Picture for Viktoriia Sharmanska

Viktoriia Sharmanska

Efficient Online Inference of Vision Transformers by Training-Free Tokenization

Add code
Nov 23, 2024
Viaarxiv icon

Distribution Matching for Multi-Task Learning of Classification Tasks: a Large-Scale Study on Faces & Beyond

Add code
Jan 03, 2024
Viaarxiv icon

Okapi: Generalising Better by Making Statistical Matches Match

Add code
Nov 07, 2022
Viaarxiv icon

Free-HeadGAN: Neural Talking Head Synthesis with Explicit Gaze Control

Add code
Aug 03, 2022
Figure 1 for Free-HeadGAN: Neural Talking Head Synthesis with Explicit Gaze Control
Figure 2 for Free-HeadGAN: Neural Talking Head Synthesis with Explicit Gaze Control
Figure 3 for Free-HeadGAN: Neural Talking Head Synthesis with Explicit Gaze Control
Figure 4 for Free-HeadGAN: Neural Talking Head Synthesis with Explicit Gaze Control
Viaarxiv icon

RealPatch: A Statistical Matching Framework for Model Patching with Real Samples

Add code
Aug 03, 2022
Figure 1 for RealPatch: A Statistical Matching Framework for Model Patching with Real Samples
Figure 2 for RealPatch: A Statistical Matching Framework for Model Patching with Real Samples
Figure 3 for RealPatch: A Statistical Matching Framework for Model Patching with Real Samples
Figure 4 for RealPatch: A Statistical Matching Framework for Model Patching with Real Samples
Viaarxiv icon

DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image

Add code
Apr 11, 2022
Figure 1 for DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image
Figure 2 for DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image
Figure 3 for DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image
Figure 4 for DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image
Viaarxiv icon

Addressing Missing Sources with Adversarial Support-Matching

Add code
Mar 24, 2022
Figure 1 for Addressing Missing Sources with Adversarial Support-Matching
Figure 2 for Addressing Missing Sources with Adversarial Support-Matching
Figure 3 for Addressing Missing Sources with Adversarial Support-Matching
Figure 4 for Addressing Missing Sources with Adversarial Support-Matching
Viaarxiv icon

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

Add code
May 08, 2021
Figure 1 for Distribution Matching for Heterogeneous Multi-Task Learning: a Large-scale Face Study
Figure 2 for Distribution Matching for Heterogeneous Multi-Task Learning: a Large-scale Face Study
Figure 3 for Distribution Matching for Heterogeneous Multi-Task Learning: a Large-scale Face Study
Figure 4 for Distribution Matching for Heterogeneous Multi-Task Learning: a Large-scale Face Study
Viaarxiv icon

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

Add code
Mar 30, 2021
Figure 1 for Head2HeadFS: Video-based Head Reenactment with Few-shot Learning
Figure 2 for Head2HeadFS: Video-based Head Reenactment with Few-shot Learning
Figure 3 for Head2HeadFS: Video-based Head Reenactment with Few-shot Learning
Figure 4 for Head2HeadFS: Video-based Head Reenactment with Few-shot Learning
Viaarxiv icon

HeadGAN: Video-and-Audio-Driven Talking Head Synthesis

Add code
Dec 15, 2020
Figure 1 for HeadGAN: Video-and-Audio-Driven Talking Head Synthesis
Figure 2 for HeadGAN: Video-and-Audio-Driven Talking Head Synthesis
Figure 3 for HeadGAN: Video-and-Audio-Driven Talking Head Synthesis
Figure 4 for HeadGAN: Video-and-Audio-Driven Talking Head Synthesis
Viaarxiv icon