but any such solution is still limited by the accuracy of the initial two-frame optical flow estimations that are completely local in time and do not exploit any temporal cues.…”

Section: Introductionmentioning

confidence: 99%

Face Flow

Snape

Roussos

Panagakis

et al. 2015

2015 IEEE International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

In this paper, we propose a method for the robust and efficient computation of multi-frame optical flow in an expressive sequence of facial images. We formulate a novel energy minimisation problem for establishing dense correspondences between a neutral template and every frame of a sequence. We exploit the highly correlated nature of human expressions by representing dense facial motion using a deformation basis. Furthermore, we exploit the even higher correlation between deformations in a given input sequence by imposing a low-rank prior on the coefficients of the deformation basis, yielding temporally consistent optical flow. Our proposed model-based formulation, in conjunction with the inverse compositional strategy and lowrank matrix optimisation that we adopt, leads to a highly efficient algorithm for calculating facial flow. As experimental evaluation, we show quantitative experiments on a challenging novel benchmark of face sequences, with dense ground truth optical flow provided by motion capture data. We also provide qualitative results on a real sequence displaying fast motion and occlusions. Extensive quantitative and qualitative comparisons demonstrate that the proposed method outperforms state-of-the-art optical flow and dense non-rigid registration techniques, whilst running an order of magnitude faster.

show abstract

A FACS valid 3D dynamic action unit database with applications to 3D dynamic morphable facial modeling

Abstract: Abstract

Cited by 129 publications

References 25 publications

A Grassmannian Framework for Face Recognition of 3D Dynamic Sequences with Challenging Conditions

A Grassmannian Framework for Face Recognition of 3D Dynamic Sequences with Challenging Conditions

Binary Pattern Analysis for 3D Facial Action Unit Detection

Face Flow

Contact Info

Product

Resources

About