Dimitris Metaxas

papers

1,267

total citations

papers (17)

SVDiff: Compact Parameter Space for Diffusion Fine-Tuning

ICCV 2023arXiv

372

citations

Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness

NEURIPS 2020arXiv

185

citations

DeepTag: An Unsupervised Deep Learning Method for Motion Tracking on Cardiac Tagging Magnetic Resonance Images

CVPR 2021arXiv

citations

Show Me What and Tell Me How: Video Synthesis via Multimodal Conditioning

CVPR 2022arXiv

citations

Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization

CVPR 2021arXiv

citations

Learn distributed GAN with Temporary Discriminators

ECCV 2020arXiv

citations

How to Trace Latent Generative Model Generated Images without Artificial Watermark?

ICML 2024arXiv

citations

OmniLabel: A Challenging Benchmark for Language-Based Object Detection

ICCV 2023arXiv

citations

Neural Deformable Models for 3D Bi-Ventricular Heart Shape Reconstruction and Modeling from 2D Sparse Cardiac Magnetic Resonance Imaging

ICCV 2023arXiv

citations

LEPARD: Learning Explicit Part Discovery for 3D Articulated Shape Reconstruction

NEURIPS 2023

citations

FlowChef: Steering of Rectified Flow Models for Controlled Generations

ICCV 2025

citations

Deep Subspace Clustering with Data Augmentation

NEURIPS 2020

citations

Dimitris Metaxas

papers (17)

SVDiff: Compact Parameter Space for Diffusion Fine-Tuning

Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness

A Topological Filter for Learning with Label Noise

Deep Animation Video Interpolation in the Wild

Improved Transformer for High-Resolution GANs

Global Matching With Overlapping Attention for Optical Flow Estimation

OnlineAugment: Online Data Augmentation with Less Domain Knowledge

DeepTag: An Unsupervised Deep Learning Method for Motion Tracking on Cardiac Tagging Magnetic Resonance Images

Show Me What and Tell Me How: Video Synthesis via Multimodal Conditioning

Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization

Learn distributed GAN with Temporary Discriminators

How to Trace Latent Generative Model Generated Images without Artificial Watermark?

OmniLabel: A Challenging Benchmark for Language-Based Object Detection

Neural Deformable Models for 3D Bi-Ventricular Heart Shape Reconstruction and Modeling from 2D Sparse Cardiac Magnetic Resonance Imaging

LEPARD: Learning Explicit Part Discovery for 3D Articulated Shape Reconstruction

FlowChef: Steering of Rectified Flow Models for Controlled Generations

Deep Subspace Clustering with Data Augmentation

papers (17)

SVDiff: Compact Parameter Space for Diffusion Fine-Tuning

Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness

A Topological Filter for Learning with Label Noise

Deep Animation Video Interpolation in the Wild

Improved Transformer for High-Resolution GANs

Global Matching With Overlapping Attention for Optical Flow Estimation

OnlineAugment: Online Data Augmentation with Less Domain Knowledge

DeepTag: An Unsupervised Deep Learning Method for Motion Tracking on Cardiac Tagging Magnetic Resonance Images

Show Me What and Tell Me How: Video Synthesis via Multimodal Conditioning

Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization

Learn distributed GAN with Temporary Discriminators

How to Trace Latent Generative Model Generated Images without Artificial Watermark?

OmniLabel: A Challenging Benchmark for Language-Based Object Detection

Neural Deformable Models for 3D Bi-Ventricular Heart Shape Reconstruction and Modeling from 2D Sparse Cardiac Magnetic Resonance Imaging

LEPARD: Learning Explicit Part Discovery for 3D Articulated Shape Reconstruction

FlowChef: Steering of Rectified Flow Models for Controlled Generations

Deep Subspace Clustering with Data Augmentation