Imperial College London

STEFANOS ZAFEIRIOU, PhD

Faculty of EngineeringDepartment of Computing

Reader in Machine Learning and Computer Vision
 
 
 
//

Contact

 

+44 (0)20 7594 8461s.zafeiriou Website CV

 
 
//

Location

 

375Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Publication Type
Year
to

178 results found

Chrysos GG, Zafeiriou S, 2018, (PDT)-T-2: Person-Specific Detection, Deformable Tracking, IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, Vol: 40, Pages: 2555-2568, ISSN: 0162-8828

JOURNAL ARTICLE

Sagonas C, Ververas E, Panagakis Y, Zafeiriou Set al., 2018, Recovering Joint and Individual Components in Facial Data, IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, Vol: 40, Pages: 2668-2681, ISSN: 0162-8828

JOURNAL ARTICLE

Booth J, Roussos A, Ververas E, Antonakos E, Ploumpis S, Panagakis Y, Zafeiriou Set al., 2018, 3D Reconstruction of "In-the-Wild" Faces in Images and Videos., IEEE Trans Pattern Anal Mach Intell, Vol: 40, Pages: 2638-2652

3D Morphable Models (3DMMs) are powerful statistical models of 3D facial shape and texture, and are among the state-of-the-art methods for reconstructing facial shape from single images. With the advent of new 3D sensors, many 3D facial datasets have been collected containing both neutral as well as expressive faces. However, all datasets are captured under controlled conditions. Thus, even though powerful 3D facial shape models can be learnt from such data, it is difficult to build statistical texture models that are sufficient to reconstruct faces captured in unconstrained conditions ("in-the-wild"). In this paper, we propose the first "in-the-wild" 3DMM by combining a statistical model of facial identity and expression shape with an "in-the-wild" texture model. We show that such an approach allows for the development of a greatly simplified fitting procedure for images and videos, as there is no need to optimise with regards to the illumination parameters. We have collected three new benchmarks that combine "in-the-wild" images and video with ground truth 3D facial geometry, the first of their kind, and report extensive quantitative evaluations using them that demonstrate our method is state-of-the-art.

JOURNAL ARTICLE

Wang M, Panagakis Y, Snape P, Zafeiriou SPet al., 2018, Disentangling the Modes of Variation in Unlabelled Data., IEEE Trans Pattern Anal Mach Intell, Vol: 40, Pages: 2682-2695

Statistical methods are of paramount importance in discovering the modes of variation in visual data. The Principal Component Analysis (PCA) is probably the most prominent method for extracting a single mode of variation in the data. However, in practice, several factors contribute to the appearance of visual objects including pose, illumination, and deformation, to mention a few. To extract these modes of variations from visual data, several supervised methods, such as the TensorFaces relying on multilinear (tensor) decomposition have been developed. The main drawbacks of such methods is that they require both labels regarding the modes of variations and the same number of samples under all modes of variations (e.g., the same face under different expressions, poses etc.). Therefore, their applicability is limited to well-organised data, usually captured in well-controlled conditions. In this paper, we propose a novel general multilinear matrix decomposition method that discovers the multilinear structure of possibly incomplete sets of visual data in unsupervised setting (i.e., without the presence of labels). We also propose extensions of the method with sparsity and low-rank constraints in order to handle noisy data, captured in unconstrained conditions. Besides that, a graph-regularised variant of the method is also developed in order to exploit available geometric or label information for some modes of variations. We demonstrate the applicability of the proposed method in several computer vision tasks, including Shape from Shading (SfS) (in the wild and with occlusion removal), expression transfer, and estimation of surface normals from images captured in the wild.

JOURNAL ARTICLE

Chrysos GG, Antonakos E, Zafeiriou S, 2018, IPST: Incremental Pictorial Structures for Model-Free Tracking of Deformable Objects, IEEE TRANSACTIONS ON IMAGE PROCESSING, Vol: 27, Pages: 3529-3540, ISSN: 1057-7149

JOURNAL ARTICLE

Trigeorgis G, Nicolaou MA, Schuller BW, Zafeiriou Set al., 2018, Deep Canonical Time Warping for Simultaneous Alignment and Representation Learning of Sequences, IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, Vol: 40, Pages: 1128-1138, ISSN: 0162-8828

JOURNAL ARTICLE

Booth J, Roussos A, Ponniah A, Dunaway D, Zafeiriou Set al., 2018, Large Scale 3D Morphable Models, INTERNATIONAL JOURNAL OF COMPUTER VISION, Vol: 126, Pages: 233-254, ISSN: 0920-5691

JOURNAL ARTICLE

Chrysos GG, Antonakos E, Snape P, Asthana A, Zafeiriou Set al., 2018, A Comprehensive Performance Evaluation of Deformable Face Tracking "In-the-Wild", INTERNATIONAL JOURNAL OF COMPUTER VISION, Vol: 126, Pages: 198-232, ISSN: 0920-5691

JOURNAL ARTICLE

Kollias D, Tzirakis P, Nicolaou MA, Papaioannou A, Zhao G, Schuller BW, Kotsia I, Zafeiriou Set al., 2018, Deep Affect Prediction in-the-wild: Aff-Wild Database and Challenge, Deep Architectures, and Beyond., CoRR, Vol: abs/1804.10938

JOURNAL ARTICLE

Tzirakis P, Trigeorgis G, Nicolaou MA, Schuller BW, Zafeiriou Set al., 2017, End-to-End Multimodal Emotion Recognition Using Deep Neural Networks, IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, Vol: 11, Pages: 1301-1309, ISSN: 1932-4553

JOURNAL ARTICLE

Zafeiriou L, Panagakis Y, Pantic M, Zafeiriou Set al., 2017, Nonnegative Decompositions for Dynamic Visual Data Analysis, IEEE TRANSACTIONS ON IMAGE PROCESSING, Vol: 26, Pages: 5603-5617, ISSN: 1057-7149

JOURNAL ARTICLE

Chrysos, Zafeiriou S, PD2T: Person-specific Detection, Deformable Tracking, IEEE Transactions on Pattern Analysis and Machine Intelligence, ISSN: 0162-8828

JOURNAL ARTICLE

Georgakis C, Panagakis Y, Zafeiriou S, Pantic Met al., 2017, The Conflict Escalation Resolution (CONFER) Database, IMAGE AND VISION COMPUTING, Vol: 65, Pages: 37-48, ISSN: 0262-8856

JOURNAL ARTICLE

Sagonas C, Panagakis Y, Zafeiriou S, Pantic Met al., 2017, Robust Statistical Frontalization of Human and Animal Faces, INTERNATIONAL JOURNAL OF COMPUTER VISION, Vol: 122, Pages: 270-291, ISSN: 0920-5691

JOURNAL ARTICLE

Guler RA, Zhou Y, Trigeorgis G, Antonakos E, Snape P, Zafeiriou S, Kokkinos Iet al., DenseReg: Fully Convolutional Dense Shape Regression In-the-Wild

In this work we use deep learning to establish dense correspondences betweena 3D object model and an image "in the wild". We introduce "DenseReg", afully-convolutional neural network (F-CNN) that densely regresses at everyforeground pixel a pair of U-V template coordinates in a single feedforwardpass. To train DenseReg we construct a supervision signal by combining 3Ddeformable model fitting and 2D landmark annotations. We define the regressiontask in terms of the intrinsic, U-V coordinates of a 3D deformable model thatis brought into correspondence with image instances at training time. A host ofother object-related tasks (e.g. part segmentation, landmark localization) areshown to be by-products of this task, and to largely improve thanks to itsintroduction. We obtain highly-accurate regression results by combining ideasfrom semantic segmentation with regression networks, yielding a 'quantizedregression' architecture that first obtains a quantized estimate of positionthrough classification, and refines it through regression of the residual. Weshow that such networks can boost the performance of existing state-of-the-artsystems for pose estimation. Firstly, we show that our system can serve as aninitialization for Statistical Deformable Models, as well as an element ofcascaded architectures that jointly localize landmarks and estimate densecorrespondences. We also show that the obtained dense correspondence can act asa source of 'privileged information' that complements and extends the purelandmark-level annotations, accelerating and improving the training of poseestimation networks. We report state-of-the-art performance on the challenging300W benchmark for facial landmark localization and on the MPII and LSPdatasets for human pose estimation.

CONFERENCE PAPER

Booth J, Antonakos E, Ploumpis S, Trigeorgis G, Panagakis Y, Zafeiriou Set al., 3D Face Morphable Models “In-the-Wild”, IEEE International Conference on Computer Vision and Pattern Recognition, Publisher: IEEE

3D Morphable Models (3DMMs) are powerful statisticalmodels of 3D facial shape and texture, and among the state-of-the-art methods for reconstructing facial shape from sin-gle images. With the advent of new 3D sensors, many 3D fa-cial datasets have been collected containing both neutral aswell as expressive faces. However, all datasets are capturedunder controlled conditions. Thus, even though powerful3D facial shape models can be learnt from such data, it isdifficult to build statistical texture models that are sufficientto reconstruct faces captured in unconstrained conditions(“in-the-wild”). In this paper, we propose the first, to thebest of our knowledge, “in-the-wild” 3DMM by combininga powerful statistical model of facial shape, which describesboth identity and expression, with an “in-the-wild” texturemodel. We show that the employment of such an “in-the-wild” texture model greatly simplifies the fitting procedure,because there is no need to optimise with regards to the illu-mination parameters. Furthermore, we propose a new fastalgorithm for fitting the 3DMM in arbitrary images. Fi-nally, we have captured the first 3D facial database withrelatively unconstrained conditions and report quantitativeevaluations with state-of-the-art performance. Complemen-tary qualitative reconstruction results are demonstrated onstandard “in-the-wild” facial databases.

CONFERENCE PAPER

Cheng S, Marras I, Zafeiriou S, Pantic Met al., 2017, Statistical non-rigid ICP algorithm and its application to 3D face alignment, IMAGE AND VISION COMPUTING, Vol: 58, Pages: 3-12, ISSN: 0262-8856

JOURNAL ARTICLE

Trigeorgis G, Bousmalis K, Zafeiriou S, Schuller BWet al., 2017, A Deep Matrix Factorization Method for Learning Attribute Representations, IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, Vol: 39, Pages: 417-429, ISSN: 0162-8828

JOURNAL ARTICLE

Zafeiriou S, Trigeorgis G, Chrysos G, Deng J, Shen Jet al., 2017, The Menpo Facial Landmark Localisation Challenge: A step towards the solution, 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Publisher: IEEE, Pages: 2116-2125, ISSN: 2160-7508

CONFERENCE PAPER

Fabris A, Nicolaou MA, Kotsia I, Zafeiriou Set al., 2017, DYNAMIC PROBABILISTIC LINEAR DISCRIMINANT ANALYSIS FOR VIDEO CLASSIFICATION, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Publisher: IEEE, Pages: 2781-2785, ISSN: 1520-6149

CONFERENCE PAPER

Chrysos GG, Zafeiriou S, 2017, Deep Face Deblurring, 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Publisher: IEEE, Pages: 2015-2024, ISSN: 2160-7508

CONFERENCE PAPER

Wang M, Panagakis Y, Snape P, Zafeiriou Set al., 2017, Learning the Multilinear Structure of Visual Data, 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Publisher: IEEE, Pages: 6053-6061, ISSN: 1063-6919

CONFERENCE PAPER

Sagonas C, Panagakis Y, Leidinger A, Zafeiriou Set al., 2017, Robust Joint and Individual Variance Explained, 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Publisher: IEEE, Pages: 5739-5748, ISSN: 1063-6919

CONFERENCE PAPER

Trigeorgis G, Snape P, Kokkinos I, Zafeiriou Set al., 2017, Face Normals "in-the- wild" using Fully Convolutional Networks, 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Publisher: IEEE, Pages: 340-349, ISSN: 1063-6919

CONFERENCE PAPER

Booth J, Antonakos E, Ploumpis S, Trigeorgis G, Panagakis Y, Zafeiriou Set al., 2017, 3D Face Morphable Models "In-the-Wild", 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Publisher: IEEE, Pages: 5464-5473, ISSN: 1063-6919

CONFERENCE PAPER

Guler RA, Trigeorgis G, Antonakos E, Snape P, Zafeiriou S, Kokkinos Iet al., 2017, DenseReg: Fully Convolutional Dense Shape Regression In-the-Wild, 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Publisher: IEEE, Pages: 2614-2623, ISSN: 1063-6919

CONFERENCE PAPER

Xue N, Panagakis Y, Zafeiriou S, 2017, Side Information in Robust Principal Component Analysis: Algorithms and Applications, 16th IEEE International Conference on Computer Vision (ICCV), Publisher: IEEE, Pages: 4327-4335, ISSN: 1550-5499

CONFERENCE PAPER

Alabort-i-Medina J, Zafeiriou S, 2017, A Unified Framework for Compositional Fitting of Active Appearance Models, INTERNATIONAL JOURNAL OF COMPUTER VISION, Vol: 121, Pages: 26-64, ISSN: 0920-5691

JOURNAL ARTICLE

Bahri M, Panagakis Y, Zafeiriou S, 2017, Robust Kronecker-Decomposable Component Analysis for Low-Rank Modeling, 16th IEEE International Conference on Computer Vision (ICCV), Publisher: IEEE, Pages: 3372-3381, ISSN: 1550-5499

CONFERENCE PAPER

Tzirakis P, Trigeorgis G, Nicolaou MA, Schuller BW, Zafeiriou Set al., 2017, End-to-End Multimodal Emotion Recognition Using Deep Neural Networks., J. Sel. Topics Signal Processing, Vol: 11, Pages: 1301-1309

JOURNAL ARTICLE

This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.

Request URL: http://wlsprd.imperial.ac.uk:80/respub/WEB-INF/jsp/search-html.jsp Request URI: /respub/WEB-INF/jsp/search-html.jsp Query String: respub-action=search.html&id=00581716&limit=30&person=true