Search Results for author: Georgios Tzimiropoulos

Found 60 papers, 27 papers with code

iBoot: Image-bootstrapped Self-Supervised Video Representation Learning

no code implementations16 Jun 2022 Fatemeh Saleh, Fuwen Tan, Adrian Bulat, Georgios Tzimiropoulos, Brais Martinez

Video self-supervised learning (SSL) suffers from added challenges: video datasets are typically not as large as image datasets, compute is an order of magnitude larger, and the amount of spurious patterns the optimizer has to sieve through is multiplied several fold.

Data Augmentation Representation Learning +1

ContraCLIP: Interpretable GAN generation driven by pairs of contrasting sentences

1 code implementation5 Jun 2022 Christos Tzelepis, James Oldfield, Georgios Tzimiropoulos, Ioannis Patras

This work addresses the problem of discovering non-linear interpretable paths in the latent space of pre-trained GANs in a model-agnostic manner.

Knowledge Distillation Meets Open-Set Semi-Supervised Learning

1 code implementation13 May 2022 Jing Yang, Xiatian Zhu, Adrian Bulat, Brais Martinez, Georgios Tzimiropoulos

The key idea is that we leverage the teacher's classifier as a semantic critic for evaluating the representations of both teacher and student and distilling the semantic knowledge with high-order structured information over all feature dimensions.

Face Recognition Knowledge Distillation

EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformers

2 code implementations6 May 2022 Junting Pan, Adrian Bulat, Fuwen Tan, Xiatian Zhu, Lukasz Dudziak, Hongsheng Li, Georgios Tzimiropoulos, Brais Martinez

In this work, pushing further along this under-studied direction we introduce EdgeViTs, a new family of light-weight ViTs that, for the first time, enable attention-based vision models to compete with the best light-weight CNNs in the tradeoff between accuracy and on-device efficiency.

Finding Directions in GAN's Latent Space for Neural Face Reenactment

no code implementations31 Jan 2022 Stella Bounareli, Vasileios Argyriou, Georgios Tzimiropoulos

Because GANs are characterized by weak controllability, the core of our approach is a method to discover which directions in latent GAN space are responsible for controlling facial pose and expression variations.

Disentanglement Face Reenactment

S3: Supervised Self-supervised Learning under Label Noise

no code implementations22 Nov 2021 Chen Feng, Georgios Tzimiropoulos, Ioannis Patras

Despite the large progress in supervised learning with Neural Networks, there are significant challenges in obtaining high-quality, large-scale and accurately labeled datasets.

Image Classification Self-Supervised Learning

Subpixel Heatmap Regression for Facial Landmark Localization

no code implementations3 Nov 2021 Adrian Bulat, Enrique Sanchez, Georgios Tzimiropoulos

Deep Learning models based on heatmap regression have revolutionized the task of facial landmark localization with existing models working robustly under large poses, non-uniform illumination and shadows, occlusions and self-occlusions, low resolution and blur.

 Ranked #1 on Face Alignment on COFW (using extra training data)

Face Alignment

Defensive Tensorization

no code implementations26 Oct 2021 Adrian Bulat, Jean Kossaifi, Sourav Bhattacharya, Yannis Panagakis, Timothy Hospedales, Georgios Tzimiropoulos, Nicholas D Lane, Maja Pantic

We propose defensive tensorization, an adversarial defence technique that leverages a latent high-order factorization of the network.

Audio Classification Classification +1

WarpedGANSpace: Finding non-linear RBF paths in GAN latent space

1 code implementation ICCV 2021 Christos Tzelepis, Georgios Tzimiropoulos, Ioannis Patras

This work addresses the problem of discovering, in an unsupervised manner, interpretable paths in the latent space of pretrained GANs, so as to provide an intuitive and easy way of controlling the underlying generative factors.

Space-time Mixing Attention for Video Transformer

1 code implementation NeurIPS 2021 Adrian Bulat, Juan-Manuel Perez-Rua, Swathikiran Sudhakaran, Brais Martinez, Georgios Tzimiropoulos

In this work, we propose a Video Transformer model the complexity of which scales linearly with the number of frames in the video sequence and hence induces no overhead compared to an image-based Transformer model.

Action Classification Action Recognition +2

Bit-Mixer: Mixed-precision networks with runtime bit-width selection

no code implementations ICCV 2021 Adrian Bulat, Georgios Tzimiropoulos

In this work, we propose Bit-Mixer, the very first method to train a meta-quantized network where during test time any layer can change its bid-width without affecting at all the overall network's ability for highly accurate inference.

AutoML Binarization +1

Pre-training strategies and datasets for facial representation learning

1 code implementation30 Mar 2021 Adrian Bulat, Shiyang Cheng, Jing Yang, Andrew Garbett, Enrique Sanchez, Georgios Tzimiropoulos

Recent work on Deep Learning in the area of face analysis has focused on supervised learning for specific tasks of interest (e. g. face recognition, facial landmark localization etc.)

3D Face Reconstruction 3D Facial Landmark Localization +11

Improving memory banks for unsupervised learning with large mini-batch, consistency and hard negative mining

no code implementations8 Feb 2021 Adrian Bulat, Enrique Sánchez-Lozano, Georgios Tzimiropoulos

An important component of unsupervised learning by instance-based discrimination is a memory bank for storing a feature representation for each training sample in the dataset.

Knowledge distillation via softmax regression representation learning

no code implementations ICLR 2021 Jing Yang, Brais Martinez, Adrian Bulat, Georgios Tzimiropoulos

We advocate for a method that optimizes the output feature of the penultimate layer of the student network and hence is directly related to representation learning.

Knowledge Distillation Model Compression +1

Semi-supervised Facial Action Unit Intensity Estimation with Contrastive Learning

no code implementations3 Nov 2020 Enrique Sanchez, Adrian Bulat, Anestis Zaganidis, Georgios Tzimiropoulos

The second stage uses another dataset of randomly chosen labeled frames to train a regressor on top of our spatio-temporal model for estimating the AU intensity.

Contrastive Learning Unsupervised Pre-training

A Transfer Learning approach to Heatmap Regression for Action Unit intensity estimation

no code implementations14 Apr 2020 Ioanna Ntinou, Enrique Sanchez, Adrian Bulat, Michel Valstar, Georgios Tzimiropoulos

Action Units (AUs) are geometrically-based atomic facial muscle movements known to produce appearance changes at specific facial locations.

Face Alignment Transfer Learning

Knowledge distillation via adaptive instance normalization

no code implementations9 Mar 2020 Jing Yang, Brais Martinez, Adrian Bulat, Georgios Tzimiropoulos

To this end, we propose a new knowledge distillation method based on transferring feature statistics, specifically the channel-wise mean and variance, from the teacher to the student.

Knowledge Distillation Model Compression

Toward fast and accurate human pose estimation via soft-gated skip connections

3 code implementations25 Feb 2020 Adrian Bulat, Jean Kossaifi, Georgios Tzimiropoulos, Maja Pantic

In addition, with a reduction of 3x in model size and complexity, we show no decrease in performance when compared to the original HourGlass network.

Ranked #2 on Pose Estimation on MPII Human Pose (using extra training data)

Pose Estimation

Towards Pose-invariant Lip-Reading

no code implementations14 Nov 2019 Shiyang Cheng, Pingchuan Ma, Georgios Tzimiropoulos, Stavros Petridis, Adrian Bulat, Jie Shen, Maja Pantic

The proposed model significantly outperforms previous approaches on non-frontal views while retaining the superior performance on frontal and near frontal mouth views.

Lip Reading

Object landmark discovery through unsupervised adaptation

1 code implementation NeurIPS 2019 Enrique Sanchez, Georgios Tzimiropoulos

Contrary to previous works, we do however assume that a landmark detector, which has already learned a structured representation for a given object category in a fully supervised manner, is available.

Unsupervised Landmark Detection

XNOR-Net++: Improved Binary Neural Networks

1 code implementation30 Sep 2019 Adrian Bulat, Georgios Tzimiropoulos

This paper proposes an improved training algorithm for binary neural networks in which both weights and activations are binary numbers.

Binarization Classification with Binary Neural Network +3

Defensive Tensorization: Randomized Tensor Parametrization for Robust Neural Networks

no code implementations25 Sep 2019 Adrian Bulat, Jean Kossaifi, Sourav Bhattacharya, Yannis Panagakis, Georgios Tzimiropoulos, Nicholas D. Lane, Maja Pantic

As deep neural networks become widely adopted for solving most problems in computer vision and audio-understanding, there are rising concerns about their potential vulnerability.

Adversarial Defense Audio Classification +1

Incremental multi-domain learning with network latent tensor factorization

no code implementations12 Apr 2019 Adrian Bulat, Jean Kossaifi, Georgios Tzimiropoulos, Maja Pantic

Adapting the learned classification to new domains is a hard problem due to at least three reasons: (1) the new domains and the tasks might be drastically different; (2) there might be very limited amount of annotated data on the new domain and (3) full training of a new model for each new task is prohibitive in terms of computation and memory, due to the sheer number of parameters of deep CNNs.

General Classification Image Classification +2

Improved training of binary networks for human pose estimation and image recognition

1 code implementation11 Apr 2019 Adrian Bulat, Georgios Tzimiropoulos, Jean Kossaifi, Maja Pantic

Big neural networks trained on large datasets have advanced the state-of-the-art for a large variety of challenging problems, improving performance by a large margin.

Binarization Classification with Binary Neural Network +4

Features Extraction Based on an Origami Representation of 3D Landmarks

no code implementations12 Dec 2018 Juan Manuel Fernandez Montenegro, Mahdi Maktab Dar Oghaz, Athanasios Gkelias, Georgios Tzimiropoulos, Vasileios Argyriou

The performance evaluation demonstrates an improvement on facial emotion classification (accuracy and F1 score) that indicates the superiority of the proposed methodology.

Classification Emotion Classification +1

Pushing the boundaries of audiovisual word recognition using Residual Networks and LSTMs

no code implementations3 Nov 2018 Themos Stafylakis, Muhammad Haris Khan, Georgios Tzimiropoulos

A further analysis on the utility of target word boundaries is provided, as well as on the capacity of the network in modeling the linguistic context of the target word.

Lipreading speech-recognition +1

Audio-Visual Speech Recognition With A Hybrid CTC/Attention Architecture

no code implementations28 Sep 2018 Stavros Petridis, Themos Stafylakis, Pingchuan Ma, Georgios Tzimiropoulos, Maja Pantic

Therefore, we could use a CTC loss in combination with an attention-based model in order to force monotonic alignments and at the same time get rid of the conditional independence assumption.

Audio-Visual Speech Recognition Automatic Speech Recognition +3

3D Human Body Reconstruction from a Single Image via Volumetric Regression

no code implementations11 Sep 2018 Aaron S. Jackson, Chris Manafas, Georgios Tzimiropoulos

This paper proposes the use of an end-to-end Convolutional Neural Network for direct reconstruction of the 3D geometry of humans via volumetric regression.

Hierarchical binary CNNs for landmark localization with limited resources

1 code implementation14 Aug 2018 Adrian Bulat, Georgios Tzimiropoulos

To this end, we make the following contributions: (a) we are the first to study the effect of neural network binarization on localization tasks, namely human pose estimation and face alignment.

3D Face Alignment Binarization +2

Zero-shot keyword spotting for visual speech recognition in-the-wild

1 code implementation ECCV 2018 Themos Stafylakis, Georgios Tzimiropoulos

Visual keyword spotting (KWS) is the problem of estimating whether a text query occurs in a given recording using only video information.

Automatic Speech Recognition speech-recognition +2

Joint Action Unit localisation and intensity estimation through heatmap regression

1 code implementation9 May 2018 Enrique Sanchez-Lozano, Georgios Tzimiropoulos, Michel Valstar

Contrary to previous works that try to learn an unsupervised representation of the Action Unit regions, we propose to directly and jointly estimate all AU intensities through heatmap regression, along with the location in the face where they cause visible changes.

End-to-end Audiovisual Speech Recognition

2 code implementations18 Feb 2018 Stavros Petridis, Themos Stafylakis, Pingchuan Ma, Feipeng Cai, Georgios Tzimiropoulos, Maja Pantic

In presence of high levels of noise, the end-to-end audiovisual model significantly outperforms both audio-only models.

Lipreading speech-recognition +1

Deep word embeddings for visual speech recognition

1 code implementation30 Oct 2017 Themos Stafylakis, Georgios Tzimiropoulos

In this paper we present a deep learning architecture for extracting word embeddings for visual speech recognition.

Lipreading speech-recognition +2

Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression

1 code implementation ICCV 2017 Aaron S. Jackson, Adrian Bulat, Vasileios Argyriou, Georgios Tzimiropoulos

Our CNN works with just a single 2D facial image, does not require accurate alignment nor establishes dense correspondence between images, works for arbitrary facial poses and expressions, and can be used to reconstruct the whole 3D facial geometry (including the non-visible parts of the face) bypassing the construction (during training) and fitting (during testing) of a 3D Morphable Model.

3D Face Reconstruction Face Alignment

How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)

9 code implementations ICCV 2017 Adrian Bulat, Georgios Tzimiropoulos

To this end, we make the following 5 contributions: (a) we construct, for the first time, a very strong baseline by combining a state-of-the-art architecture for landmark localization with a state-of-the-art residual block, train it on a very large yet synthetically expanded 2D facial landmark dataset and finally evaluate it on all other 2D facial landmark datasets.

3D Face Alignment Face Alignment +1

Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment with Limited Resources

3 code implementations ICCV 2017 Adrian Bulat, Georgios Tzimiropoulos

(d) We present results for experiments on the most challenging datasets for human pose estimation and face alignment, reporting in many cases state-of-the-art performance.

Binarization Face Alignment +1

A Functional Regression approach to Facial Landmark Tracking

no code implementations7 Dec 2016 Enrique Sánchez-Lozano, Georgios Tzimiropoulos, Brais Martinez, Fernando de la Torre, Michel Valstar

This paper presents a Functional Regression solution to the least squares problem, which we coin Continuous Regression, resulting in the first real-time incremental face tracker.

Face Detection Incremental Learning +1

A CNN Cascade for Landmark Guided Semantic Part Segmentation

no code implementations30 Sep 2016 Aaron Jackson, Michel Valstar, Georgios Tzimiropoulos

This paper proposes a CNN cascade for semantic part segmentation guided by pose-specific information encoded in terms of a set of landmarks (or keypoints).

Pose Estimation

Convolutional aggregation of local evidence for large pose face alignment

no code implementations British Machine Vision Conference 2016 Adrian Bulat, Georgios Tzimiropoulos

Besides playing the role of a graphical model, CNN regression is a key feature of our system, guiding the network to rely on context for predicting the location of occluded landmarks, typically encountered in very large poses.

Face Alignment Face Detection

Human pose estimation via Convolutional Part Heatmap Regression

1 code implementation6 Sep 2016 Adrian Bulat, Georgios Tzimiropoulos

Our main contribution is a CNN cascaded architecture specifically designed for learning part relationships and spatial context, and robustly inferring pose even for the case of severe part occlusions.

Pose Estimation

Cascaded Continuous Regression for Real-time Incremental Face Tracking

no code implementations3 Aug 2016 Enrique Sánchez-Lozano, Brais Martinez, Georgios Tzimiropoulos, Michel Valstar

We then derive the incremental learning updates for CCR (iCCR) and show that it is an order of magnitude faster than standard incremental learning for cascaded regression, bringing the time required for the update from seconds down to a fraction of a second, thus enabling real-time tracking.

Face Alignment Incremental Learning +1

Project-Out Cascaded Regression With an Application to Face Alignment

no code implementations CVPR 2015 Georgios Tzimiropoulos

Cascaded regression approaches have been recently shown to achieve state-of-the-art performance for many computer vision tasks.

Face Alignment

Gauss-Newton Deformable Part Models for Face Alignment in-the-Wild

no code implementations CVPR 2014 Georgios Tzimiropoulos, Maja Pantic

To address this limitation, in this paper, we propose to jointly optimize a part-based, trained in-the-wild, flexible appearance model along with a global shape model which results in a joint translational motion model for the model parts via Gauss-Newton (GN) optimization.

Face Alignment

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