Stefanos Zafeiriou

Imperial College London — United Kingdom

Computer Science · Physical Sciences

68h-index22.0kcitations471works5.02yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Face recognition and analysis(200), Face and Expression Recognition(144), Generative Adversarial Networks and Image Synthesis(71), 3D Shape Modeling and Analysis(70), Human Pose and Action Recognition(48)

Publications469 total

STARCaster: Spatio-Temporal AutoRegressive Video Diffusion for Identity- and View-Aware Talking Portraits
arXiv (Cornell University)·2025Open Access
EEG-D3: A Solution to the Hidden Overfitting Problem of Deep Learning Models
arXiv (Cornell University)·2025Open Access
A Comprehensive Review of Biosignal Foundation Models
2025Open Access
NeuroRVQ: Multi-Scale EEG Tokenization for Generative Large Brainwave Models
arXiv (Cornell University)·2025Open Access
ImHead: A Large-scale Implicit Morphable Model for Localized Head Modeling
arXiv (Cornell University)·2025Open Access
ID-Consistent, Precise Expression Generation with Blendshape-Guided Diffusion
arXiv (Cornell University)·2025Open Access
Embodied Arena: A Comprehensive, Unified, and Evolving Evaluation Platform for Embodied AI
arXiv (Cornell University)·2025Open Access
Assessing the Capabilities of Large Brainwave Foundation Models
2025
Are Large Brainwave Foundation Models Capable Yet? Insights from Fine-tuning
arXiv (Cornell University)·2025Open Access
Advancements in Affective and Behavior Analysis: The 8th ABAW Workshop and Competition
2025· 4 cited
Dyn-HaMR: Recovering 4D Interacting Hand Motion from a Dynamic Camera
2025· 1 cited
S<sup>3</sup>-Face: SSS-Compliant Facial Reflectance Estimation via Diffusion Priors
2025Open Access
Arc2Avatar: Generating Expressive 3D Avatars from a Single Image via ID Guidance
2025· 4 cited
WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild
2025· 12 cited
Advancing Brainwave Modeling with a Codebook-Based Foundation Model
arXiv (Cornell University)·2025Open Access
FitDiff: Robust Monocular 3D Facial Shape and Reflectance Estimation using Diffusion Models
2025
Latent alignment in deep learning models for EEG decoding
Journal of Neural Engineering·2025· 5 citedOpen Access
Arc2Avatar: Generating Expressive 3D Avatars from a Single Image via ID Guidance
arXiv (Cornell University)·2025Open Access
Improving Face Generation Quality and Prompt Following with Synthetic Captions
Lecture notes in computer science·2025· 1 cited
7th ABAW Competition: Multi-task Learning and Compound Expression Recognition
Lecture notes in computer science·2025· 29 cited
page 1 of 24Next →

Frequent Co-authors

Maja Pantić(11), Irene Kotsia(9), Jiankang Deng(8), George Trigeorgis(8), Björn W. Schuller(8), Georgios Tzimiropoulos(7), Mihalis A. Nicolaou(7), Epameinondas Antonakos(7), Christos Sagonas(5), Panagiotis Tzirakis(5), Dimitrios Kollias(5), Jia Guo(4), Athanasios Papaioannou(4), Shiyang Cheng(4), Patrick Snape(4), James G. Booth(4), Akshay Asthana(3), Yuxiang Zhou(3), Guoying Zhao(3), David Dunaway(3)