112 citations · 333 across the 19 of their papers we have counts for
20 papers
Multiplayer Interactive World Models with Representation Autoencoders
Anthony Hu, Václav Volhejn, Adrien Ramanana Rahary +24
We introduce the first multiplayer world model for highly dynamic environments governed by complex physical interactions. Whereas single-player world models treat the other agents…
Visual-Word Tokenizer: Beyond Fixed Sets of Tokens in Vision Transformers
Leonidas Gee, Wing Yan Li, Viktoriia Sharmanska +1
The cost of deploying vision transformers increasingly represents a barrier to wider industrial adoption. Existing compression techniques require additional end-to-end fine-tuning…
Distribution Matching for Multi-Task Learning of Classification Tasks: a Large-Scale Study on Faces & Beyond
Dimitrios Kollias, Viktoriia Sharmanska, Stefanos Zafeiriou
Multi-Task Learning (MTL) is a framework, where multiple related tasks are learned jointly and benefit from a shared representation space, or parameter transfer. To provide suffici…
Okapi: Generalising Better by Making Statistical Matches Match
Myles Bartlett, Sara Romiti, Viktoriia Sharmanska +1
We propose Okapi, a simple, efficient, and general method for robust semi-supervised learning based on online statistical matching. Our method uses a nearest-neighbours-based match…
Free-HeadGAN: Neural Talking Head Synthesis with Explicit Gaze Control
Michail Christos Doukas, Evangelos Ververas, Viktoriia Sharmanska +1
We present Free-HeadGAN, a person-generic neural talking head synthesis system. We show that modeling faces with sparse 3D facial landmarks are sufficient for achieving state-of-th…
RealPatch: A Statistical Matching Framework for Model Patching with Real Samples
Sara Romiti, Christopher Inskip, Viktoriia Sharmanska +1
Machine learning classifiers are typically trained to minimise the average error across a dataset. Unfortunately, in practice, this process often exploits spurious correlations cau…
DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image
Tetiana Martyniuk, Orest Kupyn, Yana Kurliak +3
We present DAD-3DHeads, a dense and diverse large-scale dataset, and a robust model for 3D Dense Head Alignment in the wild. It contains annotations of over 3.5K landmarks that acc…
Addressing Missing Sources with Adversarial Support-Matching
Thomas Kehrenberg, Myles Bartlett, Viktoriia Sharmanska +1
When trained on diverse labeled data, machine learning models have proven themselves to be a powerful tool in all facets of society. However, due to budget limitations, deliberate…
Distribution Matching for Heterogeneous Multi-Task Learning: a Large-scale Face Study
Dimitrios Kollias, Viktoriia Sharmanska, Stefanos Zafeiriou
Multi-Task Learning has emerged as a methodology in which multiple tasks are jointly learned by a shared learning algorithm, such as a DNN. MTL is based on the assumption that the…
Head2HeadFS: Video-based Head Reenactment with Few-shot Learning
Michail Christos Doukas, Mohammad Rami Koujan, Viktoriia Sharmanska +1
Over the past years, a substantial amount of work has been done on the problem of facial reenactment, with the solutions coming mainly from the graphics community. Head reenactment…
HeadGAN: One-shot Neural Head Synthesis and Editing
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. However, most of them either perform poorly in terms of photo-…
Head2Head++: Deep Facial Attributes Re-Targeting
Michail Christos Doukas, Mohammad Rami Koujan, Viktoriia Sharmanska +1
Facial video re-targeting is a challenging problem aiming to modify the facial attributes of a target subject in a seamless manner by a driving monocular sequence. We leverage the…
Contrastive Examples for Addressing the Tyranny of the Majority
Viktoriia Sharmanska, Lisa Anne Hendricks, Trevor Darrell +1
Computer vision algorithms, e.g. for face recognition, favour groups of individuals that are better represented in the training data. This happens because of the generalization tha…
Face Behavior a la carte: Expressions, Affect and Action Units in a Single Network
Dimitrios Kollias, Viktoriia Sharmanska, Stefanos Zafeiriou
Automatic facial behavior analysis has a long history of studies in the intersection of computer vision, physiology and psychology. However it is only recently, with the collection…
Video-to-Video Translation for Visual Speech Synthesis
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 domai…
Discovering Fair Representations in the Data Domain
Novi Quadrianto, Viktoriia Sharmanska, Oliver Thomas
Interpretability and fairness are critical in computer vision and machine learning applications, in particular when dealing with human outcomes, e.g. inviting or not inviting for a…
Curriculum Learning of Multiple Tasks
Anastasia Pentina, Viktoriia Sharmanska, Christoph H. Lampert
Sharing information between multiple tasks enables algorithms to achieve good generalization performance even from small amounts of training data. However, in a realistic scenario…
Learning to Transfer Privileged Information
Viktoriia Sharmanska, Novi Quadrianto, Christoph H. Lampert
We introduce a learning framework called learning using privileged information (LUPI) to the computer vision field. We focus on the prototypical computer vision problem of teaching…
Mind the Nuisance: Gaussian Process Classification using Privileged Noise
Daniel Hernández-Lobato, Viktoriia Sharmanska, Kristian Kersting +2
The learning with privileged information setting has recently attracted a lot of attention within the machine learning community, as it allows the integration of additional knowled…
The Supervised IBP: Neighbourhood Preserving Infinite Latent Feature Models
Novi Quadrianto, Viktoriia Sharmanska, David A. Knowles +1
We propose a probabilistic model to infer supervised latent variables in the Hamming space from observed data. Our model allows simultaneous inference of the number of binary laten…