Search Results for author: Stefanos Zafeiriou

Found 126 papers, 39 papers with code

BLSM: A Bone-Level Skinned Model of the Human Mesh

no code implementations ECCV 2020 Haoyang Wang, Riza Alp Güler, Iasonas Kokkinos, George Papandreou, Stefanos Zafeiriou

We introduce BLSM, a bone-level skinned model of the human body mesh where bone scales are set prior to template synthesis, rather than the common, inverse practice.

Unity

GraphWalks: Efficient Shape Agnostic Geodesic Shortest Path Estimation

no code implementations30 May 2022 Rolandos Alexandros Potamias, Alexandros Neofytou, Kyriaki-Margarita Bintsi, Stefanos Zafeiriou

To address such limitations and alleviate the computational burden, we propose a learnable network to approximate geodesic paths.

Facial Geometric Detail Recovery via Implicit Representation

1 code implementation18 Mar 2022 Xingyu Ren, Alexandros Lattas, Baris Gecer, Jiankang Deng, Chao Ma, Xiaokang Yang, Stefanos Zafeiriou

Learning a dense 3D model with fine-scale details from a single facial image is highly challenging and ill-posed.

Embedding Earth: Self-supervised contrastive pre-training for dense land cover classification

1 code implementation11 Mar 2022 Michail Tarasiou, Stefanos Zafeiriou

In training machine learning models for land cover semantic segmentation there is a stark contrast between the availability of satellite imagery to be used as inputs and ground truth data to enable supervised learning.

Semantic Segmentation

Team Cogitat at NeurIPS 2021: Benchmarks for EEG Transfer Learning Competition

no code implementations1 Feb 2022 Stylianos Bakas, Siegfried Ludwig, Konstantinos Barmpas, Mehdi Bahri, Yannis Panagakis, Nikolaos Laskaris, Dimitrios A. Adamos, Stefanos Zafeiriou

The second task required to transfer models trained on the subjects of one or more source motor imagery datasets to perform inference on two target datasets, providing a small set of personalized calibration data for multiple test subjects.

EEG Eeg Decoding +1

Neural Mesh Simplification

no code implementations CVPR 2022 Rolandos Alexandros Potamias, Stylianos Ploumpis, Stefanos Zafeiriou

Then, we train a sparse attention network to propose candidate triangles based on the edge connectivity of the sampled vertices.

AvatarMe++: Facial Shape and BRDF Inference with Photorealistic Rendering-Aware GANs

1 code implementation11 Dec 2021 Alexandros Lattas, Stylianos Moschoglou, Stylianos Ploumpis, Baris Gecer, Abhijeet Ghosh, Stefanos Zafeiriou

Nevertheless, to the best of our knowledge, there is no method which can produce render-ready high-resolution 3D faces from "in-the-wild" images and this can be attributed to the: (a) scarcity of available data for training, and (b) lack of robust methodologies that can successfully be applied on very high-resolution data.

3D Face Reconstruction Face Generation

EEGminer: Discovering Interpretable Features of Brain Activity with Learnable Filters

no code implementations19 Oct 2021 Siegfried Ludwig, Stylianos Bakas, Dimitrios A. Adamos, Nikolaos Laskaris, Yannis Panagakis, Stefanos Zafeiriou

Patterns of brain activity are associated with different brain processes and can be used to identify different brain states and make behavioral predictions.

EEG Eeg Decoding +1

Revisiting Point Cloud Simplification: A Learnable Feature Preserving Approach

no code implementations30 Sep 2021 Rolandos Alexandros Potamias, Giorgos Bouritsas, Stefanos Zafeiriou

In an attempt to alleviate this computational burden, we propose a fast point cloud simplification method by learning to sample salient points.

Masked Face Recognition Challenge: The InsightFace Track Report

1 code implementation18 Aug 2021 Jiankang Deng, Jia Guo, Xiang An, Zheng Zhu, Stefanos Zafeiriou

In this workshop, we organize Masked Face Recognition (MFR) challenge and focus on bench-marking deep face recognition methods under the existence of facial masks.

Face Recognition

Poly-NL: Linear Complexity Non-local Layers with Polynomials

no code implementations6 Jul 2021 Francesca Babiloni, Ioannis Marras, Filippos Kokkinos, Jiankang Deng, Grigorios Chrysos, Stefanos Zafeiriou

Spatial self-attention layers, in the form of Non-Local blocks, introduce long-range dependencies in Convolutional Neural Networks by computing pairwise similarities among all possible positions.

Face Detection Instance Segmentation +1

3D human tongue reconstruction from single "in-the-wild" images

no code implementations CVPR 2022 Stylianos Ploumpis, Stylianos Moschoglou, Vasileios Triantafyllou, Stefanos Zafeiriou

3D face reconstruction from a single image is a task that has garnered increased interest in the Computer Vision community, especially due to its broad use in a number of applications such as realistic 3D avatar creation, pose invariant face recognition and face hallucination.

3D Face Reconstruction Computer Vision +3

Variational Prototype Learning for Deep Face Recognition

no code implementations CVPR 2021 Jiankang Deng, Jia Guo, Jing Yang, Alexandros Lattas, Stefanos Zafeiriou

Deep face recognition has achieved remarkable improvements due to the introduction of margin-based softmax loss, in which the prototype stored in the last linear layer represents the center of each class.

Face Recognition

Analysing Affective Behavior in the second ABAW2 Competition

no code implementations14 Jun 2021 Dimitrios Kollias, Irene Kotsia, Elnar Hajiyev, Stefanos Zafeiriou

The Affective Behavior Analysis in-the-wild (ABAW2) 2021 Competition is the second -- following the first very successful ABAW Competition held in conjunction with IEEE FG 2020- Competition that aims at automatically analyzing affect.

Action Unit Detection Arousal Estimation +1

Fast-GANFIT: Generative Adversarial Network for High Fidelity 3D Face Reconstruction

1 code implementation16 May 2021 Baris Gecer, Stylianos Ploumpis, Irene Kotsia, Stefanos Zafeiriou

In this paper, we take a radically different approach and harness the power of Generative Adversarial Networks (GANs) and DCNNs in order to reconstruct the facial texture and shape from single images.

3D Face Reconstruction

Sample and Computation Redistribution for Efficient Face Detection

2 code implementations ICLR 2022 Jia Guo, Jiankang Deng, Alexandros Lattas, Stefanos Zafeiriou

Although tremendous strides have been made in uncontrolled face detection, efficient face detection with a low computation cost as well as high precision remains an open challenge.

Face Detection

Distribution Matching for Heterogeneous Multi-Task Learning: a Large-scale Face Study

no code implementations8 May 2021 Dimitrios Kollias, Viktoriia Sharmanska, Stefanos Zafeiriou

Based on this approach, we build FaceBehaviorNet, the first framework for large-scale face analysis, by jointly learning all facial behavior tasks.

Action Unit Detection Emotion Recognition +3

DeepSatData: Building large scale datasets of satellite images for training machine learning models

1 code implementation28 Apr 2021 Michail Tarasiou, Stefanos Zafeiriou

This report presents design considerations for automatically generating satellite imagery datasets for training machine learning models with emphasis placed on dense classification tasks, e. g. semantic segmentation.

Semantic Segmentation

Context-self contrastive pretraining for crop type semantic segmentation

1 code implementation9 Apr 2021 Michail Tarasiou, Riza Alp Guler, Stefanos Zafeiriou

For crop type semantic segmentation from satellite images we find performance at parcel boundaries to be a critical bottleneck and explain how CSCL tackles the underlying cause of that problem, improving the state-of-the-art performance in this task.

Contrastive Learning Semantic Segmentation +1

Head2HeadFS: Video-based Head Reenactment with Few-shot Learning

no code implementations30 Mar 2021 Michail Christos Doukas, Mohammad Rami Koujan, Viktoriia Sharmanska, Stefanos Zafeiriou

Head reenactment is an even more challenging task, which aims at transferring not only the facial expression, but also the entire head pose from a source person to a target.

Few-Shot Learning Pose Transfer

Affect Analysis in-the-wild: Valence-Arousal, Expressions, Action Units and a Unified Framework

no code implementations29 Mar 2021 Dimitrios Kollias, Stefanos Zafeiriou

Affect analysis and recognition can be seen as a dual knowledge generation problem, involving: i) creation of new, large and rich in-the-wild databases and ii) design and training of novel deep neural architectures that are able to analyse affect over these databases and to successfully generalise their performance on other datasets.

Action Unit Detection Emotion Classification +1

Speech Emotion Recognition using Semantic Information

1 code implementation4 Mar 2021 Panagiotis Tzirakis, Anh Nguyen, Stefanos Zafeiriou, Björn W. Schuller

In this paper, we propose a novel framework that can capture both the semantic and the paralinguistic information in the signal.

Speech Emotion Recognition Sound Audio and Speech Processing

Poly-NL: Linear Complexity Non-Local Layers With 3rd Order Polynomials

no code implementations ICCV 2021 Francesca Babiloni, Ioannis Marras, Filippos Kokkinos, Jiankang Deng, Grigorios Chrysos, Stefanos Zafeiriou

Spatial self-attention layers, in the form of Non-Local blocks, introduce long-range dependencies in Convolutional Neural Networks by computing pairwise similarities among all possible positions.

Face Detection Instance Segmentation +1

Binary Graph Neural Networks

1 code implementation CVPR 2021 Mehdi Bahri, Gaétan Bahl, Stefanos Zafeiriou

In this paper, we present and evaluate different strategies for the binarization of graph neural networks.

Binarization Representation Learning

OSTeC: One-Shot Texture Completion

1 code implementation CVPR 2021 Baris Gecer, Jiankang Deng, Stefanos Zafeiriou

Many recent 3D facial texture reconstruction and pose manipulation from a single image approaches still rely on large and clean face datasets to train image-to-image Generative Adversarial Networks (GANs).

Face Recognition Robust Face Recognition

Shape My Face: Registering 3D Face Scans by Surface-to-Surface Translation

no code implementations16 Dec 2020 Mehdi Bahri, Eimear O' Sullivan, Shunwang Gong, Feng Liu, Xiaoming Liu, Michael M. Bronstein, Stefanos Zafeiriou

Compared to the previous state-of-the-art learning algorithms for non-rigid registration of face scans, SMF only requires the raw data to be rigidly aligned (with scaling) with a pre-defined face template.

Translation

HeadGAN: One-shot Neural Head Synthesis and Editing

no code implementations ICCV 2021 Michail Christos Doukas, Stefanos Zafeiriou, Viktoriia Sharmanska

Recent attempts to solve the problem of head reenactment using a single reference image have shown promising results.

Learning to Generate Customized Dynamic 3D Facial Expressions

no code implementations ECCV 2020 Rolandos Alexandros Potamias, Jiali Zheng, Stylianos Ploumpis, Giorgos Bouritsas, Evangelos Ververas, Stefanos Zafeiriou

To this end, in this study we employ a deep mesh encoder-decoder like architecture to synthesize realistic high resolution facial expressions by using a single neutral frame along with an expression identification.

Deep Polynomial Neural Networks

1 code implementation20 Jun 2020 Grigorios Chrysos, Stylianos Moschoglou, Giorgos Bouritsas, Jiankang Deng, Yannis Panagakis, Stefanos Zafeiriou

We introduce three tensor decompositions that significantly reduce the number of parameters and show how they can be efficiently implemented by hierarchical neural networks.

Computer Vision Conditional Image Generation +5

Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting

1 code implementation16 Jun 2020 Giorgos Bouritsas, Fabrizio Frasca, Stefanos Zafeiriou, Michael M. Bronstein

It has been shown that the expressive power of standard GNNs is bounded by the Weisfeiler-Leman (WL) graph isomorphism test, from which they inherit proven limitations such as the inability to detect and count graph substructures.

Graph Classification Graph Regression

ReenactNet: Real-time Full Head Reenactment

no code implementations22 May 2020 Mohammad Rami Koujan, Michail Christos Doukas, Anastasios Roussos, Stefanos Zafeiriou

Video-to-video synthesis is a challenging problem aiming at learning a translation function between a sequence of semantic maps and a photo-realistic video depicting the characteristics of a driving video.

Translation Video-to-Video Synthesis

Head2Head: Video-based Neural Head Synthesis

1 code implementation22 May 2020 Mohammad Rami Koujan, Michail Christos Doukas, Anastasios Roussos, Stefanos Zafeiriou

In this paper, we propose a novel machine learning architecture for facial reenactment.

DeepFaceFlow: In-the-wild Dense 3D Facial Motion Estimation

1 code implementation CVPR 2020 Mohammad Rami Koujan, Anastasios Roussos, Stefanos Zafeiriou

Dense 3D facial motion capture from only monocular in-the-wild pairs of RGB images is a highly challenging problem with numerous applications, ranging from facial expression recognition to facial reenactment.

3D Reconstruction Facial Expression Recognition +1

Geometrically Principled Connections in Graph Neural Networks

no code implementations CVPR 2020 Shunwang Gong, Mehdi Bahri, Michael M. Bronstein, Stefanos Zafeiriou

Graph convolution operators bring the advantages of deep learning to a variety of graph and mesh processing tasks previously deemed out of reach.

Graph Classification

Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild

1 code implementation CVPR 2020 Dominik Kulon, Riza Alp Güler, Iasonas Kokkinos, Michael Bronstein, Stefanos Zafeiriou

We introduce a simple and effective network architecture for monocular 3D hand pose estimation consisting of an image encoder followed by a mesh convolutional decoder that is trained through a direct 3D hand mesh reconstruction loss.

3D Hand Pose Estimation Benchmark

AvatarMe: Realistically Renderable 3D Facial Reconstruction "in-the-wild"

1 code implementation CVPR 2020 Alexandros Lattas, Stylianos Moschoglou, Baris Gecer, Stylianos Ploumpis, Vasileios Triantafyllou, Abhijeet Ghosh, Stefanos Zafeiriou

Over the last years, with the advent of Generative Adversarial Networks (GANs), many face analysis tasks have accomplished astounding performance, with applications including, but not limited to, face generation and 3D face reconstruction from a single "in-the-wild" image.

3D Face Reconstruction Face Generation

$Π-$nets: Deep Polynomial Neural Networks

2 code implementations8 Mar 2020 Grigorios G. Chrysos, Stylianos Moschoglou, Giorgos Bouritsas, Yannis Panagakis, Jiankang Deng, Stefanos Zafeiriou

Deep Convolutional Neural Networks (DCNNs) is currently the method of choice both for generative, as well as for discriminative learning in computer vision and machine learning.

Audio Classification Computer Vision +3

Reconstructing the Noise Manifold for Image Denoising

no code implementations11 Feb 2020 Ioannis Marras, Grigorios G. Chrysos, Ioannis Alexiou, Gregory Slabaugh, Stefanos Zafeiriou

Deep Convolutional Neural Networks (CNNs) have been successfully used in many low-level vision problems like image denoising.

Conditional Image Generation Image Denoising +1

Analysing Affective Behavior in the First ABAW 2020 Competition

no code implementations30 Jan 2020 Dimitrios Kollias, Attila Schulc, Elnar Hajiyev, Stefanos Zafeiriou

For the Challenges, we provide a common benchmark database, Aff-Wild2, which is a large scale in-the-wild database and the first one annotated for all these three tasks.

Action Unit Detection Arousal Estimation +1

Extracting deep local features to detect manipulated images of human faces

no code implementations29 Nov 2019 Michail Tarasiou, Stefanos Zafeiriou

Recent developments in computer vision and machine learning have made it possible to create realistic manipulated videos of human faces, raising the issue of ensuring adequate protection against the malevolent effects unlocked by such capabilities.

Computer Vision

Pixel Adaptive Filtering Units

no code implementations24 Nov 2019 Filippos Kokkinos, Ioannis Marras, Matteo Maggioni, Gregory Slabaugh, Stefanos Zafeiriou

Next, we employ PAFU in deep neural networks as a replacement of standard convolutional layers to enhance the original architectures with spatially varying computations to achieve considerable performance improvements.

Computer Vision Translation

Towards a complete 3D morphable model of the human head

1 code implementation18 Nov 2019 Stylianos Ploumpis, Evangelos Ververas, Eimear O' Sullivan, Stylianos Moschoglou, Haoyang Wang, Nick Pears, William A. P. Smith, Baris Gecer, Stefanos Zafeiriou

Eye and eye region models are incorporated into the head model, along with basic models of the teeth, tongue and inner mouth cavity.

Face Model

SpiralNet++: A Fast and Highly Efficient Mesh Convolution Operator

1 code implementation13 Nov 2019 Shunwang Gong, Lei Chen, Michael Bronstein, Stefanos Zafeiriou

Intrinsic graph convolution operators with differentiable kernel functions play a crucial role in analyzing 3D shape meshes.

3D Shape Reconstruction

Face Behavior a la carte: Expressions, Affect and Action Units in a Single Network

no code implementations15 Oct 2019 Dimitrios Kollias, Viktoriia Sharmanska, Stefanos Zafeiriou

We present the first and the largest study of all facial behaviour tasks learned jointly in a single multi-task, multi-domain and multi-label network, which we call FaceBehaviorNet.

Computer Vision Emotion Recognition +1

Complement Face Forensic Detection and Localization with FacialLandmarks

no code implementations12 Oct 2019 Kritaphat Songsri-in, Stefanos Zafeiriou

In addition, our proposed method consists of two branches and can coherently predict face forensic detection and localization to outperform the previous state-of-the-art techniques on the newly proposed dataset as well as the faceforecsic++ dataset especially on low-quality videos.

General Classification

Exploiting multi-CNN features in CNN-RNN based Dimensional Emotion Recognition on the OMG in-the-wild Dataset

no code implementations3 Oct 2019 Dimitrios Kollias, Stefanos Zafeiriou

This paper presents a novel CNN-RNN based approach, which exploits multiple CNN features for dimensional emotion recognition in-the-wild, utilizing the One-Minute Gradual-Emotion (OMG-Emotion) dataset.

Arousal Estimation Emotion Recognition +1

Expression, Affect, Action Unit Recognition: Aff-Wild2, Multi-Task Learning and ArcFace

no code implementations25 Sep 2019 Dimitrios Kollias, Stefanos Zafeiriou

The need to collect and annotate diverse in-the-wild datasets has become apparent with the rise of deep learning models, as the default approach to address any computer vision task.

Action Unit Detection Arousal Estimation +3

SliderGAN: Synthesizing Expressive Face Images by Sliding 3D Blendshape Parameters

no code implementations26 Aug 2019 Evangelos Ververas, Stefanos Zafeiriou

In particular, we propose the SliderGAN which transforms an input face image into a new one according to the continuous values of a statistical blendshape model of facial motion.

Image-to-Image Translation Translation

PolyGAN: High-Order Polynomial Generators

no code implementations19 Aug 2019 Grigorios Chrysos, Stylianos Moschoglou, Yannis Panagakis, Stefanos Zafeiriou

Generative Adversarial Networks (GANs) have become the gold standard when it comes to learning generative models for high-dimensional distributions.

Video-to-Video Translation for Visual Speech Synthesis

no code implementations28 May 2019 Michail C. Doukas, Viktoriia Sharmanska, Stefanos Zafeiriou

Despite remarkable success in image-to-image translation that celebrates the advancements of generative adversarial networks (GANs), very limited attempts are known for video domain translation.

Image-to-Image Translation Speech Synthesis +1

Single Image 3D Hand Reconstruction with Mesh Convolutions

1 code implementation4 May 2019 Dominik Kulon, Haoyang Wang, Riza Alp Güler, Michael Bronstein, Stefanos Zafeiriou

In this paper, we demonstrate an alternative solution that is based on the idea of encoding images into a latent non-linear representation of meshes.

3D Reconstruction

3DFaceGAN: Adversarial Nets for 3D Face Representation, Generation, and Translation

no code implementations1 May 2019 Stylianos Moschoglou, Stylianos Ploumpis, Mihalis Nicolaou, Athanasios Papaioannou, Stefanos Zafeiriou

As a result, linear methods such as Principal Component Analysis (PCA) have been mainly utilized towards 3D shape analysis, despite being unable to capture non-linearities and high frequency details of the 3D face - such as eyelid and lip variations.

3D Shape Representation Computer Vision +4

Face Video Generation from a Single Image and Landmarks

no code implementations25 Apr 2019 Kritaphat Songsri-in, Stefanos Zafeiriou

In this paper we are concerned with the challenging problem of producing a full image sequence of a deformable face given only an image and generic facial motions encoded by a set of sparse landmarks.

Image-to-Image Translation Translation +1

Synthesising 3D Facial Motion from "In-the-Wild" Speech

no code implementations15 Apr 2019 Panagiotis Tzirakis, Athanasios Papaioannou, Alexander Lattas, Michail Tarasiou, Björn Schuller, Stefanos Zafeiriou

Synthesising 3D facial motion from speech is a crucial problem manifesting in a multitude of applications such as computer games and movies.

Lip Reading motion synthesis

Dense 3D Face Decoding over 2500FPS: Joint Texture & Shape Convolutional Mesh Decoders

no code implementations CVPR 2019 Yuxiang Zhou, Jiankang Deng, Irene Kotsia, Stefanos Zafeiriou

3D Morphable Models (3DMMs) are statistical models that represent facial texture and shape variations using a set of linear bases and more particular Principal Component Analysis (PCA).

MeshGAN: Non-linear 3D Morphable Models of Faces

no code implementations25 Mar 2019 Shiyang Cheng, Michael Bronstein, Yuxiang Zhou, Irene Kotsia, Maja Pantic, Stefanos Zafeiriou

Generative Adversarial Networks (GANs) are currently the method of choice for generating visual data.

Combining 3D Morphable Models: A Large scale Face-and-Head Model

1 code implementation CVPR 2019 Stylianos Ploumpis, Haoyang Wang, Nick Pears, William A. P. Smith, Stefanos Zafeiriou

Three-dimensional Morphable Models (3DMMs) are powerful statistical tools for representing the 3D surfaces of an object class.

GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstruction

1 code implementation CVPR 2019 Baris Gecer, Stylianos Ploumpis, Irene Kotsia, Stefanos Zafeiriou

In this paper, we take a radically different approach and harness the power of Generative Adversarial Networks (GANs) and DCNNs in order to reconstruct the facial texture and shape from single images.

 Ranked #1 on 3D Face Reconstruction on Florence (Average 3D Error metric)

3D Face Reconstruction

Deep Neural Network Augmentation: Generating Faces for Affect Analysis

no code implementations12 Nov 2018 Dimitrios Kollias, Shiyang Cheng, Evangelos Ververas, Irene Kotsia, Stefanos Zafeiriou

This paper presents a novel approach for synthesizing facial affect; either in terms of the six basic expressions (i. e., anger, disgust, fear, joy, sadness and surprise), or in terms of valence (i. e., how positive or negative is an emotion) and arousal (i. e., power of the emotion activation).

Data Augmentation Face Generation

Aff-Wild2: Extending the Aff-Wild Database for Affect Recognition

1 code implementation11 Nov 2018 Dimitrios Kollias, Stefanos Zafeiriou

The obtained results show premise for utilization of the extended Aff-Wild, as well as of the developed deep neural architectures for visual analysis of human behaviour in terms of continuous emotion dimensions.

Emotion Recognition

A Multi-Task Learning & Generation Framework: Valence-Arousal, Action Units & Primary Expressions

no code implementations11 Nov 2018 Dimitrios Kollias, Stefanos Zafeiriou

Various approaches have been proposed for: i) discrete emotion recognition in terms of the primary facial expressions; ii) emotion analysis in terms of facial Action Units (AUs), assuming a fixed expression intensity; iii) dimensional emotion analysis, in terms of valence and arousal (VA).

Emotion Recognition Image Generation +1

Training Deep Neural Networks with Different Datasets In-the-wild: The Emotion Recognition Paradigm

no code implementations12 Sep 2018 Dimitrios Kollias, Stefanos Zafeiriou

A novel procedure is presented in this paper, for training a deep convolutional and recurrent neural network, taking into account both the available training data set and some information extracted from similar networks trained with other relevant data sets.

Emotion Recognition

4DFAB: A Large Scale 4D Database for Facial Expression Analysis and Biometric Applications

no code implementations CVPR 2018 Shiyang Cheng, Irene Kotsia, Maja Pantic, Stefanos Zafeiriou

The progress we are currently witnessing in many computer vision applications, including automatic face analysis, would not be made possible without tremendous efforts in collecting and annotating large scale visual databases.

Computer Vision Facial Expression Recognition

Robust Conditional Generative Adversarial Networks

1 code implementation ICLR 2019 Grigorios G. Chrysos, Jean Kossaifi, Stefanos Zafeiriou

Conditional generative adversarial networks (cGAN) have led to large improvements in the task of conditional image generation, which lies at the heart of computer vision.

Computer Vision Conditional Image Generation

A Multi-component CNN-RNN Approach for Dimensional Emotion Recognition in-the-wild

no code implementations3 May 2018 Dimitrios Kollias, Stefanos Zafeiriou

This paper presents our approach to the One-Minute Gradual-Emotion Recognition (OMG-Emotion) Challenge, focusing on dimensional emotion recognition through visual analysis of the provided emotion videos.

Emotion Recognition

Motion deblurring of faces

no code implementations8 Mar 2018 Grigorios G. Chrysos, Paolo Favaro, Stefanos Zafeiriou

Notwithstanding, a much less standing mode of variation is motion deblurring, which however presents substantial challenges in face analysis.

Computer Vision Deblurring +1

DenseReg: Fully Convolutional Dense Shape Regression In-the-Wild

no code implementations CVPR 2017 Riza Alp Guler, Yuxiang Zhou, George Trigeorgis, Epameinondas Antonakos, Patrick Snape, Stefanos Zafeiriou, Iasonas Kokkinos

We define the regression task in terms of the intrinsic, U-V coordinates of a 3D deformable model that is brought into correspondence with image instances at training time.

Face Alignment Pose Estimation +1

End2You -- The Imperial Toolkit for Multimodal Profiling by End-to-End Learning

1 code implementation4 Feb 2018 Panagiotis Tzirakis, Stefanos Zafeiriou, Bjorn W. Schuller

To our knowledge, this is the first toolkit that provides generic end-to-end learning for profiling capabilities in either unimodal or multimodal cases.

Self-Learning

ArcFace: Additive Angular Margin Loss for Deep Face Recognition

84 code implementations CVPR 2019 Jiankang Deng, Jia Guo, Niannan Xue, Stefanos Zafeiriou

One of the main challenges in feature learning using Deep Convolutional Neural Networks (DCNNs) for large-scale face recognition is the design of appropriate loss functions that enhance discriminative power.

 Ranked #1 on Face Verification on IJB-C (training dataset metric)

Face Identification Face Recognition +1

Side Information for Face Completion: a Robust PCA Approach

no code implementations20 Jan 2018 Niannan Xue, Jiankang Deng, Shiyang Cheng, Yannis Panagakis, Stefanos Zafeiriou

Robust principal component analysis (RPCA) is a powerful method for learning low-rank feature representation of various visual data.

Face Recognition Facial Inpainting +1

Visual Data Augmentation through Learning

no code implementations20 Jan 2018 Grigorios G. Chrysos, Yannis Panagakis, Stefanos Zafeiriou

In addition, the state-of-the-art data-driven methods demand a vast amount of data, hence a standard engineering trick employed is artificial data augmentation for instance by adding into the data cropped and (affinely) transformed images.

Data Augmentation

Robust Kronecker Component Analysis

no code implementations18 Jan 2018 Mehdi Bahri, Yannis Panagakis, Stefanos Zafeiriou

Dictionary learning and component analysis models are fundamental for learning compact representations that are relevant to a given task (feature extraction, dimensionality reduction, denoising, etc.).

Dictionary Learning Dimensionality Reduction +1

Multi-Attribute Robust Component Analysis for Facial UV Maps

no code implementations15 Dec 2017 Stylianos Moschoglou, Evangelos Ververas, Yannis Panagakis, Mihalis Nicolaou, Stefanos Zafeiriou

In this paper, we propose a novel component analysis technique that is suitable for facial UV maps containing a considerable amount of missing information and outliers, while additionally, incorporates knowledge from various attributes (such as age and identity).

3D Face Alignment Face Alignment +1

UV-GAN: Adversarial Facial UV Map Completion for Pose-invariant Face Recognition

no code implementations CVPR 2018 Jiankang Deng, Shiyang Cheng, Niannan Xue, Yuxiang Zhou, Stefanos Zafeiriou

We demonstrate that by attaching the completed UV to the fitted mesh and generating instances of arbitrary poses, we can increase pose variations for training deep face recognition/verification models, and minimise pose discrepancy during testing, which lead to better performance.

3D Face Alignment Face Alignment +4

An Adversarial Neuro-Tensorial Approach For Learning Disentangled Representations

no code implementations28 Nov 2017 Mengjiao Wang, Zhixin Shu, Shiyang Cheng, Yannis Panagakis, Dimitris Samaras, Stefanos Zafeiriou

Several factors contribute to the appearance of an object in a visual scene, including pose, illumination, and deformation, among others.

3D Face Reconstruction

The Unconstrained Ear Recognition Challenge

no code implementations23 Aug 2017 Žiga Emeršič, Dejan Štepec, Vitomir Štruc, Peter Peer, Anjith George, Adil Ahmad, Elshibani Omar, Terrance E. Boult, Reza Safdari, Yuxiang Zhou, Stefanos Zafeiriou, Dogucan Yaman, Fevziye I. Eyiokur, Hazim K. Ekenel

In this paper we present the results of the Unconstrained Ear Recognition Challenge (UERC), a group benchmarking effort centered around the problem of person recognition from ear images captured in uncontrolled conditions.

Person Recognition

Joint Multi-view Face Alignment in the Wild

no code implementations20 Aug 2017 Jiankang Deng, George Trigeorgis, Yuxiang Zhou, Stefanos Zafeiriou

This encompasses two basic problems: i) the detection and deformable fitting steps are performed independently, while the detector might not provide best-suited initialisation for the fitting step, ii) the face appearance varies hugely across different poses, which makes the deformable face fitting very challenging and thus distinct models have to be used (\eg, one for profile and one for frontal faces).

Benchmark Face Alignment +1

Face Normals "In-The-Wild" Using Fully Convolutional Networks

no code implementations CVPR 2017 George Trigeorgis, Patrick Snape, Iasonas Kokkinos, Stefanos Zafeiriou

In this work we pursue a data-driven approach to the problem of estimating surface normals from a single intensity image, focusing in particular on human faces.

3D Reconstruction

Robust Joint and Individual Variance Explained

no code implementations CVPR 2017 Christos Sagonas, Yannis Panagakis, Alina Leidinger, Stefanos Zafeiriou

Even though the CCA is a powerful tool, it has several drawbacks that render its application challenging for computer vision applications.

Computer Vision

Learning the Multilinear Structure of Visual Data

no code implementations CVPR 2017 Mengjiao Wang, Yannis Panagakis, Patrick Snape, Stefanos Zafeiriou

To extract these modes of variations from visual data, several supervised methods, such as the TensorFaces, that rely on multilinear (tensor) decomposition (e. g., Higher Order SVD) have been developed.

Tensor Decomposition

Deep Face Deblurring

no code implementations27 Apr 2017 Grigorios G. Chrysos, Stefanos Zafeiriou

Blind deblurring consists a long studied task, however the outcomes of generic methods are not effective in real world blurred images.

Computer Vision Deblurring +1

End-to-End Multimodal Emotion Recognition using Deep Neural Networks

2 code implementations27 Apr 2017 Panagiotis Tzirakis, George Trigeorgis, Mihalis A. Nicolaou, Björn Schuller, Stefanos Zafeiriou

The system is then trained in an end-to-end fashion where - by also taking advantage of the correlations of the each of the streams - we manage to significantly outperform the traditional approaches based on auditory and visual handcrafted features for the prediction of spontaneous and natural emotions on the RECOLA database of the AVEC 2016 research challenge on emotion recognition.

Multimodal Emotion Recognition

Robust Kronecker-Decomposable Component Analysis for Low-Rank Modeling

1 code implementation ICCV 2017 Mehdi Bahri, Yannis Panagakis, Stefanos Zafeiriou

In this paper, we introduce a new robust decomposition of images by combining ideas from sparse dictionary learning and PCP.

Computer Vision Dictionary Learning +1

Side Information in Robust Principal Component Analysis: Algorithms and Applications

no code implementations ICCV 2017 Niannan Xue, Yannis Panagakis, Stefanos Zafeiriou

Robust Principal Component Analysis (RPCA) aims at recovering a low-rank subspace from grossly corrupted high-dimensional (often visual) data and is a cornerstone in many machine learning and computer vision applications.

Computer Vision Facial Expression Recognition +1

3D Face Morphable Models "In-the-Wild"

no code implementations CVPR 2017 James Booth, Epameinondas Antonakos, Stylianos Ploumpis, George Trigeorgis, Yannis Panagakis, Stefanos Zafeiriou

In this paper, we propose the first, to the best of our knowledge, "in-the-wild" 3DMM by combining a powerful statistical model of facial shape, which describes both identity and expression, with an "in-the-wild" texture model.

Ranked #3 on 3D Face Reconstruction on Florence (Average 3D Error metric)

3D Face Reconstruction

DenseReg: Fully Convolutional Dense Shape Regression In-the-Wild

no code implementations CVPR 2017 Riza Alp Güler, George Trigeorgis, Epameinondas Antonakos, Patrick Snape, Stefanos Zafeiriou, Iasonas Kokkinos

As such our network can provide useful correspondence information as a stand-alone system, while when used as an initialization for Statistical Deformable Models we obtain landmark localization results that largely outperform the current state-of-the-art on the challenging 300W benchmark.

Semantic Segmentation

Non-Negative Matrix Factorizations for Multiplex Network Analysis

no code implementations1 Dec 2016 Vladimir Gligorijevic, Yannis Panagakis, Stefanos Zafeiriou

Networks have been a general tool for representing, analyzing, and modeling relational data arising in several domains.

Community Detection

Automatic Sleep Stage Scoring with Single-Channel EEG Using Convolutional Neural Networks

no code implementations5 Oct 2016 Orestis Tsinalis, Paul M. Matthews, Yike Guo, Stefanos Zafeiriou

We used convolutional neural networks (CNNs) for automatic sleep stage scoring based on single-channel electroencephalography (EEG) to learn task-specific filters for classification without using prior domain knowledge.

EEG

Estimating Correspondences of Deformable Objects "In-The-Wild"

no code implementations CVPR 2016 Yuxiang Zhou, Epameinondas Antonakos, Joan Alabort-i-Medina, Anastasios Roussos, Stefanos Zafeiriou

In this paper, we show for the first time, to the best of our knowledge, that it is possible to construct SDMs by putting object shapes in dense correspondence.

Semantic Segmentation

A 3D Morphable Model Learnt From 10,000 Faces

no code implementations CVPR 2016 James Booth, Anastasios Roussos, Stefanos Zafeiriou, Allan Ponniah, David Dunaway

We present Large Scale Facial Model (LSFM) -- a 3D Morphable Model (3DMM) automatically constructed from 9, 663 distinct facial identities.

Deep Canonical Time Warping

no code implementations CVPR 2016 George Trigeorgis, Mihalis A. Nicolaou, Stefanos Zafeiriou, Bjorn W. Schuller

Thus, they fail to capture complex, hierarchical non-linear representations which may prove to be beneficial towards the task of temporal alignment, particularly when dealing with multi-modal data (e. g., aligning visual and acoustic information).

Time Series

A Comprehensive Performance Evaluation of Deformable Face Tracking "In-the-Wild"

1 code implementation18 Mar 2016 Grigorios G. Chrysos, Epameinondas Antonakos, Patrick Snape, Akshay Asthana, Stefanos Zafeiriou

Recently, technologies such as face detection, facial landmark localisation and face recognition and verification have matured enough to provide effective and efficient solutions for imagery captured under arbitrary conditions (referred to as "in-the-wild").

Face Alignment Face Detection +1

A Unified Framework for Compositional Fitting of Active Appearance Models

no code implementations2 Jan 2016 Joan Alabort-i-Medina, Stefanos Zafeiriou

Active Appearance Models (AAMs) are one of the most popular and well-established techniques for modeling deformable objects in computer vision.

Computer Vision

Face Flow

no code implementations ICCV 2015 Patrick Snape, Anastasios Roussos, Yannis Panagakis, Stefanos Zafeiriou

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.

Optical Flow Estimation

Robust Statistical Face Frontalization

no code implementations ICCV 2015 Christos Sagonas, Yannis Panagakis, Stefanos Zafeiriou, Maja Pantic

The proposed method is assessed in frontal face reconstruction, face landmark localization, pose-invariant face recognition, and face verification in unconstrained conditions.

Face Alignment Face Recognition +3

MAGMA: Multi-level accelerated gradient mirror descent algorithm for large-scale convex composite minimization

no code implementations18 Sep 2015 Vahan Hovhannisyan, Panos Parpas, Stefanos Zafeiriou

Composite convex optimization models arise in several applications, and are especially prevalent in inverse problems with a sparsity inducing norm and in general convex optimization with simple constraints.

Face Recognition

A deep matrix factorization method for learning attribute representations

no code implementations10 Sep 2015 George Trigeorgis, Konstantinos Bousmalis, Stefanos Zafeiriou, Bjoern W. Schuller

Semi-Non-negative Matrix Factorization is a technique that learns a low-dimensional representation of a dataset that lends itself to a clustering interpretation.

Automatic Construction Of Robust Spherical Harmonic Subspaces

no code implementations CVPR 2015 Patrick Snape, Yannis Panagakis, Stefanos Zafeiriou

In this paper we propose a method to automatically recover a class specific low dimensional spherical harmonic basis from a set of in-the-wild facial images.

Unifying Holistic and Parts-Based Deformable Model Fitting

no code implementations CVPR 2015 Joan Alabort-i-Medina, Stefanos Zafeiriou

In this paper we try to marry the previous two frameworks into a unified one that potentially combines the advantages of both.

Computer Vision Face Alignment

Active Pictorial Structures

no code implementations CVPR 2015 Epameinondas Antonakos, Joan Alabort-i-Medina, Stefanos Zafeiriou

Inspired by the tree structure used in PS, the proposed Active Pictorial Structures (APS) model the appearance of the object using multiple graph-based pairwise normal distributions (Gaussian Markov Random Field) between the patches extracted from the regions around adjacent landmarks.

Face Alignment

Face frontalization for Alignment and Recognition

no code implementations3 Feb 2015 Christos Sagonas, Yannis Panagakis, Stefanos Zafeiriou, Maja Pantic

The proposed method is assessed in frontal face reconstruction (pose correction), face landmark localization, and pose-invariant face recognition and verification by conducting experiments on $6$ facial images databases.

Face Recognition Face Reconstruction +1

Merging SVMs with Linear Discriminant Analysis: A Combined Model

no code implementations CVPR 2014 Symeon Nikitidis, Stefanos Zafeiriou, Maja Pantic

A key problem often encountered by many learning algorithms in computer vision dealing with high dimensional data is the so called "curse of dimensionality" which arises when the available training samples are less than the input feature space dimensionality.

Computer Vision Dimensionality Reduction +1

RAPS: Robust and Efficient Automatic Construction of Person-Specific Deformable Models

no code implementations CVPR 2014 Christos Sagonas, Yannis Panagakis, Stefanos Zafeiriou, Maja Pantic

Next, to correct the fittings of a generic model, image congealing (i. e., batch image aliment) is performed by employing only the learnt orthonormal subspace.

Computer Vision Face Alignment +1

Automatic Construction of Deformable Models In-The-Wild

no code implementations CVPR 2014 Epameinondas Antonakos, Stefanos Zafeiriou

The only requirements of the method are a crude bounding box object detector and a-priori knowledge of the object's shape (e. g. a point distribution model).

object-detection Object Detection

Bayesian Active Appearance Models

no code implementations CVPR 2014 Joan Alabort-i-Medina, Stefanos Zafeiriou

In this paper we provide the first, to the best of our knowledge, Bayesian formulation of one of the most successful and well-studied statistical models of shape and texture, i. e.

Texture Synthesis

Incremental Face Alignment in the Wild

no code implementations CVPR 2014 Akshay Asthana, Stefanos Zafeiriou, Shiyang Cheng, Maja Pantic

We propose very efficient strategies to update the model and we show that is possible to automatically construct robust discriminative person and imaging condition specific models 'in-the-wild' that outperform state-of-the-art generic face alignment strategies.

Face Alignment

Kernel-PCA Analysis of Surface Normals for Shape-from-Shading

no code implementations CVPR 2014 Patrick Snape, Stefanos Zafeiriou

We propose a kernel-based framework for computing components from a set of surface normals.

Robust Canonical Time Warping for the Alignment of Grossly Corrupted Sequences

no code implementations CVPR 2013 Yannis Panagakis, Mihalis A. Nicolaou, Stefanos Zafeiriou, Maja Pantic

The superiority of the proposed method against the state-of-the-art time alignment methods, namely the canonical time warping and the generalized time warping, is indicated by the experimental results on both synthetic and real datasets.

Compressive Sensing Dynamic Time Warping

Robust Discriminative Response Map Fitting with Constrained Local Models

no code implementations CVPR 2013 Akshay Asthana, Stefanos Zafeiriou, Shiyang Cheng, Maja Pantic

We present a novel discriminative regression based approach for the Constrained Local Models (CLMs) framework, referred to as the Discriminative Response Map Fitting (DRMF) method, which shows impressive performance in the generic face fitting scenario.

A Unified Framework for Probabilistic Component Analysis

no code implementations13 Mar 2013 Mihalis A. Nicolaou, Stefanos Zafeiriou, Maja Pantic

We present a unifying framework which reduces the construction of probabilistic component analysis techniques to a mere selection of the latent neighbourhood, thus providing an elegant and principled framework for creating novel component analysis models as well as constructing probabilistic equivalents of deterministic component analysis methods.

Cannot find the paper you are looking for? You can Submit a new open access paper.