Deep face recognition: A survey

M Wang, W Deng - Neurocomputing, 2021 - Elsevier
Deep learning applies multiple processing layers to learn representations of data with
multiple levels of feature extraction. This emerging technique has reshaped the research …

Eamm: One-shot emotional talking face via audio-based emotion-aware motion model

X Ji, H Zhou, K Wang, Q Wu, W Wu, F Xu… - ACM SIGGRAPH 2022 …, 2022 - dl.acm.org
Although significant progress has been made to audio-driven talking face generation,
existing methods either neglect facial emotion or cannot be applied to arbitrary subjects. In …

Arcface: Additive angular margin loss for deep face recognition

J Deng, J Guo, N Xue… - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
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 can …

Looking to listen at the cocktail party: A speaker-independent audio-visual model for speech separation

A Ephrat, I Mosseri, O Lang, T Dekel, K Wilson… - arXiv preprint arXiv …, 2018 - arxiv.org
We present a joint audio-visual model for isolating a single speech signal from a mixture of
sounds such as other speakers and background noise. Solving this task using only audio as …

Ganfit: Generative adversarial network fitting for high fidelity 3d face reconstruction

B Gecer, S Ploumpis, I Kotsia… - Proceedings of the …, 2019 - openaccess.thecvf.com
In the past few years, a lot of work has been done towards reconstructing the 3D facial
structure from single images by capitalizing on the power of Deep Convolutional Neural …

Nonlinear 3d face morphable model

L Tran, X Liu - Proceedings of the IEEE conference on …, 2018 - openaccess.thecvf.com
As a classic statistical model of 3D facial shape and texture, 3D Morphable Model (3DMM) is
widely used in facial analysis, eg, model fitting, image synthesis. Conventional 3DMM is …

Unsupervised training for 3d morphable model regression

K Genova, F Cole, A Maschinot… - Proceedings of the …, 2018 - openaccess.thecvf.com
We present a method for training a regression network from image pixels to 3D morphable
model coordinates using only unlabeled photographs. The training loss is based on features …

Towards large-pose face frontalization in the wild

X Yin, X Yu, K Sohn, X Liu… - Proceedings of the …, 2017 - openaccess.thecvf.com
Despite recent advances in face recognition using deep learning, severe accuracy drops are
observed for large pose variations in unconstrained environments. Learning pose-invariant …

Self-supervised multi-level face model learning for monocular reconstruction at over 250 hz

A Tewari, M Zollhöfer, P Garrido… - Proceedings of the …, 2018 - openaccess.thecvf.com
The reconstruction of dense 3D models of face geometry and appearance from a single
image is highly challenging and ill-posed. To constrain the problem, many approaches rely …

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

A Lattas, S Moschoglou, B Gecer… - Proceedings of the …, 2020 - openaccess.thecvf.com
Over the last years, with the advent of Generative Adversarial Networks (GANs), many face
analysis tasks have accomplished astounding performance, with applications including, but …